Responses

Create a model response

client.Responses.New(ctx, body) (*Response, error)

post /responses

Creates a model response. Provide text or image inputs to generate text or JSON outputs. Have the model call your own custom code or use built-in tools like web search or file search to use your own data as input for the model's response.

Parameters

body ResponseNewParams
- Background param.Field[bool]
  
  Whether to run the model response in the background. Learn more.
- ContextManagement param.Field[[]ResponseNewParamsContextManagement]
  
  Context management configuration for this request.
  - Type string
    
    The context management entry type. Currently only 'compaction' is supported.
  - CompactThreshold int64
    
    Token threshold at which compaction should be triggered for this entry.
- Conversation param.Field[ResponseNewParamsConversationUnion]
  
  The conversation that this response belongs to. Items from this conversation are prepended to input_items for this response request. Input items and output items from this response are automatically added to this conversation after this response completes.
  - string
  - type ResponseConversationParamResp struct{…}
    
    The conversation that this response belongs to.
    - ID string
      
      The unique ID of the conversation.
- Include param.Field[[]ResponseIncludable]
  
  Specify additional output data to include in the model response. Currently supported values are:
  - web_search_call.action.sources: Include the sources of the web search tool call.
  - code_interpreter_call.outputs: Includes the outputs of python code execution in code interpreter tool call items.
  - computer_call_output.output.image_url: Include image urls from the computer call output.
  - file_search_call.results: Include the search results of the file search tool call.
  - message.input_image.image_url: Include image urls from the input message.
  - message.output_text.logprobs: Include logprobs with assistant messages.
  - reasoning.encrypted_content: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the store parameter is set to false, or when an organization is enrolled in the zero data retention program).
  - const ResponseIncludableFileSearchCallResults ResponseIncludable = "file_search_call.results"
  - const ResponseIncludableWebSearchCallResults ResponseIncludable = "web_search_call.results"
  - const ResponseIncludableWebSearchCallActionSources ResponseIncludable = "web_search_call.action.sources"
  - const ResponseIncludableMessageInputImageImageURL ResponseIncludable = "message.input_image.image_url"
  - const ResponseIncludableComputerCallOutputOutputImageURL ResponseIncludable = "computer_call_output.output.image_url"
  - const ResponseIncludableCodeInterpreterCallOutputs ResponseIncludable = "code_interpreter_call.outputs"
  - const ResponseIncludableReasoningEncryptedContent ResponseIncludable = "reasoning.encrypted_content"
  - const ResponseIncludableMessageOutputTextLogprobs ResponseIncludable = "message.output_text.logprobs"
- Input param.Field[ResponseNewParamsInputUnion]
  
  Text, image, or file inputs to the model, used to generate a response.
  
  Learn more:
  - Text inputs and outputs
  - Image inputs
  - File inputs
  - Conversation state
  - Function calling
  - string
  - type ResponseInput []ResponseInputItemUnion
    
    A list of one or many input items to the model, containing different content types.
    - type EasyInputMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
      - Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
      - Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
      - Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
    - type ResponseInputItemMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
      - Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
      - Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
      - Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
      - Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
      - ID string
        
        The unique ID of the output message.
      - Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
      - Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
      - Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
      - Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
      - Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
      - ID string
        
        The unique ID of the file search tool call.
      - Queries []string
        
        The queries used to search for files.
      - Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
      - Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
      - Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
      - ID string
        
        The unique ID of the computer call.
      - CallID string
        
        An identifier used when responding to the tool call with output.
      - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
      - Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
      - Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
      - Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
    - type ResponseInputItemComputerCallOutput struct{…}
      
      The output of a computer tool call.
      - CallID string
        
        The ID of the computer tool call that produced the output.
      - Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
      - Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
      - ID string
        
        The ID of the computer tool call output.
      - AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
      - ID string
        
        The unique ID of the web search tool call.
      - Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
      - Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
      - Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
      - Arguments string
        
        A JSON string of the arguments to pass to the function.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Name string
        
        The name of the function to run.
      - Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
      - ID string
        
        The unique ID of the function tool call.
      - Namespace string
        
        The namespace of the function to run.
      - Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
    - type ResponseInputItemFunctionCallOutput struct{…}
      
      The output of a function tool call.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
      - ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
    - type ResponseInputItemToolSearchCall struct{…}
      - Arguments any
        
        The arguments supplied to the tool search call.
      - Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
      - ID string
        
        The unique ID of this tool search call.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
      - Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
    - type ResponseToolSearchOutputItemParamResp struct{…}
      - Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
      - Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
      - ID string
        
        The unique ID of this tool search output.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
      - Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
    - type ResponseInputItemAdditionalTools struct{…}
      - Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
      - Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
      - ID string
        
        The unique ID of this additional tools item.
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
      - ID string
        
        The unique identifier of the reasoning content.
      - Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
      - Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
      - Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
      - EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
      - Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
    - type ResponseCompactionItemParamResp struct{…}
      
      A compaction item generated by the v1/responses/compact API.
      - EncryptedContent string
        
        The encrypted content of the compaction summary.
      - Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
      - ID string
        
        The ID of the compaction item.
    - type ResponseInputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
      - ID string
        
        The unique ID of the image generation call.
      - Result string
        
        The generated image encoded in base64.
      - Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
      - Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
      - ID string
        
        The unique ID of the code interpreter tool call.
      - Code string
        
        The code to run, or null if not available.
      - ContainerID string
        
        The ID of the container used to run the code.
      - Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
      - Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
      - Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
    - type ResponseInputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
      - ID string
        
        The unique ID of the local shell call.
      - Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
      - CallID string
        
        The unique ID of the local shell tool call generated by the model.
      - Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
      - Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
    - type ResponseInputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
      - ID string
        
        The unique ID of the local shell tool call generated by the model.
      - Output string
        
        A JSON string of the output of the local shell tool call.
      - Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
    - type ResponseInputItemShellCall struct{…}
      
      A tool representing a request to execute one or more shell commands.
      - Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
      - ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
      - Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
      - Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
    - type ResponseInputItemShellCallOutput struct{…}
      
      The streamed output items emitted by a shell tool call.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
      - Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
      - ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
      - MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
      - Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
    - type ResponseInputItemApplyPatchCall struct{…}
      
      A tool call representing a request to create, delete, or update files using diff patches.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
      - Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
      - Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
      - ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - type ResponseInputItemApplyPatchCallOutput struct{…}
      
      The streamed output emitted by an apply patch tool call.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
      - Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
      - ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
      - Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
    - type ResponseInputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
      - ID string
        
        The unique ID of the list.
      - ServerLabel string
        
        The label of the MCP server.
      - Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
      - Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
      - Error string
        
        Error message if the server could not list tools.
    - type ResponseInputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
      - ID string
        
        The unique ID of the approval request.
      - Arguments string
        
        A JSON string of arguments for the tool.
      - Name string
        
        The name of the tool to run.
      - ServerLabel string
        
        The label of the MCP server making the request.
      - Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
    - type ResponseInputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
      - ApprovalRequestID string
        
        The ID of the approval request being answered.
      - Approve bool
        
        Whether the request was approved.
      - Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
      - ID string
        
        The unique ID of the approval response
      - Reason string
        
        Optional reason for the decision.
    - type ResponseInputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
      - ID string
        
        The unique ID of the tool call.
      - Arguments string
        
        A JSON string of the arguments passed to the tool.
      - Name string
        
        The name of the tool that was run.
      - ServerLabel string
        
        The label of the MCP server running the tool.
      - Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
      - ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
      - Error string
        
        The error from the tool call, if any.
      - Output string
        
        The output from the tool call.
      - Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
    - type ResponseCustomToolCallOutput struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
      - CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
      - Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
      - ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
      - CallID string
        
        An identifier used to map this custom tool call to a tool call output.
      - Input string
        
        The input for the custom tool call generated by the model.
      - Name string
        
        The name of the custom tool being called.
      - Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
      - ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
      - Namespace string
        
        The namespace of the custom tool being called.
    - type ResponseInputItemCompactionTrigger struct{…}
      
      Compacts the current context. Must be the final input item.
      - Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
    - type ResponseInputItemItemReference struct{…}
      
      An internal identifier for an item to reference.
      - ID string
        
        The ID of the item to reference.
      - Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
- Instructions param.Field[string]
  
  A system (or developer) message inserted into the model's context.
  
  When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
- MaxOutputTokens param.Field[int64]
  
  An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
- MaxToolCalls param.Field[int64]
  
  The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
- Metadata param.Field[Metadata]
  
  Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
  
  Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
- Model param.Field[ResponsesModel]
  
  Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
- Moderation param.Field[ResponseNewParamsModeration]
  
  Configuration for running moderation on the input and output of this response.
  - Model string
    
    The moderation model to use for moderated completions, e.g. 'omni-moderation-latest'.
- ParallelToolCalls param.Field[bool]
  
  Whether to allow the model to run tool calls in parallel.
- PreviousResponseID param.Field[string]
  
  The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
- Prompt param.Field[ResponsePrompt]
  
  Reference to a prompt template and its variables. Learn more.
- PromptCacheKey param.Field[string]
  
  Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
- PromptCacheRetention param.Field[ResponseNewParamsPromptCacheRetention]
  
  The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.
  
  For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:
  - Organizations without ZDR enabled default to 24h.
  - Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.
  - const ResponseNewParamsPromptCacheRetentionInMemory ResponseNewParamsPromptCacheRetention = "in_memory"
  - const ResponseNewParamsPromptCacheRetention24h ResponseNewParamsPromptCacheRetention = "24h"
- Reasoning param.Field[Reasoning]
  
  gpt-5 and o-series models only
  
  Configuration options for reasoning models.
- SafetyIdentifier param.Field[string]
  
  A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
- ServiceTier param.Field[ResponseNewParamsServiceTier]
  
  Specifies the processing type used for serving the request.
  - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
  - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
  - If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
  - When not set, the default behavior is 'auto'.
  When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
  - const ResponseNewParamsServiceTierAuto ResponseNewParamsServiceTier = "auto"
  - const ResponseNewParamsServiceTierDefault ResponseNewParamsServiceTier = "default"
  - const ResponseNewParamsServiceTierFlex ResponseNewParamsServiceTier = "flex"
  - const ResponseNewParamsServiceTierScale ResponseNewParamsServiceTier = "scale"
  - const ResponseNewParamsServiceTierPriority ResponseNewParamsServiceTier = "priority"
- Store param.Field[bool]
  
  Whether to store the generated model response for later retrieval via API.
- ``
- StreamOptions param.Field[ResponseNewParamsStreamOptions]
  
  Options for streaming responses. Only set this when you set stream: true.
  - IncludeObfuscation bool
    
    When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an obfuscation field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set include_obfuscation to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API.
- Temperature param.Field[float64]
  
  What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
- Text param.Field[ResponseTextConfig]
  
  Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
  - Text inputs and outputs
  - Structured Outputs
- ToolChoice param.Field[ResponseNewParamsToolChoiceUnion]
  
  How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.
  - type ToolChoiceOptions string
    
    Controls which (if any) tool is called by the model.
    
    none means the model will not call any tool and instead generates a message.
    
    auto means the model can pick between generating a message or calling one or more tools.
    
    required means the model must call one or more tools.
    - const ToolChoiceOptionsNone ToolChoiceOptions = "none"
    - const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
    - const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
  - type ToolChoiceAllowed struct{…}
    
    Constrains the tools available to the model to a pre-defined set.
    - Mode ToolChoiceAllowedMode
      
      Constrains the tools available to the model to a pre-defined set.
      
      auto allows the model to pick from among the allowed tools and generate a message.
      
      required requires the model to call one or more of the allowed tools.
      - const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
      - const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
    - Tools []map[string, any]
      
      A list of tool definitions that the model should be allowed to call.
      
      For the Responses API, the list of tool definitions might look like:
```
[
  { "type": "function", "name": "get_weather" },
  { "type": "mcp", "server_label": "deepwiki" },
  { "type": "image_generation" }
]
```
    - Type AllowedTools
      
      Allowed tool configuration type. Always allowed_tools.
      - const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
  - type ToolChoiceTypes struct{…}
    
    Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
    - Type ToolChoiceTypesType
      
      The type of hosted tool the model should to use. Learn more about built-in tools.
      
      Allowed values are:
      - file_search
      - web_search_preview
      - computer
      - computer_use_preview
      - computer_use
      - code_interpreter
      - image_generation
      - const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
      - const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
      - const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
      - const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
      - const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
      - const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
      - const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
      - const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
  - type ToolChoiceFunction struct{…}
    
    Use this option to force the model to call a specific function.
    - Name string
      
      The name of the function to call.
    - Type Function
      
      For function calling, the type is always function.
      - const FunctionFunction Function = "function"
  - type ToolChoiceMcp struct{…}
    
    Use this option to force the model to call a specific tool on a remote MCP server.
    - ServerLabel string
      
      The label of the MCP server to use.
    - Type Mcp
      
      For MCP tools, the type is always mcp.
      - const McpMcp Mcp = "mcp"
    - Name string
      
      The name of the tool to call on the server.
  - type ToolChoiceCustom struct{…}
    
    Use this option to force the model to call a specific custom tool.
    - Name string
      
      The name of the custom tool to call.
    - Type Custom
      
      For custom tool calling, the type is always custom.
      - const CustomCustom Custom = "custom"
  - type ToolChoiceApplyPatch struct{…}
    
    Forces the model to call the apply_patch tool when executing a tool call.
    - Type ApplyPatch
      
      The tool to call. Always apply_patch.
      - const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
  - type ToolChoiceShell struct{…}
    
    Forces the model to call the shell tool when a tool call is required.
    - Type Shell
      
      The tool to call. Always shell.
      - const ShellShell Shell = "shell"
- Tools param.Field[[]ToolUnion]
  
  An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
  
  We support the following categories of tools:
  - Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
  - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
  - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
  - type FunctionTool struct{…}
    
    Defines a function in your own code the model can choose to call. Learn more about function calling.
  - type FileSearchTool struct{…}
    
    A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
  - type ComputerTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
  - type ComputerUsePreviewTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
  - type WebSearchTool struct{…}
    
    Search the Internet for sources related to the prompt. Learn more about the web search tool.
  - type ToolMcp struct{…}
    
    Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
  - type ToolCodeInterpreter struct{…}
    
    A tool that runs Python code to help generate a response to a prompt.
  - type ToolImageGeneration struct{…}
    
    A tool that generates images using the GPT image models.
  - type ToolLocalShell struct{…}
    
    A tool that allows the model to execute shell commands in a local environment.
  - type FunctionShellTool struct{…}
    
    A tool that allows the model to execute shell commands.
  - type CustomTool struct{…}
    
    A custom tool that processes input using a specified format. Learn more about custom tools
  - type NamespaceTool struct{…}
    
    Groups function/custom tools under a shared namespace.
  - type ToolSearchTool struct{…}
    
    Hosted or BYOT tool search configuration for deferred tools.
  - type WebSearchPreviewTool struct{…}
    
    This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
  - type ApplyPatchTool struct{…}
    
    Allows the assistant to create, delete, or update files using unified diffs.
- TopLogprobs param.Field[int64]
  
  An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
- TopP param.Field[float64]
  
  An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
  
  We generally recommend altering this or temperature but not both.
- Truncation param.Field[ResponseNewParamsTruncation]
  
  The truncation strategy to use for the model response.
  - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
  - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
  - const ResponseNewParamsTruncationAuto ResponseNewParamsTruncation = "auto"
  - const ResponseNewParamsTruncationDisabled ResponseNewParamsTruncation = "disabled"
- User param.Field[string]
  
  This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.

Returns

type Response struct{…}
- ID string
  
  Unique identifier for this Response.
- CreatedAt float64
  
  Unix timestamp (in seconds) of when this Response was created.
- Error ResponseError
  
  An error object returned when the model fails to generate a Response.
  - Code ResponseErrorCode
    
    The error code for the response.
    - const ResponseErrorCodeServerError ResponseErrorCode = "server_error"
    - const ResponseErrorCodeRateLimitExceeded ResponseErrorCode = "rate_limit_exceeded"
    - const ResponseErrorCodeInvalidPrompt ResponseErrorCode = "invalid_prompt"
    - const ResponseErrorCodeVectorStoreTimeout ResponseErrorCode = "vector_store_timeout"
    - const ResponseErrorCodeInvalidImage ResponseErrorCode = "invalid_image"
    - const ResponseErrorCodeInvalidImageFormat ResponseErrorCode = "invalid_image_format"
    - const ResponseErrorCodeInvalidBase64Image ResponseErrorCode = "invalid_base64_image"
    - const ResponseErrorCodeInvalidImageURL ResponseErrorCode = "invalid_image_url"
    - const ResponseErrorCodeImageTooLarge ResponseErrorCode = "image_too_large"
    - const ResponseErrorCodeImageTooSmall ResponseErrorCode = "image_too_small"
    - const ResponseErrorCodeImageParseError ResponseErrorCode = "image_parse_error"
    - const ResponseErrorCodeImageContentPolicyViolation ResponseErrorCode = "image_content_policy_violation"
    - const ResponseErrorCodeInvalidImageMode ResponseErrorCode = "invalid_image_mode"
    - const ResponseErrorCodeImageFileTooLarge ResponseErrorCode = "image_file_too_large"
    - const ResponseErrorCodeUnsupportedImageMediaType ResponseErrorCode = "unsupported_image_media_type"
    - const ResponseErrorCodeEmptyImageFile ResponseErrorCode = "empty_image_file"
    - const ResponseErrorCodeFailedToDownloadImage ResponseErrorCode = "failed_to_download_image"
    - const ResponseErrorCodeImageFileNotFound ResponseErrorCode = "image_file_not_found"
  - Message string
    
    A human-readable description of the error.
- IncompleteDetails ResponseIncompleteDetails
  
  Details about why the response is incomplete.
  - Reason string
    
    The reason why the response is incomplete.
    - const ResponseIncompleteDetailsReasonMaxOutputTokens ResponseIncompleteDetailsReason = "max_output_tokens"
    - const ResponseIncompleteDetailsReasonContentFilter ResponseIncompleteDetailsReason = "content_filter"
- Instructions ResponseInstructionsUnion
  
  A system (or developer) message inserted into the model's context.
  
  When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
  - string
  - type ResponseInstructionsInputItemList []ResponseInputItemUnion
    
    A list of one or many input items to the model, containing different content types.
    - type EasyInputMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
      - Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
      - Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
      - Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
    - type ResponseInputItemMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
      - Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
      - Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
      - Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
      - Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
      - ID string
        
        The unique ID of the output message.
      - Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
      - Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
      - Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
      - Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
      - Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
      - ID string
        
        The unique ID of the file search tool call.
      - Queries []string
        
        The queries used to search for files.
      - Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
      - Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
      - Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
      - ID string
        
        The unique ID of the computer call.
      - CallID string
        
        An identifier used when responding to the tool call with output.
      - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
      - Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
      - Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
      - Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
    - type ResponseInputItemComputerCallOutput struct{…}
      
      The output of a computer tool call.
      - CallID string
        
        The ID of the computer tool call that produced the output.
      - Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
      - Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
      - ID string
        
        The ID of the computer tool call output.
      - AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
      - ID string
        
        The unique ID of the web search tool call.
      - Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
      - Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
      - Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
      - Arguments string
        
        A JSON string of the arguments to pass to the function.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Name string
        
        The name of the function to run.
      - Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
      - ID string
        
        The unique ID of the function tool call.
      - Namespace string
        
        The namespace of the function to run.
      - Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
    - type ResponseInputItemFunctionCallOutput struct{…}
      
      The output of a function tool call.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
      - ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
    - type ResponseInputItemToolSearchCall struct{…}
      - Arguments any
        
        The arguments supplied to the tool search call.
      - Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
      - ID string
        
        The unique ID of this tool search call.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
      - Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
    - type ResponseToolSearchOutputItemParamResp struct{…}
      - Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
      - Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
      - ID string
        
        The unique ID of this tool search output.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
      - Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
    - type ResponseInputItemAdditionalTools struct{…}
      - Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
      - Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
      - ID string
        
        The unique ID of this additional tools item.
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
      - ID string
        
        The unique identifier of the reasoning content.
      - Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
      - Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
      - Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
      - EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
      - Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
    - type ResponseCompactionItemParamResp struct{…}
      
      A compaction item generated by the v1/responses/compact API.
      - EncryptedContent string
        
        The encrypted content of the compaction summary.
      - Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
      - ID string
        
        The ID of the compaction item.
    - type ResponseInputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
      - ID string
        
        The unique ID of the image generation call.
      - Result string
        
        The generated image encoded in base64.
      - Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
      - Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
      - ID string
        
        The unique ID of the code interpreter tool call.
      - Code string
        
        The code to run, or null if not available.
      - ContainerID string
        
        The ID of the container used to run the code.
      - Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
      - Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
      - Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
    - type ResponseInputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
      - ID string
        
        The unique ID of the local shell call.
      - Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
      - CallID string
        
        The unique ID of the local shell tool call generated by the model.
      - Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
      - Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
    - type ResponseInputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
      - ID string
        
        The unique ID of the local shell tool call generated by the model.
      - Output string
        
        A JSON string of the output of the local shell tool call.
      - Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
    - type ResponseInputItemShellCall struct{…}
      
      A tool representing a request to execute one or more shell commands.
      - Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
      - ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
      - Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
      - Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
    - type ResponseInputItemShellCallOutput struct{…}
      
      The streamed output items emitted by a shell tool call.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
      - Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
      - ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
      - MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
      - Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
    - type ResponseInputItemApplyPatchCall struct{…}
      
      A tool call representing a request to create, delete, or update files using diff patches.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
      - Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
      - Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
      - ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - type ResponseInputItemApplyPatchCallOutput struct{…}
      
      The streamed output emitted by an apply patch tool call.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
      - Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
      - ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
      - Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
    - type ResponseInputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
      - ID string
        
        The unique ID of the list.
      - ServerLabel string
        
        The label of the MCP server.
      - Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
      - Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
      - Error string
        
        Error message if the server could not list tools.
    - type ResponseInputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
      - ID string
        
        The unique ID of the approval request.
      - Arguments string
        
        A JSON string of arguments for the tool.
      - Name string
        
        The name of the tool to run.
      - ServerLabel string
        
        The label of the MCP server making the request.
      - Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
    - type ResponseInputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
      - ApprovalRequestID string
        
        The ID of the approval request being answered.
      - Approve bool
        
        Whether the request was approved.
      - Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
      - ID string
        
        The unique ID of the approval response
      - Reason string
        
        Optional reason for the decision.
    - type ResponseInputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
      - ID string
        
        The unique ID of the tool call.
      - Arguments string
        
        A JSON string of the arguments passed to the tool.
      - Name string
        
        The name of the tool that was run.
      - ServerLabel string
        
        The label of the MCP server running the tool.
      - Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
      - ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
      - Error string
        
        The error from the tool call, if any.
      - Output string
        
        The output from the tool call.
      - Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
    - type ResponseCustomToolCallOutput struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
      - CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
      - Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
      - ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
      - CallID string
        
        An identifier used to map this custom tool call to a tool call output.
      - Input string
        
        The input for the custom tool call generated by the model.
      - Name string
        
        The name of the custom tool being called.
      - Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
      - ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
      - Namespace string
        
        The namespace of the custom tool being called.
    - type ResponseInputItemCompactionTrigger struct{…}
      
      Compacts the current context. Must be the final input item.
      - Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
    - type ResponseInputItemItemReference struct{…}
      
      An internal identifier for an item to reference.
      - ID string
        
        The ID of the item to reference.
      - Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
- Metadata Metadata
  
  Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
  
  Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
- Model ResponsesModel
  
  Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
  - string
  - type ChatModel string
    - const ChatModelGPT5_4 ChatModel = "gpt-5.4"
    - const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"
    - const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"
    - const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"
    - const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"
    - const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"
    - const ChatModelGPT5_2 ChatModel = "gpt-5.2"
    - const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"
    - const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"
    - const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"
    - const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"
    - const ChatModelGPT5_1 ChatModel = "gpt-5.1"
    - const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"
    - const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"
    - const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"
    - const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"
    - const ChatModelGPT5 ChatModel = "gpt-5"
    - const ChatModelGPT5Mini ChatModel = "gpt-5-mini"
    - const ChatModelGPT5Nano ChatModel = "gpt-5-nano"
    - const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"
    - const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"
    - const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"
    - const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"
    - const ChatModelGPT4_1 ChatModel = "gpt-4.1"
    - const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"
    - const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"
    - const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"
    - const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"
    - const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"
    - const ChatModelO4Mini ChatModel = "o4-mini"
    - const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"
    - const ChatModelO3 ChatModel = "o3"
    - const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"
    - const ChatModelO3Mini ChatModel = "o3-mini"
    - const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"
    - const ChatModelO1 ChatModel = "o1"
    - const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"
    - const ChatModelO1Preview ChatModel = "o1-preview"
    - const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"
    - const ChatModelO1Mini ChatModel = "o1-mini"
    - const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"
    - const ChatModelGPT4o ChatModel = "gpt-4o"
    - const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"
    - const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"
    - const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"
    - const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"
    - const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"
    - const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"
    - const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"
    - const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"
    - const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"
    - const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"
    - const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"
    - const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"
    - const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"
    - const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"
    - const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"
    - const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"
    - const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"
    - const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"
    - const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"
    - const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"
    - const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"
    - const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"
    - const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"
    - const ChatModelGPT4 ChatModel = "gpt-4"
    - const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"
    - const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"
    - const ChatModelGPT4_32k ChatModel = "gpt-4-32k"
    - const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"
    - const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"
    - const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"
    - const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"
    - const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"
    - const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"
    - const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"
    - const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"
    - const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"
  - type ResponsesModel string
    - const ResponsesModelO1Pro ResponsesModel = "o1-pro"
    - const ResponsesModelO1Pro2025_03_19 ResponsesModel = "o1-pro-2025-03-19"
    - const ResponsesModelO3Pro ResponsesModel = "o3-pro"
    - const ResponsesModelO3Pro2025_06_10 ResponsesModel = "o3-pro-2025-06-10"
    - const ResponsesModelO3DeepResearch ResponsesModel = "o3-deep-research"
    - const ResponsesModelO3DeepResearch2025_06_26 ResponsesModel = "o3-deep-research-2025-06-26"
    - const ResponsesModelO4MiniDeepResearch ResponsesModel = "o4-mini-deep-research"
    - const ResponsesModelO4MiniDeepResearch2025_06_26 ResponsesModel = "o4-mini-deep-research-2025-06-26"
    - const ResponsesModelComputerUsePreview ResponsesModel = "computer-use-preview"
    - const ResponsesModelComputerUsePreview2025_03_11 ResponsesModel = "computer-use-preview-2025-03-11"
    - const ResponsesModelGPT5Codex ResponsesModel = "gpt-5-codex"
    - const ResponsesModelGPT5Pro ResponsesModel = "gpt-5-pro"
    - const ResponsesModelGPT5Pro2025_10_06 ResponsesModel = "gpt-5-pro-2025-10-06"
    - const ResponsesModelGPT5_1CodexMax ResponsesModel = "gpt-5.1-codex-max"
- Object Response
  
  The object type of this resource - always set to response.
  - const ResponseResponse Response = "response"
- Output []ResponseOutputItemUnion
  
  An array of content items generated by the model.
  - The length and order of items in the output array is dependent on the model's response.
  - Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.
  - type ResponseOutputMessage struct{…}
    
    An output message from the model.
  - type ResponseFileSearchToolCall struct{…}
    
    The results of a file search tool call. See the file search guide for more information.
  - type ResponseFunctionToolCall struct{…}
    
    A tool call to run a function. See the function calling guide for more information.
  - type ResponseFunctionToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the function call tool output.
    - CallID string
      
      The unique ID of the function tool call generated by the model.
    - Output ResponseFunctionToolCallOutputItemOutputUnion
      
      The output from the function call generated by your code. Can be a string or an list of output content.
      - string
      - type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
    - Status ResponseFunctionToolCallOutputItemStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
      - const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
      - const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
    - Type FunctionCallOutput
      
      The type of the function tool call output. Always function_call_output.
      - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseFunctionWebSearch struct{…}
    
    The results of a web search tool call. See the web search guide for more information.
  - type ResponseComputerToolCall struct{…}
    
    A tool call to a computer use tool. See the computer use guide for more information.
  - type ResponseComputerToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the computer call tool output.
    - CallID string
      
      The ID of the computer tool call that produced the output.
    - Output ResponseComputerToolCallOutputScreenshot
      
      A computer screenshot image used with the computer use tool.
    - Status ResponseComputerToolCallOutputItemStatus
      
      The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
      - const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
      - const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
      - const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
      - const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
    - Type ComputerCallOutput
      
      The type of the computer tool call output. Always computer_call_output.
      - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
    - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
      
      The safety checks reported by the API that have been acknowledged by the developer.
      - ID string
        
        The ID of the pending safety check.
      - Code string
        
        The type of the pending safety check.
      - Message string
        
        Details about the pending safety check.
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseReasoningItem struct{…}
    
    A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
  - type ResponseToolSearchCall struct{…}
    - ID string
      
      The unique ID of the tool search call item.
    - Arguments any
      
      Arguments used for the tool search call.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchCallExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
      - const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
    - Status ResponseToolSearchCallStatus
      
      The status of the tool search call item that was recorded.
      - const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
      - const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
      - const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
    - Type ToolSearchCall
      
      The type of the item. Always tool_search_call.
      - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseToolSearchOutputItem struct{…}
    - ID string
      
      The unique ID of the tool search output item.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchOutputItemExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
      - const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
    - Status ResponseToolSearchOutputItemStatus
      
      The status of the tool search output item that was recorded.
      - const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
      - const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
      - const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
    - Tools []ToolUnion
      
      The loaded tool definitions returned by tool search.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - Type ToolSearchOutput
      
      The type of the item. Always tool_search_output.
      - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemAdditionalTools struct{…}
    - ID string
      
      The unique ID of the additional tools item.
    - Role string
      
      The role that provided the additional tools.
      - const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
      - const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
      - const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
      - const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
      - const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
      - const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
      - const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
      - const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
    - Tools []ToolUnion
      
      The additional tool definitions made available at this item.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - Type AdditionalTools
      
      The type of the item. Always additional_tools.
      - const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
  - type ResponseCompactionItem struct{…}
    
    A compaction item generated by the v1/responses/compact API.
    - ID string
      
      The unique ID of the compaction item.
    - EncryptedContent string
      
      The encrypted content that was produced by compaction.
    - Type Compaction
      
      The type of the item. Always compaction.
      - const CompactionCompaction Compaction = "compaction"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemImageGenerationCall struct{…}
    
    An image generation request made by the model.
    - ID string
      
      The unique ID of the image generation call.
    - Result string
      
      The generated image encoded in base64.
    - Status string
      
      The status of the image generation call.
      - const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
      - const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
      - const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
      - const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
    - Type ImageGenerationCall
      
      The type of the image generation call. Always image_generation_call.
      - const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
  - type ResponseCodeInterpreterToolCall struct{…}
    
    A tool call to run code.
  - type ResponseOutputItemLocalShellCall struct{…}
    
    A tool call to run a command on the local shell.
    - ID string
      
      The unique ID of the local shell call.
    - Action ResponseOutputItemLocalShellCallAction
      
      Execute a shell command on the server.
      - Command []string
        
        The command to run.
      - Env map[string, string]
        
        Environment variables to set for the command.
      - Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
      - User string
        
        Optional user to run the command as.
      - WorkingDirectory string
        
        Optional working directory to run the command in.
    - CallID string
      
      The unique ID of the local shell tool call generated by the model.
    - Status string
      
      The status of the local shell call.
      - const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
      - const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
    - Type LocalShellCall
      
      The type of the local shell call. Always local_shell_call.
      - const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
  - type ResponseOutputItemLocalShellCallOutput struct{…}
    
    The output of a local shell tool call.
    - ID string
      
      The unique ID of the local shell tool call generated by the model.
    - Output string
      
      A JSON string of the output of the local shell tool call.
    - Type LocalShellCallOutput
      
      The type of the local shell tool call output. Always local_shell_call_output.
      - const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete.
      - const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
      - const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
  - type ResponseFunctionShellToolCall struct{…}
    
    A tool call that executes one or more shell commands in a managed environment.
    - ID string
      
      The unique ID of the shell tool call. Populated when this item is returned via API.
    - Action ResponseFunctionShellToolCallAction
      
      The shell commands and limits that describe how to run the tool call.
      - Commands []string
      - MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - Environment ResponseFunctionShellToolCallEnvironmentUnion
      
      Represents the use of a local environment to perform shell actions.
      - type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
      - type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
    - Status ResponseFunctionShellToolCallStatus
      
      The status of the shell call. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
      - const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
      - const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
    - Type ShellCall
      
      The type of the item. Always shell_call.
      - const ShellCallShellCall ShellCall = "shell_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseFunctionShellToolCallOutput struct{…}
    
    The output of a shell tool call that was emitted.
    - ID string
      
      The unique ID of the shell call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - MaxOutputLength int64
      
      The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
    - Output []ResponseFunctionShellToolCallOutputOutput
      
      An array of shell call output contents
      - Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
      - Stderr string
        
        The standard error output that was captured.
      - Stdout string
        
        The standard output that was captured.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - Status ResponseFunctionShellToolCallOutputStatus
      
      The status of the shell call output. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
      - const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
      - const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
    - Type ShellCallOutput
      
      The type of the shell call output. Always shell_call_output.
      - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseApplyPatchToolCall struct{…}
    
    A tool call that applies file diffs by creating, deleting, or updating files.
    - ID string
      
      The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Operation ResponseApplyPatchToolCallOperationUnion
      
      One of the create_file, delete_file, or update_file operations applied via apply_patch.
      - type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
      - type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
      - type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
    - Status ResponseApplyPatchToolCallStatus
      
      The status of the apply patch tool call. One of in_progress or completed.
      - const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
      - const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
    - Type ApplyPatchCall
      
      The type of the item. Always apply_patch_call.
      - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseApplyPatchToolCallOutput struct{…}
    
    The output emitted by an apply patch tool call.
    - ID string
      
      The unique ID of the apply patch tool call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Status ResponseApplyPatchToolCallOutputStatus
      
      The status of the apply patch tool call output. One of completed or failed.
      - const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
      - const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
    - Type ApplyPatchCallOutput
      
      The type of the item. Always apply_patch_call_output.
      - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
    - CreatedBy string
      
      The ID of the entity that created this tool call output.
    - Output string
      
      Optional textual output returned by the apply patch tool.
  - type ResponseOutputItemMcpCall struct{…}
    
    An invocation of a tool on an MCP server.
    - ID string
      
      The unique ID of the tool call.
    - Arguments string
      
      A JSON string of the arguments passed to the tool.
    - Name string
      
      The name of the tool that was run.
    - ServerLabel string
      
      The label of the MCP server running the tool.
    - Type McpCall
      
      The type of the item. Always mcp_call.
      - const McpCallMcpCall McpCall = "mcp_call"
    - ApprovalRequestID string
      
      Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
    - Error string
      
      The error from the tool call, if any.
    - Output string
      
      The output from the tool call.
    - Status string
      
      The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
      - const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
      - const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
      - const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
      - const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
      - const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
  - type ResponseOutputItemMcpListTools struct{…}
    
    A list of tools available on an MCP server.
    - ID string
      
      The unique ID of the list.
    - ServerLabel string
      
      The label of the MCP server.
    - Tools []ResponseOutputItemMcpListToolsTool
      
      The tools available on the server.
      - InputSchema any
        
        The JSON schema describing the tool's input.
      - Name string
        
        The name of the tool.
      - Annotations any
        
        Additional annotations about the tool.
      - Description string
        
        The description of the tool.
    - Type McpListTools
      
      The type of the item. Always mcp_list_tools.
      - const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
    - Error string
      
      Error message if the server could not list tools.
  - type ResponseOutputItemMcpApprovalRequest struct{…}
    
    A request for human approval of a tool invocation.
    - ID string
      
      The unique ID of the approval request.
    - Arguments string
      
      A JSON string of arguments for the tool.
    - Name string
      
      The name of the tool to run.
    - ServerLabel string
      
      The label of the MCP server making the request.
    - Type McpApprovalRequest
      
      The type of the item. Always mcp_approval_request.
      - const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
  - type ResponseOutputItemMcpApprovalResponse struct{…}
    
    A response to an MCP approval request.
    - ID string
      
      The unique ID of the approval response
    - ApprovalRequestID string
      
      The ID of the approval request being answered.
    - Approve bool
      
      Whether the request was approved.
    - Type McpApprovalResponse
      
      The type of the item. Always mcp_approval_response.
      - const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
    - Reason string
      
      Optional reason for the decision.
  - type ResponseCustomToolCall struct{…}
    
    A call to a custom tool created by the model.
  - type ResponseCustomToolCallOutputItem struct{…}
    
    The output of a custom tool call from your code, being sent back to the model.
    - ID string
      
      The unique ID of the custom tool call output item.
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
      - const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
      - const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
    - CreatedBy string
      
      The identifier of the actor that created the item.
- ParallelToolCalls bool
  
  Whether to allow the model to run tool calls in parallel.
- Temperature float64
  
  What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
- ToolChoice ResponseToolChoiceUnion
  
  How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.
  - type ToolChoiceOptions string
    
    Controls which (if any) tool is called by the model.
    
    none means the model will not call any tool and instead generates a message.
    
    auto means the model can pick between generating a message or calling one or more tools.
    
    required means the model must call one or more tools.
    - const ToolChoiceOptionsNone ToolChoiceOptions = "none"
    - const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
    - const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
  - type ToolChoiceAllowed struct{…}
    
    Constrains the tools available to the model to a pre-defined set.
    - Mode ToolChoiceAllowedMode
      
      Constrains the tools available to the model to a pre-defined set.
      
      auto allows the model to pick from among the allowed tools and generate a message.
      
      required requires the model to call one or more of the allowed tools.
      - const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
      - const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
    - Tools []map[string, any]
      
      A list of tool definitions that the model should be allowed to call.
      
      For the Responses API, the list of tool definitions might look like:
```
[
  { "type": "function", "name": "get_weather" },
  { "type": "mcp", "server_label": "deepwiki" },
  { "type": "image_generation" }
]
```
    - Type AllowedTools
      
      Allowed tool configuration type. Always allowed_tools.
      - const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
  - type ToolChoiceTypes struct{…}
    
    Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
    - Type ToolChoiceTypesType
      
      The type of hosted tool the model should to use. Learn more about built-in tools.
      
      Allowed values are:
      - file_search
      - web_search_preview
      - computer
      - computer_use_preview
      - computer_use
      - code_interpreter
      - image_generation
      - const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
      - const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
      - const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
      - const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
      - const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
      - const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
      - const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
      - const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
  - type ToolChoiceFunction struct{…}
    
    Use this option to force the model to call a specific function.
    - Name string
      
      The name of the function to call.
    - Type Function
      
      For function calling, the type is always function.
      - const FunctionFunction Function = "function"
  - type ToolChoiceMcp struct{…}
    
    Use this option to force the model to call a specific tool on a remote MCP server.
    - ServerLabel string
      
      The label of the MCP server to use.
    - Type Mcp
      
      For MCP tools, the type is always mcp.
      - const McpMcp Mcp = "mcp"
    - Name string
      
      The name of the tool to call on the server.
  - type ToolChoiceCustom struct{…}
    
    Use this option to force the model to call a specific custom tool.
    - Name string
      
      The name of the custom tool to call.
    - Type Custom
      
      For custom tool calling, the type is always custom.
      - const CustomCustom Custom = "custom"
  - type ToolChoiceApplyPatch struct{…}
    
    Forces the model to call the apply_patch tool when executing a tool call.
    - Type ApplyPatch
      
      The tool to call. Always apply_patch.
      - const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
  - type ToolChoiceShell struct{…}
    
    Forces the model to call the shell tool when a tool call is required.
    - Type Shell
      
      The tool to call. Always shell.
      - const ShellShell Shell = "shell"
- Tools []ToolUnion
  
  An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
  
  We support the following categories of tools:
  - Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
  - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
  - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
  - type FunctionTool struct{…}
    
    Defines a function in your own code the model can choose to call. Learn more about function calling.
  - type FileSearchTool struct{…}
    
    A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
  - type ComputerTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
  - type ComputerUsePreviewTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
  - type WebSearchTool struct{…}
    
    Search the Internet for sources related to the prompt. Learn more about the web search tool.
  - type ToolMcp struct{…}
    
    Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
  - type ToolCodeInterpreter struct{…}
    
    A tool that runs Python code to help generate a response to a prompt.
  - type ToolImageGeneration struct{…}
    
    A tool that generates images using the GPT image models.
  - type ToolLocalShell struct{…}
    
    A tool that allows the model to execute shell commands in a local environment.
  - type FunctionShellTool struct{…}
    
    A tool that allows the model to execute shell commands.
  - type CustomTool struct{…}
    
    A custom tool that processes input using a specified format. Learn more about custom tools
  - type NamespaceTool struct{…}
    
    Groups function/custom tools under a shared namespace.
  - type ToolSearchTool struct{…}
    
    Hosted or BYOT tool search configuration for deferred tools.
  - type WebSearchPreviewTool struct{…}
    
    This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
  - type ApplyPatchTool struct{…}
    
    Allows the assistant to create, delete, or update files using unified diffs.
- TopP float64
  
  An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
  
  We generally recommend altering this or temperature but not both.
- Background bool
  
  Whether to run the model response in the background. Learn more.
- CompletedAt float64
  
  Unix timestamp (in seconds) of when this Response was completed. Only present when the status is completed.
- Conversation ResponseConversation
  
  The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
  - ID string
    
    The unique ID of the conversation that this response was associated with.
- MaxOutputTokens int64
  
  An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
- MaxToolCalls int64
  
  The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
- Moderation ResponseModeration
  
  Moderation results for the response input and output, if moderated completions were requested.
  - Input ResponseModerationInputUnion
    
    Moderation for the response input.
    - type ResponseModerationInputModerationResult struct{…}
      
      A moderation result produced for the response input or output.
      - Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
      - CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeText ResponseModerationInputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeImage ResponseModerationInputModerationResultCategoryAppliedInputType = "image"
      - CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
      - Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
      - Model string
        
        The moderation model that produced this result.
      - Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
    - type ResponseModerationInputError struct{…}
      
      An error produced while attempting moderation for the response input or output.
      - Code string
        
        The error code.
      - Message string
        
        The error message.
      - Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
  - Output ResponseModerationOutputUnion
    
    Moderation for the response output.
    - type ResponseModerationOutputModerationResult struct{…}
      
      A moderation result produced for the response input or output.
      - Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
      - CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeText ResponseModerationOutputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeImage ResponseModerationOutputModerationResultCategoryAppliedInputType = "image"
      - CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
      - Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
      - Model string
        
        The moderation model that produced this result.
      - Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
    - type ResponseModerationOutputError struct{…}
      
      An error produced while attempting moderation for the response input or output.
      - Code string
        
        The error code.
      - Message string
        
        The error message.
      - Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
- PreviousResponseID string
  
  The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
- Prompt ResponsePrompt
  
  Reference to a prompt template and its variables. Learn more.
  - ID string
    
    The unique identifier of the prompt template to use.
  - Variables map[string, ResponsePromptVariableUnion]
    
    Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
    - string
    - type ResponseInputText struct{…}
      
      A text input to the model.
    - type ResponseInputImage struct{…}
      
      An image input to the model. Learn about image inputs.
    - type ResponseInputFile struct{…}
      
      A file input to the model.
  - Version string
    
    Optional version of the prompt template.
- PromptCacheKey string
  
  Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
- PromptCacheRetention ResponsePromptCacheRetention
  
  The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.
  
  For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:
  - Organizations without ZDR enabled default to 24h.
  - Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.
  - const ResponsePromptCacheRetentionInMemory ResponsePromptCacheRetention = "in_memory"
  - const ResponsePromptCacheRetention24h ResponsePromptCacheRetention = "24h"
- Reasoning Reasoning
  
  gpt-5 and o-series models only
  
  Configuration options for reasoning models.
  - Context ReasoningContext
    
    Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
    - const ReasoningContextAuto ReasoningContext = "auto"
    - const ReasoningContextCurrentTurn ReasoningContext = "current_turn"
    - const ReasoningContextAllTurns ReasoningContext = "all_turns"
  - Effort ReasoningEffort
    
    Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
    - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
    - All models before gpt-5.1 default to medium reasoning effort, and do not support none.
    - The gpt-5-pro model defaults to (and only supports) high reasoning effort.
    - xhigh is supported for all models after gpt-5.1-codex-max.
    - const ReasoningEffortNone ReasoningEffort = "none"
    - const ReasoningEffortMinimal ReasoningEffort = "minimal"
    - const ReasoningEffortLow ReasoningEffort = "low"
    - const ReasoningEffortMedium ReasoningEffort = "medium"
    - const ReasoningEffortHigh ReasoningEffort = "high"
    - const ReasoningEffortXhigh ReasoningEffort = "xhigh"
  - GenerateSummary ReasoningGenerateSummary
    
    Deprecated: use summary instead.
    
    A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
    - const ReasoningGenerateSummaryAuto ReasoningGenerateSummary = "auto"
    - const ReasoningGenerateSummaryConcise ReasoningGenerateSummary = "concise"
    - const ReasoningGenerateSummaryDetailed ReasoningGenerateSummary = "detailed"
  - Summary ReasoningSummary
    
    A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
    
    concise is supported for computer-use-preview models and all reasoning models after gpt-5.
    - const ReasoningSummaryAuto ReasoningSummary = "auto"
    - const ReasoningSummaryConcise ReasoningSummary = "concise"
    - const ReasoningSummaryDetailed ReasoningSummary = "detailed"
- SafetyIdentifier string
  
  A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
- ServiceTier ResponseServiceTier
  
  Specifies the processing type used for serving the request.
  - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
  - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
  - If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
  - When not set, the default behavior is 'auto'.
  When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
  - const ResponseServiceTierAuto ResponseServiceTier = "auto"
  - const ResponseServiceTierDefault ResponseServiceTier = "default"
  - const ResponseServiceTierFlex ResponseServiceTier = "flex"
  - const ResponseServiceTierScale ResponseServiceTier = "scale"
  - const ResponseServiceTierPriority ResponseServiceTier = "priority"
- Status ResponseStatus
  
  The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
  - const ResponseStatusCompleted ResponseStatus = "completed"
  - const ResponseStatusFailed ResponseStatus = "failed"
  - const ResponseStatusInProgress ResponseStatus = "in_progress"
  - const ResponseStatusCancelled ResponseStatus = "cancelled"
  - const ResponseStatusQueued ResponseStatus = "queued"
  - const ResponseStatusIncomplete ResponseStatus = "incomplete"
- Text ResponseTextConfig
  
  Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
  - Text inputs and outputs
  - Structured Outputs
  - Format ResponseFormatTextConfigUnion
    
    An object specifying the format that the model must output.
    
    Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
    
    The default format is { "type": "text" } with no additional options.
    
    Not recommended for gpt-4o and newer models:
    
    Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
    - type ResponseFormatText struct{…}
      
      Default response format. Used to generate text responses.
      - Type Text
        
        The type of response format being defined. Always text.
        
        const TextText Text = "text"
    - type ResponseFormatTextJSONSchemaConfig struct{…}
      
      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
      - Name string
        
        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
      - Schema map[string, any]
        
        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
      - Type JSONSchema
        
        The type of response format being defined. Always json_schema.
        
        const JSONSchemaJSONSchema JSONSchema = "json_schema"
      - Description string
        
        A description of what the response format is for, used by the model to determine how to respond in the format.
      - Strict bool
        
        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
    - type ResponseFormatJSONObject struct{…}
      
      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
      - Type JSONObject
        
        The type of response format being defined. Always json_object.
        
        const JSONObjectJSONObject JSONObject = "json_object"
  - Verbosity ResponseTextConfigVerbosity
    
    Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
    - const ResponseTextConfigVerbosityLow ResponseTextConfigVerbosity = "low"
    - const ResponseTextConfigVerbosityMedium ResponseTextConfigVerbosity = "medium"
    - const ResponseTextConfigVerbosityHigh ResponseTextConfigVerbosity = "high"
- TopLogprobs int64
  
  An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
- Truncation ResponseTruncation
  
  The truncation strategy to use for the model response.
  - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
  - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
  - const ResponseTruncationAuto ResponseTruncation = "auto"
  - const ResponseTruncationDisabled ResponseTruncation = "disabled"
- Usage ResponseUsage
  
  Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
  - InputTokens int64
    
    The number of input tokens.
  - InputTokensDetails ResponseUsageInputTokensDetails
    
    A detailed breakdown of the input tokens.
    - CachedTokens int64
      
      The number of tokens that were retrieved from the cache. More on prompt caching.
  - OutputTokens int64
    
    The number of output tokens.
  - OutputTokensDetails ResponseUsageOutputTokensDetails
    
    A detailed breakdown of the output tokens.
    - ReasoningTokens int64
      
      The number of reasoning tokens.
  - TotalTokens int64
    
    The total number of tokens used.
- User string
  
  This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
  "github.com/openai/openai-go/responses"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  response, err := client.Responses.New(context.TODO(), responses.ResponseNewParams{

  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", response.ID)
}

Response

{
  "id": "id",
  "created_at": 0,
  "error": {
    "code": "server_error",
    "message": "message"
  },
  "incomplete_details": {
    "reason": "max_output_tokens"
  },
  "instructions": "string",
  "metadata": {
    "foo": "string"
  },
  "model": "gpt-5.1",
  "object": "response",
  "output": [
    {
      "id": "id",
      "content": [
        {
          "annotations": [
            {
              "file_id": "file_id",
              "filename": "filename",
              "index": 0,
              "type": "file_citation"
            }
          ],
          "text": "text",
          "type": "output_text",
          "logprobs": [
            {
              "token": "token",
              "bytes": [
                0
              ],
              "logprob": 0,
              "top_logprobs": [
                {
                  "token": "token",
                  "bytes": [
                    0
                  ],
                  "logprob": 0
                }
              ]
            }
          ]
        }
      ],
      "role": "assistant",
      "status": "in_progress",
      "type": "message",
      "phase": "commentary"
    }
  ],
  "parallel_tool_calls": true,
  "temperature": 1,
  "tool_choice": "none",
  "tools": [
    {
      "name": "name",
      "parameters": {
        "foo": "bar"
      },
      "strict": true,
      "type": "function",
      "defer_loading": true,
      "description": "description"
    }
  ],
  "top_p": 1,
  "background": true,
  "completed_at": 0,
  "conversation": {
    "id": "id"
  },
  "max_output_tokens": 0,
  "max_tool_calls": 0,
  "moderation": {
    "input": {
      "categories": {
        "foo": true
      },
      "category_applied_input_types": {
        "foo": [
          "text"
        ]
      },
      "category_scores": {
        "foo": 0
      },
      "flagged": true,
      "model": "model",
      "type": "moderation_result"
    },
    "output": {
      "categories": {
        "foo": true
      },
      "category_applied_input_types": {
        "foo": [
          "text"
        ]
      },
      "category_scores": {
        "foo": 0
      },
      "flagged": true,
      "model": "model",
      "type": "moderation_result"
    }
  },
  "output_text": "output_text",
  "previous_response_id": "previous_response_id",
  "prompt": {
    "id": "id",
    "variables": {
      "foo": "string"
    },
    "version": "version"
  },
  "prompt_cache_key": "prompt-cache-key-1234",
  "prompt_cache_retention": "in_memory",
  "reasoning": {
    "context": "auto",
    "effort": "none",
    "generate_summary": "auto",
    "summary": "auto"
  },
  "safety_identifier": "safety-identifier-1234",
  "service_tier": "auto",
  "status": "completed",
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "low"
  },
  "top_logprobs": 0,
  "truncation": "auto",
  "usage": {
    "input_tokens": 0,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 0,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 0
  },
  "user": "user-1234"
}

Get a model response

client.Responses.Get(ctx, responseID, query) (*Response, error)

get /responses/{response_id}

Retrieves a model response with the given ID.

Parameters

responseID string
query ResponseGetParams
- Include param.Field[[]ResponseIncludable]
  
  Additional fields to include in the response. See the include parameter for Response creation above for more information.
  - const ResponseIncludableFileSearchCallResults ResponseIncludable = "file_search_call.results"
  - const ResponseIncludableWebSearchCallResults ResponseIncludable = "web_search_call.results"
  - const ResponseIncludableWebSearchCallActionSources ResponseIncludable = "web_search_call.action.sources"
  - const ResponseIncludableMessageInputImageImageURL ResponseIncludable = "message.input_image.image_url"
  - const ResponseIncludableComputerCallOutputOutputImageURL ResponseIncludable = "computer_call_output.output.image_url"
  - const ResponseIncludableCodeInterpreterCallOutputs ResponseIncludable = "code_interpreter_call.outputs"
  - const ResponseIncludableReasoningEncryptedContent ResponseIncludable = "reasoning.encrypted_content"
  - const ResponseIncludableMessageOutputTextLogprobs ResponseIncludable = "message.output_text.logprobs"
- IncludeObfuscation param.Field[bool]
  
  When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an obfuscation field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set include_obfuscation to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API.
- StartingAfter param.Field[int64]
  
  The sequence number of the event after which to start streaming.
- ``

Returns

type Response struct{…}
- ID string
  
  Unique identifier for this Response.
- CreatedAt float64
  
  Unix timestamp (in seconds) of when this Response was created.
- Error ResponseError
  
  An error object returned when the model fails to generate a Response.
  - Code ResponseErrorCode
    
    The error code for the response.
    - const ResponseErrorCodeServerError ResponseErrorCode = "server_error"
    - const ResponseErrorCodeRateLimitExceeded ResponseErrorCode = "rate_limit_exceeded"
    - const ResponseErrorCodeInvalidPrompt ResponseErrorCode = "invalid_prompt"
    - const ResponseErrorCodeVectorStoreTimeout ResponseErrorCode = "vector_store_timeout"
    - const ResponseErrorCodeInvalidImage ResponseErrorCode = "invalid_image"
    - const ResponseErrorCodeInvalidImageFormat ResponseErrorCode = "invalid_image_format"
    - const ResponseErrorCodeInvalidBase64Image ResponseErrorCode = "invalid_base64_image"
    - const ResponseErrorCodeInvalidImageURL ResponseErrorCode = "invalid_image_url"
    - const ResponseErrorCodeImageTooLarge ResponseErrorCode = "image_too_large"
    - const ResponseErrorCodeImageTooSmall ResponseErrorCode = "image_too_small"
    - const ResponseErrorCodeImageParseError ResponseErrorCode = "image_parse_error"
    - const ResponseErrorCodeImageContentPolicyViolation ResponseErrorCode = "image_content_policy_violation"
    - const ResponseErrorCodeInvalidImageMode ResponseErrorCode = "invalid_image_mode"
    - const ResponseErrorCodeImageFileTooLarge ResponseErrorCode = "image_file_too_large"
    - const ResponseErrorCodeUnsupportedImageMediaType ResponseErrorCode = "unsupported_image_media_type"
    - const ResponseErrorCodeEmptyImageFile ResponseErrorCode = "empty_image_file"
    - const ResponseErrorCodeFailedToDownloadImage ResponseErrorCode = "failed_to_download_image"
    - const ResponseErrorCodeImageFileNotFound ResponseErrorCode = "image_file_not_found"
  - Message string
    
    A human-readable description of the error.
- IncompleteDetails ResponseIncompleteDetails
  
  Details about why the response is incomplete.
  - Reason string
    
    The reason why the response is incomplete.
    - const ResponseIncompleteDetailsReasonMaxOutputTokens ResponseIncompleteDetailsReason = "max_output_tokens"
    - const ResponseIncompleteDetailsReasonContentFilter ResponseIncompleteDetailsReason = "content_filter"
- Instructions ResponseInstructionsUnion
  
  A system (or developer) message inserted into the model's context.
  
  When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
  - string
  - type ResponseInstructionsInputItemList []ResponseInputItemUnion
    
    A list of one or many input items to the model, containing different content types.
    - type EasyInputMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
      - Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
      - Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
      - Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
    - type ResponseInputItemMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
      - Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
      - Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
      - Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
      - Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
      - ID string
        
        The unique ID of the output message.
      - Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
      - Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
      - Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
      - Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
      - Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
      - ID string
        
        The unique ID of the file search tool call.
      - Queries []string
        
        The queries used to search for files.
      - Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
      - Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
      - Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
      - ID string
        
        The unique ID of the computer call.
      - CallID string
        
        An identifier used when responding to the tool call with output.
      - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
      - Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
      - Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
      - Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
    - type ResponseInputItemComputerCallOutput struct{…}
      
      The output of a computer tool call.
      - CallID string
        
        The ID of the computer tool call that produced the output.
      - Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
      - Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
      - ID string
        
        The ID of the computer tool call output.
      - AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
      - ID string
        
        The unique ID of the web search tool call.
      - Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
      - Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
      - Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
      - Arguments string
        
        A JSON string of the arguments to pass to the function.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Name string
        
        The name of the function to run.
      - Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
      - ID string
        
        The unique ID of the function tool call.
      - Namespace string
        
        The namespace of the function to run.
      - Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
    - type ResponseInputItemFunctionCallOutput struct{…}
      
      The output of a function tool call.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
      - ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
    - type ResponseInputItemToolSearchCall struct{…}
      - Arguments any
        
        The arguments supplied to the tool search call.
      - Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
      - ID string
        
        The unique ID of this tool search call.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
      - Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
    - type ResponseToolSearchOutputItemParamResp struct{…}
      - Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
      - Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
      - ID string
        
        The unique ID of this tool search output.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
      - Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
    - type ResponseInputItemAdditionalTools struct{…}
      - Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
      - Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
      - ID string
        
        The unique ID of this additional tools item.
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
      - ID string
        
        The unique identifier of the reasoning content.
      - Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
      - Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
      - Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
      - EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
      - Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
    - type ResponseCompactionItemParamResp struct{…}
      
      A compaction item generated by the v1/responses/compact API.
      - EncryptedContent string
        
        The encrypted content of the compaction summary.
      - Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
      - ID string
        
        The ID of the compaction item.
    - type ResponseInputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
      - ID string
        
        The unique ID of the image generation call.
      - Result string
        
        The generated image encoded in base64.
      - Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
      - Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
      - ID string
        
        The unique ID of the code interpreter tool call.
      - Code string
        
        The code to run, or null if not available.
      - ContainerID string
        
        The ID of the container used to run the code.
      - Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
      - Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
      - Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
    - type ResponseInputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
      - ID string
        
        The unique ID of the local shell call.
      - Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
      - CallID string
        
        The unique ID of the local shell tool call generated by the model.
      - Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
      - Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
    - type ResponseInputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
      - ID string
        
        The unique ID of the local shell tool call generated by the model.
      - Output string
        
        A JSON string of the output of the local shell tool call.
      - Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
    - type ResponseInputItemShellCall struct{…}
      
      A tool representing a request to execute one or more shell commands.
      - Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
      - ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
      - Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
      - Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
    - type ResponseInputItemShellCallOutput struct{…}
      
      The streamed output items emitted by a shell tool call.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
      - Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
      - ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
      - MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
      - Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
    - type ResponseInputItemApplyPatchCall struct{…}
      
      A tool call representing a request to create, delete, or update files using diff patches.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
      - Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
      - Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
      - ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - type ResponseInputItemApplyPatchCallOutput struct{…}
      
      The streamed output emitted by an apply patch tool call.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
      - Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
      - ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
      - Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
    - type ResponseInputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
      - ID string
        
        The unique ID of the list.
      - ServerLabel string
        
        The label of the MCP server.
      - Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
      - Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
      - Error string
        
        Error message if the server could not list tools.
    - type ResponseInputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
      - ID string
        
        The unique ID of the approval request.
      - Arguments string
        
        A JSON string of arguments for the tool.
      - Name string
        
        The name of the tool to run.
      - ServerLabel string
        
        The label of the MCP server making the request.
      - Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
    - type ResponseInputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
      - ApprovalRequestID string
        
        The ID of the approval request being answered.
      - Approve bool
        
        Whether the request was approved.
      - Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
      - ID string
        
        The unique ID of the approval response
      - Reason string
        
        Optional reason for the decision.
    - type ResponseInputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
      - ID string
        
        The unique ID of the tool call.
      - Arguments string
        
        A JSON string of the arguments passed to the tool.
      - Name string
        
        The name of the tool that was run.
      - ServerLabel string
        
        The label of the MCP server running the tool.
      - Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
      - ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
      - Error string
        
        The error from the tool call, if any.
      - Output string
        
        The output from the tool call.
      - Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
    - type ResponseCustomToolCallOutput struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
      - CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
      - Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
      - ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
      - CallID string
        
        An identifier used to map this custom tool call to a tool call output.
      - Input string
        
        The input for the custom tool call generated by the model.
      - Name string
        
        The name of the custom tool being called.
      - Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
      - ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
      - Namespace string
        
        The namespace of the custom tool being called.
    - type ResponseInputItemCompactionTrigger struct{…}
      
      Compacts the current context. Must be the final input item.
      - Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
    - type ResponseInputItemItemReference struct{…}
      
      An internal identifier for an item to reference.
      - ID string
        
        The ID of the item to reference.
      - Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
- Metadata Metadata
  
  Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
  
  Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
- Model ResponsesModel
  
  Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
  - string
  - type ChatModel string
    - const ChatModelGPT5_4 ChatModel = "gpt-5.4"
    - const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"
    - const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"
    - const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"
    - const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"
    - const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"
    - const ChatModelGPT5_2 ChatModel = "gpt-5.2"
    - const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"
    - const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"
    - const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"
    - const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"
    - const ChatModelGPT5_1 ChatModel = "gpt-5.1"
    - const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"
    - const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"
    - const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"
    - const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"
    - const ChatModelGPT5 ChatModel = "gpt-5"
    - const ChatModelGPT5Mini ChatModel = "gpt-5-mini"
    - const ChatModelGPT5Nano ChatModel = "gpt-5-nano"
    - const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"
    - const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"
    - const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"
    - const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"
    - const ChatModelGPT4_1 ChatModel = "gpt-4.1"
    - const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"
    - const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"
    - const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"
    - const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"
    - const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"
    - const ChatModelO4Mini ChatModel = "o4-mini"
    - const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"
    - const ChatModelO3 ChatModel = "o3"
    - const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"
    - const ChatModelO3Mini ChatModel = "o3-mini"
    - const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"
    - const ChatModelO1 ChatModel = "o1"
    - const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"
    - const ChatModelO1Preview ChatModel = "o1-preview"
    - const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"
    - const ChatModelO1Mini ChatModel = "o1-mini"
    - const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"
    - const ChatModelGPT4o ChatModel = "gpt-4o"
    - const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"
    - const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"
    - const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"
    - const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"
    - const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"
    - const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"
    - const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"
    - const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"
    - const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"
    - const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"
    - const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"
    - const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"
    - const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"
    - const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"
    - const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"
    - const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"
    - const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"
    - const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"
    - const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"
    - const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"
    - const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"
    - const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"
    - const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"
    - const ChatModelGPT4 ChatModel = "gpt-4"
    - const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"
    - const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"
    - const ChatModelGPT4_32k ChatModel = "gpt-4-32k"
    - const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"
    - const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"
    - const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"
    - const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"
    - const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"
    - const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"
    - const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"
    - const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"
    - const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"
  - type ResponsesModel string
    - const ResponsesModelO1Pro ResponsesModel = "o1-pro"
    - const ResponsesModelO1Pro2025_03_19 ResponsesModel = "o1-pro-2025-03-19"
    - const ResponsesModelO3Pro ResponsesModel = "o3-pro"
    - const ResponsesModelO3Pro2025_06_10 ResponsesModel = "o3-pro-2025-06-10"
    - const ResponsesModelO3DeepResearch ResponsesModel = "o3-deep-research"
    - const ResponsesModelO3DeepResearch2025_06_26 ResponsesModel = "o3-deep-research-2025-06-26"
    - const ResponsesModelO4MiniDeepResearch ResponsesModel = "o4-mini-deep-research"
    - const ResponsesModelO4MiniDeepResearch2025_06_26 ResponsesModel = "o4-mini-deep-research-2025-06-26"
    - const ResponsesModelComputerUsePreview ResponsesModel = "computer-use-preview"
    - const ResponsesModelComputerUsePreview2025_03_11 ResponsesModel = "computer-use-preview-2025-03-11"
    - const ResponsesModelGPT5Codex ResponsesModel = "gpt-5-codex"
    - const ResponsesModelGPT5Pro ResponsesModel = "gpt-5-pro"
    - const ResponsesModelGPT5Pro2025_10_06 ResponsesModel = "gpt-5-pro-2025-10-06"
    - const ResponsesModelGPT5_1CodexMax ResponsesModel = "gpt-5.1-codex-max"
- Object Response
  
  The object type of this resource - always set to response.
  - const ResponseResponse Response = "response"
- Output []ResponseOutputItemUnion
  
  An array of content items generated by the model.
  - The length and order of items in the output array is dependent on the model's response.
  - Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.
  - type ResponseOutputMessage struct{…}
    
    An output message from the model.
  - type ResponseFileSearchToolCall struct{…}
    
    The results of a file search tool call. See the file search guide for more information.
  - type ResponseFunctionToolCall struct{…}
    
    A tool call to run a function. See the function calling guide for more information.
  - type ResponseFunctionToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the function call tool output.
    - CallID string
      
      The unique ID of the function tool call generated by the model.
    - Output ResponseFunctionToolCallOutputItemOutputUnion
      
      The output from the function call generated by your code. Can be a string or an list of output content.
      - string
      - type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
    - Status ResponseFunctionToolCallOutputItemStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
      - const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
      - const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
    - Type FunctionCallOutput
      
      The type of the function tool call output. Always function_call_output.
      - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseFunctionWebSearch struct{…}
    
    The results of a web search tool call. See the web search guide for more information.
  - type ResponseComputerToolCall struct{…}
    
    A tool call to a computer use tool. See the computer use guide for more information.
  - type ResponseComputerToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the computer call tool output.
    - CallID string
      
      The ID of the computer tool call that produced the output.
    - Output ResponseComputerToolCallOutputScreenshot
      
      A computer screenshot image used with the computer use tool.
    - Status ResponseComputerToolCallOutputItemStatus
      
      The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
      - const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
      - const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
      - const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
      - const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
    - Type ComputerCallOutput
      
      The type of the computer tool call output. Always computer_call_output.
      - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
    - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
      
      The safety checks reported by the API that have been acknowledged by the developer.
      - ID string
        
        The ID of the pending safety check.
      - Code string
        
        The type of the pending safety check.
      - Message string
        
        Details about the pending safety check.
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseReasoningItem struct{…}
    
    A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
  - type ResponseToolSearchCall struct{…}
    - ID string
      
      The unique ID of the tool search call item.
    - Arguments any
      
      Arguments used for the tool search call.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchCallExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
      - const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
    - Status ResponseToolSearchCallStatus
      
      The status of the tool search call item that was recorded.
      - const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
      - const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
      - const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
    - Type ToolSearchCall
      
      The type of the item. Always tool_search_call.
      - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseToolSearchOutputItem struct{…}
    - ID string
      
      The unique ID of the tool search output item.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchOutputItemExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
      - const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
    - Status ResponseToolSearchOutputItemStatus
      
      The status of the tool search output item that was recorded.
      - const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
      - const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
      - const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
    - Tools []ToolUnion
      
      The loaded tool definitions returned by tool search.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - Type ToolSearchOutput
      
      The type of the item. Always tool_search_output.
      - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemAdditionalTools struct{…}
    - ID string
      
      The unique ID of the additional tools item.
    - Role string
      
      The role that provided the additional tools.
      - const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
      - const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
      - const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
      - const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
      - const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
      - const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
      - const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
      - const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
    - Tools []ToolUnion
      
      The additional tool definitions made available at this item.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - Type AdditionalTools
      
      The type of the item. Always additional_tools.
      - const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
  - type ResponseCompactionItem struct{…}
    
    A compaction item generated by the v1/responses/compact API.
    - ID string
      
      The unique ID of the compaction item.
    - EncryptedContent string
      
      The encrypted content that was produced by compaction.
    - Type Compaction
      
      The type of the item. Always compaction.
      - const CompactionCompaction Compaction = "compaction"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemImageGenerationCall struct{…}
    
    An image generation request made by the model.
    - ID string
      
      The unique ID of the image generation call.
    - Result string
      
      The generated image encoded in base64.
    - Status string
      
      The status of the image generation call.
      - const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
      - const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
      - const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
      - const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
    - Type ImageGenerationCall
      
      The type of the image generation call. Always image_generation_call.
      - const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
  - type ResponseCodeInterpreterToolCall struct{…}
    
    A tool call to run code.
  - type ResponseOutputItemLocalShellCall struct{…}
    
    A tool call to run a command on the local shell.
    - ID string
      
      The unique ID of the local shell call.
    - Action ResponseOutputItemLocalShellCallAction
      
      Execute a shell command on the server.
      - Command []string
        
        The command to run.
      - Env map[string, string]
        
        Environment variables to set for the command.
      - Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
      - User string
        
        Optional user to run the command as.
      - WorkingDirectory string
        
        Optional working directory to run the command in.
    - CallID string
      
      The unique ID of the local shell tool call generated by the model.
    - Status string
      
      The status of the local shell call.
      - const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
      - const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
    - Type LocalShellCall
      
      The type of the local shell call. Always local_shell_call.
      - const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
  - type ResponseOutputItemLocalShellCallOutput struct{…}
    
    The output of a local shell tool call.
    - ID string
      
      The unique ID of the local shell tool call generated by the model.
    - Output string
      
      A JSON string of the output of the local shell tool call.
    - Type LocalShellCallOutput
      
      The type of the local shell tool call output. Always local_shell_call_output.
      - const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete.
      - const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
      - const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
  - type ResponseFunctionShellToolCall struct{…}
    
    A tool call that executes one or more shell commands in a managed environment.
    - ID string
      
      The unique ID of the shell tool call. Populated when this item is returned via API.
    - Action ResponseFunctionShellToolCallAction
      
      The shell commands and limits that describe how to run the tool call.
      - Commands []string
      - MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - Environment ResponseFunctionShellToolCallEnvironmentUnion
      
      Represents the use of a local environment to perform shell actions.
      - type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
      - type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
    - Status ResponseFunctionShellToolCallStatus
      
      The status of the shell call. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
      - const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
      - const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
    - Type ShellCall
      
      The type of the item. Always shell_call.
      - const ShellCallShellCall ShellCall = "shell_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseFunctionShellToolCallOutput struct{…}
    
    The output of a shell tool call that was emitted.
    - ID string
      
      The unique ID of the shell call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - MaxOutputLength int64
      
      The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
    - Output []ResponseFunctionShellToolCallOutputOutput
      
      An array of shell call output contents
      - Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
      - Stderr string
        
        The standard error output that was captured.
      - Stdout string
        
        The standard output that was captured.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - Status ResponseFunctionShellToolCallOutputStatus
      
      The status of the shell call output. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
      - const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
      - const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
    - Type ShellCallOutput
      
      The type of the shell call output. Always shell_call_output.
      - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseApplyPatchToolCall struct{…}
    
    A tool call that applies file diffs by creating, deleting, or updating files.
    - ID string
      
      The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Operation ResponseApplyPatchToolCallOperationUnion
      
      One of the create_file, delete_file, or update_file operations applied via apply_patch.
      - type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
      - type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
      - type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
    - Status ResponseApplyPatchToolCallStatus
      
      The status of the apply patch tool call. One of in_progress or completed.
      - const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
      - const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
    - Type ApplyPatchCall
      
      The type of the item. Always apply_patch_call.
      - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseApplyPatchToolCallOutput struct{…}
    
    The output emitted by an apply patch tool call.
    - ID string
      
      The unique ID of the apply patch tool call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Status ResponseApplyPatchToolCallOutputStatus
      
      The status of the apply patch tool call output. One of completed or failed.
      - const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
      - const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
    - Type ApplyPatchCallOutput
      
      The type of the item. Always apply_patch_call_output.
      - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
    - CreatedBy string
      
      The ID of the entity that created this tool call output.
    - Output string
      
      Optional textual output returned by the apply patch tool.
  - type ResponseOutputItemMcpCall struct{…}
    
    An invocation of a tool on an MCP server.
    - ID string
      
      The unique ID of the tool call.
    - Arguments string
      
      A JSON string of the arguments passed to the tool.
    - Name string
      
      The name of the tool that was run.
    - ServerLabel string
      
      The label of the MCP server running the tool.
    - Type McpCall
      
      The type of the item. Always mcp_call.
      - const McpCallMcpCall McpCall = "mcp_call"
    - ApprovalRequestID string
      
      Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
    - Error string
      
      The error from the tool call, if any.
    - Output string
      
      The output from the tool call.
    - Status string
      
      The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
      - const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
      - const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
      - const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
      - const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
      - const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
  - type ResponseOutputItemMcpListTools struct{…}
    
    A list of tools available on an MCP server.
    - ID string
      
      The unique ID of the list.
    - ServerLabel string
      
      The label of the MCP server.
    - Tools []ResponseOutputItemMcpListToolsTool
      
      The tools available on the server.
      - InputSchema any
        
        The JSON schema describing the tool's input.
      - Name string
        
        The name of the tool.
      - Annotations any
        
        Additional annotations about the tool.
      - Description string
        
        The description of the tool.
    - Type McpListTools
      
      The type of the item. Always mcp_list_tools.
      - const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
    - Error string
      
      Error message if the server could not list tools.
  - type ResponseOutputItemMcpApprovalRequest struct{…}
    
    A request for human approval of a tool invocation.
    - ID string
      
      The unique ID of the approval request.
    - Arguments string
      
      A JSON string of arguments for the tool.
    - Name string
      
      The name of the tool to run.
    - ServerLabel string
      
      The label of the MCP server making the request.
    - Type McpApprovalRequest
      
      The type of the item. Always mcp_approval_request.
      - const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
  - type ResponseOutputItemMcpApprovalResponse struct{…}
    
    A response to an MCP approval request.
    - ID string
      
      The unique ID of the approval response
    - ApprovalRequestID string
      
      The ID of the approval request being answered.
    - Approve bool
      
      Whether the request was approved.
    - Type McpApprovalResponse
      
      The type of the item. Always mcp_approval_response.
      - const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
    - Reason string
      
      Optional reason for the decision.
  - type ResponseCustomToolCall struct{…}
    
    A call to a custom tool created by the model.
  - type ResponseCustomToolCallOutputItem struct{…}
    
    The output of a custom tool call from your code, being sent back to the model.
    - ID string
      
      The unique ID of the custom tool call output item.
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
      - const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
      - const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
    - CreatedBy string
      
      The identifier of the actor that created the item.
- ParallelToolCalls bool
  
  Whether to allow the model to run tool calls in parallel.
- Temperature float64
  
  What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
- ToolChoice ResponseToolChoiceUnion
  
  How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.
  - type ToolChoiceOptions string
    
    Controls which (if any) tool is called by the model.
    
    none means the model will not call any tool and instead generates a message.
    
    auto means the model can pick between generating a message or calling one or more tools.
    
    required means the model must call one or more tools.
    - const ToolChoiceOptionsNone ToolChoiceOptions = "none"
    - const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
    - const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
  - type ToolChoiceAllowed struct{…}
    
    Constrains the tools available to the model to a pre-defined set.
    - Mode ToolChoiceAllowedMode
      
      Constrains the tools available to the model to a pre-defined set.
      
      auto allows the model to pick from among the allowed tools and generate a message.
      
      required requires the model to call one or more of the allowed tools.
      - const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
      - const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
    - Tools []map[string, any]
      
      A list of tool definitions that the model should be allowed to call.
      
      For the Responses API, the list of tool definitions might look like:
```
[
  { "type": "function", "name": "get_weather" },
  { "type": "mcp", "server_label": "deepwiki" },
  { "type": "image_generation" }
]
```
    - Type AllowedTools
      
      Allowed tool configuration type. Always allowed_tools.
      - const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
  - type ToolChoiceTypes struct{…}
    
    Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
    - Type ToolChoiceTypesType
      
      The type of hosted tool the model should to use. Learn more about built-in tools.
      
      Allowed values are:
      - file_search
      - web_search_preview
      - computer
      - computer_use_preview
      - computer_use
      - code_interpreter
      - image_generation
      - const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
      - const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
      - const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
      - const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
      - const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
      - const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
      - const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
      - const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
  - type ToolChoiceFunction struct{…}
    
    Use this option to force the model to call a specific function.
    - Name string
      
      The name of the function to call.
    - Type Function
      
      For function calling, the type is always function.
      - const FunctionFunction Function = "function"
  - type ToolChoiceMcp struct{…}
    
    Use this option to force the model to call a specific tool on a remote MCP server.
    - ServerLabel string
      
      The label of the MCP server to use.
    - Type Mcp
      
      For MCP tools, the type is always mcp.
      - const McpMcp Mcp = "mcp"
    - Name string
      
      The name of the tool to call on the server.
  - type ToolChoiceCustom struct{…}
    
    Use this option to force the model to call a specific custom tool.
    - Name string
      
      The name of the custom tool to call.
    - Type Custom
      
      For custom tool calling, the type is always custom.
      - const CustomCustom Custom = "custom"
  - type ToolChoiceApplyPatch struct{…}
    
    Forces the model to call the apply_patch tool when executing a tool call.
    - Type ApplyPatch
      
      The tool to call. Always apply_patch.
      - const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
  - type ToolChoiceShell struct{…}
    
    Forces the model to call the shell tool when a tool call is required.
    - Type Shell
      
      The tool to call. Always shell.
      - const ShellShell Shell = "shell"
- Tools []ToolUnion
  
  An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
  
  We support the following categories of tools:
  - Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
  - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
  - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
  - type FunctionTool struct{…}
    
    Defines a function in your own code the model can choose to call. Learn more about function calling.
  - type FileSearchTool struct{…}
    
    A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
  - type ComputerTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
  - type ComputerUsePreviewTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
  - type WebSearchTool struct{…}
    
    Search the Internet for sources related to the prompt. Learn more about the web search tool.
  - type ToolMcp struct{…}
    
    Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
  - type ToolCodeInterpreter struct{…}
    
    A tool that runs Python code to help generate a response to a prompt.
  - type ToolImageGeneration struct{…}
    
    A tool that generates images using the GPT image models.
  - type ToolLocalShell struct{…}
    
    A tool that allows the model to execute shell commands in a local environment.
  - type FunctionShellTool struct{…}
    
    A tool that allows the model to execute shell commands.
  - type CustomTool struct{…}
    
    A custom tool that processes input using a specified format. Learn more about custom tools
  - type NamespaceTool struct{…}
    
    Groups function/custom tools under a shared namespace.
  - type ToolSearchTool struct{…}
    
    Hosted or BYOT tool search configuration for deferred tools.
  - type WebSearchPreviewTool struct{…}
    
    This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
  - type ApplyPatchTool struct{…}
    
    Allows the assistant to create, delete, or update files using unified diffs.
- TopP float64
  
  An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
  
  We generally recommend altering this or temperature but not both.
- Background bool
  
  Whether to run the model response in the background. Learn more.
- CompletedAt float64
  
  Unix timestamp (in seconds) of when this Response was completed. Only present when the status is completed.
- Conversation ResponseConversation
  
  The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
  - ID string
    
    The unique ID of the conversation that this response was associated with.
- MaxOutputTokens int64
  
  An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
- MaxToolCalls int64
  
  The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
- Moderation ResponseModeration
  
  Moderation results for the response input and output, if moderated completions were requested.
  - Input ResponseModerationInputUnion
    
    Moderation for the response input.
    - type ResponseModerationInputModerationResult struct{…}
      
      A moderation result produced for the response input or output.
      - Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
      - CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeText ResponseModerationInputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeImage ResponseModerationInputModerationResultCategoryAppliedInputType = "image"
      - CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
      - Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
      - Model string
        
        The moderation model that produced this result.
      - Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
    - type ResponseModerationInputError struct{…}
      
      An error produced while attempting moderation for the response input or output.
      - Code string
        
        The error code.
      - Message string
        
        The error message.
      - Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
  - Output ResponseModerationOutputUnion
    
    Moderation for the response output.
    - type ResponseModerationOutputModerationResult struct{…}
      
      A moderation result produced for the response input or output.
      - Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
      - CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeText ResponseModerationOutputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeImage ResponseModerationOutputModerationResultCategoryAppliedInputType = "image"
      - CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
      - Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
      - Model string
        
        The moderation model that produced this result.
      - Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
    - type ResponseModerationOutputError struct{…}
      
      An error produced while attempting moderation for the response input or output.
      - Code string
        
        The error code.
      - Message string
        
        The error message.
      - Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
- PreviousResponseID string
  
  The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
- Prompt ResponsePrompt
  
  Reference to a prompt template and its variables. Learn more.
  - ID string
    
    The unique identifier of the prompt template to use.
  - Variables map[string, ResponsePromptVariableUnion]
    
    Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
    - string
    - type ResponseInputText struct{…}
      
      A text input to the model.
    - type ResponseInputImage struct{…}
      
      An image input to the model. Learn about image inputs.
    - type ResponseInputFile struct{…}
      
      A file input to the model.
  - Version string
    
    Optional version of the prompt template.
- PromptCacheKey string
  
  Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
- PromptCacheRetention ResponsePromptCacheRetention
  
  The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.
  
  For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:
  - Organizations without ZDR enabled default to 24h.
  - Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.
  - const ResponsePromptCacheRetentionInMemory ResponsePromptCacheRetention = "in_memory"
  - const ResponsePromptCacheRetention24h ResponsePromptCacheRetention = "24h"
- Reasoning Reasoning
  
  gpt-5 and o-series models only
  
  Configuration options for reasoning models.
  - Context ReasoningContext
    
    Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
    - const ReasoningContextAuto ReasoningContext = "auto"
    - const ReasoningContextCurrentTurn ReasoningContext = "current_turn"
    - const ReasoningContextAllTurns ReasoningContext = "all_turns"
  - Effort ReasoningEffort
    
    Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
    - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
    - All models before gpt-5.1 default to medium reasoning effort, and do not support none.
    - The gpt-5-pro model defaults to (and only supports) high reasoning effort.
    - xhigh is supported for all models after gpt-5.1-codex-max.
    - const ReasoningEffortNone ReasoningEffort = "none"
    - const ReasoningEffortMinimal ReasoningEffort = "minimal"
    - const ReasoningEffortLow ReasoningEffort = "low"
    - const ReasoningEffortMedium ReasoningEffort = "medium"
    - const ReasoningEffortHigh ReasoningEffort = "high"
    - const ReasoningEffortXhigh ReasoningEffort = "xhigh"
  - GenerateSummary ReasoningGenerateSummary
    
    Deprecated: use summary instead.
    
    A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
    - const ReasoningGenerateSummaryAuto ReasoningGenerateSummary = "auto"
    - const ReasoningGenerateSummaryConcise ReasoningGenerateSummary = "concise"
    - const ReasoningGenerateSummaryDetailed ReasoningGenerateSummary = "detailed"
  - Summary ReasoningSummary
    
    A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
    
    concise is supported for computer-use-preview models and all reasoning models after gpt-5.
    - const ReasoningSummaryAuto ReasoningSummary = "auto"
    - const ReasoningSummaryConcise ReasoningSummary = "concise"
    - const ReasoningSummaryDetailed ReasoningSummary = "detailed"
- SafetyIdentifier string
  
  A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
- ServiceTier ResponseServiceTier
  
  Specifies the processing type used for serving the request.
  - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
  - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
  - If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
  - When not set, the default behavior is 'auto'.
  When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
  - const ResponseServiceTierAuto ResponseServiceTier = "auto"
  - const ResponseServiceTierDefault ResponseServiceTier = "default"
  - const ResponseServiceTierFlex ResponseServiceTier = "flex"
  - const ResponseServiceTierScale ResponseServiceTier = "scale"
  - const ResponseServiceTierPriority ResponseServiceTier = "priority"
- Status ResponseStatus
  
  The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
  - const ResponseStatusCompleted ResponseStatus = "completed"
  - const ResponseStatusFailed ResponseStatus = "failed"
  - const ResponseStatusInProgress ResponseStatus = "in_progress"
  - const ResponseStatusCancelled ResponseStatus = "cancelled"
  - const ResponseStatusQueued ResponseStatus = "queued"
  - const ResponseStatusIncomplete ResponseStatus = "incomplete"
- Text ResponseTextConfig
  
  Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
  - Text inputs and outputs
  - Structured Outputs
  - Format ResponseFormatTextConfigUnion
    
    An object specifying the format that the model must output.
    
    Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
    
    The default format is { "type": "text" } with no additional options.
    
    Not recommended for gpt-4o and newer models:
    
    Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
    - type ResponseFormatText struct{…}
      
      Default response format. Used to generate text responses.
      - Type Text
        
        The type of response format being defined. Always text.
        
        const TextText Text = "text"
    - type ResponseFormatTextJSONSchemaConfig struct{…}
      
      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
      - Name string
        
        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
      - Schema map[string, any]
        
        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
      - Type JSONSchema
        
        The type of response format being defined. Always json_schema.
        
        const JSONSchemaJSONSchema JSONSchema = "json_schema"
      - Description string
        
        A description of what the response format is for, used by the model to determine how to respond in the format.
      - Strict bool
        
        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
    - type ResponseFormatJSONObject struct{…}
      
      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
      - Type JSONObject
        
        The type of response format being defined. Always json_object.
        
        const JSONObjectJSONObject JSONObject = "json_object"
  - Verbosity ResponseTextConfigVerbosity
    
    Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
    - const ResponseTextConfigVerbosityLow ResponseTextConfigVerbosity = "low"
    - const ResponseTextConfigVerbosityMedium ResponseTextConfigVerbosity = "medium"
    - const ResponseTextConfigVerbosityHigh ResponseTextConfigVerbosity = "high"
- TopLogprobs int64
  
  An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
- Truncation ResponseTruncation
  
  The truncation strategy to use for the model response.
  - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
  - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
  - const ResponseTruncationAuto ResponseTruncation = "auto"
  - const ResponseTruncationDisabled ResponseTruncation = "disabled"
- Usage ResponseUsage
  
  Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
  - InputTokens int64
    
    The number of input tokens.
  - InputTokensDetails ResponseUsageInputTokensDetails
    
    A detailed breakdown of the input tokens.
    - CachedTokens int64
      
      The number of tokens that were retrieved from the cache. More on prompt caching.
  - OutputTokens int64
    
    The number of output tokens.
  - OutputTokensDetails ResponseUsageOutputTokensDetails
    
    A detailed breakdown of the output tokens.
    - ReasoningTokens int64
      
      The number of reasoning tokens.
  - TotalTokens int64
    
    The total number of tokens used.
- User string
  
  This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
  "github.com/openai/openai-go/responses"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  response, err := client.Responses.Get(
    context.TODO(),
    "resp_677efb5139a88190b512bc3fef8e535d",
    responses.ResponseGetParams{

    },
  )
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", response.ID)
}

Response

{
  "id": "id",
  "created_at": 0,
  "error": {
    "code": "server_error",
    "message": "message"
  },
  "incomplete_details": {
    "reason": "max_output_tokens"
  },
  "instructions": "string",
  "metadata": {
    "foo": "string"
  },
  "model": "gpt-5.1",
  "object": "response",
  "output": [
    {
      "id": "id",
      "content": [
        {
          "annotations": [
            {
              "file_id": "file_id",
              "filename": "filename",
              "index": 0,
              "type": "file_citation"
            }
          ],
          "text": "text",
          "type": "output_text",
          "logprobs": [
            {
              "token": "token",
              "bytes": [
                0
              ],
              "logprob": 0,
              "top_logprobs": [
                {
                  "token": "token",
                  "bytes": [
                    0
                  ],
                  "logprob": 0
                }
              ]
            }
          ]
        }
      ],
      "role": "assistant",
      "status": "in_progress",
      "type": "message",
      "phase": "commentary"
    }
  ],
  "parallel_tool_calls": true,
  "temperature": 1,
  "tool_choice": "none",
  "tools": [
    {
      "name": "name",
      "parameters": {
        "foo": "bar"
      },
      "strict": true,
      "type": "function",
      "defer_loading": true,
      "description": "description"
    }
  ],
  "top_p": 1,
  "background": true,
  "completed_at": 0,
  "conversation": {
    "id": "id"
  },
  "max_output_tokens": 0,
  "max_tool_calls": 0,
  "moderation": {
    "input": {
      "categories": {
        "foo": true
      },
      "category_applied_input_types": {
        "foo": [
          "text"
        ]
      },
      "category_scores": {
        "foo": 0
      },
      "flagged": true,
      "model": "model",
      "type": "moderation_result"
    },
    "output": {
      "categories": {
        "foo": true
      },
      "category_applied_input_types": {
        "foo": [
          "text"
        ]
      },
      "category_scores": {
        "foo": 0
      },
      "flagged": true,
      "model": "model",
      "type": "moderation_result"
    }
  },
  "output_text": "output_text",
  "previous_response_id": "previous_response_id",
  "prompt": {
    "id": "id",
    "variables": {
      "foo": "string"
    },
    "version": "version"
  },
  "prompt_cache_key": "prompt-cache-key-1234",
  "prompt_cache_retention": "in_memory",
  "reasoning": {
    "context": "auto",
    "effort": "none",
    "generate_summary": "auto",
    "summary": "auto"
  },
  "safety_identifier": "safety-identifier-1234",
  "service_tier": "auto",
  "status": "completed",
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "low"
  },
  "top_logprobs": 0,
  "truncation": "auto",
  "usage": {
    "input_tokens": 0,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 0,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 0
  },
  "user": "user-1234"
}

Delete a model response

client.Responses.Delete(ctx, responseID) error

delete /responses/{response_id}

Deletes a model response with the given ID.

Parameters

responseID string

Example

package main

import (
  "context"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  err := client.Responses.Delete(context.TODO(), "resp_677efb5139a88190b512bc3fef8e535d")
  if err != nil {
    panic(err.Error())
  }
}

Cancel a response

client.Responses.Cancel(ctx, responseID) (*Response, error)

post /responses/{response_id}/cancel

Cancels a model response with the given ID. Only responses created with the background parameter set to true can be cancelled. Learn more.

Parameters

responseID string

Returns

type Response struct{…}
- ID string
  
  Unique identifier for this Response.
- CreatedAt float64
  
  Unix timestamp (in seconds) of when this Response was created.
- Error ResponseError
  
  An error object returned when the model fails to generate a Response.
  - Code ResponseErrorCode
    
    The error code for the response.
    - const ResponseErrorCodeServerError ResponseErrorCode = "server_error"
    - const ResponseErrorCodeRateLimitExceeded ResponseErrorCode = "rate_limit_exceeded"
    - const ResponseErrorCodeInvalidPrompt ResponseErrorCode = "invalid_prompt"
    - const ResponseErrorCodeVectorStoreTimeout ResponseErrorCode = "vector_store_timeout"
    - const ResponseErrorCodeInvalidImage ResponseErrorCode = "invalid_image"
    - const ResponseErrorCodeInvalidImageFormat ResponseErrorCode = "invalid_image_format"
    - const ResponseErrorCodeInvalidBase64Image ResponseErrorCode = "invalid_base64_image"
    - const ResponseErrorCodeInvalidImageURL ResponseErrorCode = "invalid_image_url"
    - const ResponseErrorCodeImageTooLarge ResponseErrorCode = "image_too_large"
    - const ResponseErrorCodeImageTooSmall ResponseErrorCode = "image_too_small"
    - const ResponseErrorCodeImageParseError ResponseErrorCode = "image_parse_error"
    - const ResponseErrorCodeImageContentPolicyViolation ResponseErrorCode = "image_content_policy_violation"
    - const ResponseErrorCodeInvalidImageMode ResponseErrorCode = "invalid_image_mode"
    - const ResponseErrorCodeImageFileTooLarge ResponseErrorCode = "image_file_too_large"
    - const ResponseErrorCodeUnsupportedImageMediaType ResponseErrorCode = "unsupported_image_media_type"
    - const ResponseErrorCodeEmptyImageFile ResponseErrorCode = "empty_image_file"
    - const ResponseErrorCodeFailedToDownloadImage ResponseErrorCode = "failed_to_download_image"
    - const ResponseErrorCodeImageFileNotFound ResponseErrorCode = "image_file_not_found"
  - Message string
    
    A human-readable description of the error.
- IncompleteDetails ResponseIncompleteDetails
  
  Details about why the response is incomplete.
  - Reason string
    
    The reason why the response is incomplete.
    - const ResponseIncompleteDetailsReasonMaxOutputTokens ResponseIncompleteDetailsReason = "max_output_tokens"
    - const ResponseIncompleteDetailsReasonContentFilter ResponseIncompleteDetailsReason = "content_filter"
- Instructions ResponseInstructionsUnion
  
  A system (or developer) message inserted into the model's context.
  
  When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
  - string
  - type ResponseInstructionsInputItemList []ResponseInputItemUnion
    
    A list of one or many input items to the model, containing different content types.
    - type EasyInputMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
      - Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
      - Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
      - Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
    - type ResponseInputItemMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
      - Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
      - Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
      - Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
      - Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
      - ID string
        
        The unique ID of the output message.
      - Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
      - Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
      - Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
      - Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
      - Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
      - ID string
        
        The unique ID of the file search tool call.
      - Queries []string
        
        The queries used to search for files.
      - Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
      - Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
      - Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
      - ID string
        
        The unique ID of the computer call.
      - CallID string
        
        An identifier used when responding to the tool call with output.
      - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
      - Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
      - Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
      - Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
    - type ResponseInputItemComputerCallOutput struct{…}
      
      The output of a computer tool call.
      - CallID string
        
        The ID of the computer tool call that produced the output.
      - Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
      - Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
      - ID string
        
        The ID of the computer tool call output.
      - AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
      - ID string
        
        The unique ID of the web search tool call.
      - Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
      - Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
      - Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
      - Arguments string
        
        A JSON string of the arguments to pass to the function.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Name string
        
        The name of the function to run.
      - Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
      - ID string
        
        The unique ID of the function tool call.
      - Namespace string
        
        The namespace of the function to run.
      - Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
    - type ResponseInputItemFunctionCallOutput struct{…}
      
      The output of a function tool call.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
      - ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
    - type ResponseInputItemToolSearchCall struct{…}
      - Arguments any
        
        The arguments supplied to the tool search call.
      - Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
      - ID string
        
        The unique ID of this tool search call.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
      - Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
    - type ResponseToolSearchOutputItemParamResp struct{…}
      - Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
      - Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
      - ID string
        
        The unique ID of this tool search output.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
      - Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
    - type ResponseInputItemAdditionalTools struct{…}
      - Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
      - Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
      - ID string
        
        The unique ID of this additional tools item.
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
      - ID string
        
        The unique identifier of the reasoning content.
      - Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
      - Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
      - Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
      - EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
      - Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
    - type ResponseCompactionItemParamResp struct{…}
      
      A compaction item generated by the v1/responses/compact API.
      - EncryptedContent string
        
        The encrypted content of the compaction summary.
      - Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
      - ID string
        
        The ID of the compaction item.
    - type ResponseInputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
      - ID string
        
        The unique ID of the image generation call.
      - Result string
        
        The generated image encoded in base64.
      - Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
      - Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
      - ID string
        
        The unique ID of the code interpreter tool call.
      - Code string
        
        The code to run, or null if not available.
      - ContainerID string
        
        The ID of the container used to run the code.
      - Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
      - Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
      - Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
    - type ResponseInputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
      - ID string
        
        The unique ID of the local shell call.
      - Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
      - CallID string
        
        The unique ID of the local shell tool call generated by the model.
      - Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
      - Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
    - type ResponseInputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
      - ID string
        
        The unique ID of the local shell tool call generated by the model.
      - Output string
        
        A JSON string of the output of the local shell tool call.
      - Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
    - type ResponseInputItemShellCall struct{…}
      
      A tool representing a request to execute one or more shell commands.
      - Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
      - ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
      - Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
      - Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
    - type ResponseInputItemShellCallOutput struct{…}
      
      The streamed output items emitted by a shell tool call.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
      - Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
      - ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
      - MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
      - Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
    - type ResponseInputItemApplyPatchCall struct{…}
      
      A tool call representing a request to create, delete, or update files using diff patches.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
      - Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
      - Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
      - ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - type ResponseInputItemApplyPatchCallOutput struct{…}
      
      The streamed output emitted by an apply patch tool call.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
      - Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
      - ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
      - Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
    - type ResponseInputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
      - ID string
        
        The unique ID of the list.
      - ServerLabel string
        
        The label of the MCP server.
      - Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
      - Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
      - Error string
        
        Error message if the server could not list tools.
    - type ResponseInputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
      - ID string
        
        The unique ID of the approval request.
      - Arguments string
        
        A JSON string of arguments for the tool.
      - Name string
        
        The name of the tool to run.
      - ServerLabel string
        
        The label of the MCP server making the request.
      - Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
    - type ResponseInputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
      - ApprovalRequestID string
        
        The ID of the approval request being answered.
      - Approve bool
        
        Whether the request was approved.
      - Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
      - ID string
        
        The unique ID of the approval response
      - Reason string
        
        Optional reason for the decision.
    - type ResponseInputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
      - ID string
        
        The unique ID of the tool call.
      - Arguments string
        
        A JSON string of the arguments passed to the tool.
      - Name string
        
        The name of the tool that was run.
      - ServerLabel string
        
        The label of the MCP server running the tool.
      - Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
      - ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
      - Error string
        
        The error from the tool call, if any.
      - Output string
        
        The output from the tool call.
      - Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
    - type ResponseCustomToolCallOutput struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
      - CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
      - Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
      - ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
      - CallID string
        
        An identifier used to map this custom tool call to a tool call output.
      - Input string
        
        The input for the custom tool call generated by the model.
      - Name string
        
        The name of the custom tool being called.
      - Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
      - ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
      - Namespace string
        
        The namespace of the custom tool being called.
    - type ResponseInputItemCompactionTrigger struct{…}
      
      Compacts the current context. Must be the final input item.
      - Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
    - type ResponseInputItemItemReference struct{…}
      
      An internal identifier for an item to reference.
      - ID string
        
        The ID of the item to reference.
      - Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
- Metadata Metadata
  
  Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
  
  Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
- Model ResponsesModel
  
  Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
  - string
  - type ChatModel string
    - const ChatModelGPT5_4 ChatModel = "gpt-5.4"
    - const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"
    - const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"
    - const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"
    - const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"
    - const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"
    - const ChatModelGPT5_2 ChatModel = "gpt-5.2"
    - const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"
    - const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"
    - const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"
    - const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"
    - const ChatModelGPT5_1 ChatModel = "gpt-5.1"
    - const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"
    - const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"
    - const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"
    - const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"
    - const ChatModelGPT5 ChatModel = "gpt-5"
    - const ChatModelGPT5Mini ChatModel = "gpt-5-mini"
    - const ChatModelGPT5Nano ChatModel = "gpt-5-nano"
    - const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"
    - const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"
    - const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"
    - const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"
    - const ChatModelGPT4_1 ChatModel = "gpt-4.1"
    - const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"
    - const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"
    - const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"
    - const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"
    - const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"
    - const ChatModelO4Mini ChatModel = "o4-mini"
    - const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"
    - const ChatModelO3 ChatModel = "o3"
    - const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"
    - const ChatModelO3Mini ChatModel = "o3-mini"
    - const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"
    - const ChatModelO1 ChatModel = "o1"
    - const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"
    - const ChatModelO1Preview ChatModel = "o1-preview"
    - const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"
    - const ChatModelO1Mini ChatModel = "o1-mini"
    - const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"
    - const ChatModelGPT4o ChatModel = "gpt-4o"
    - const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"
    - const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"
    - const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"
    - const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"
    - const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"
    - const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"
    - const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"
    - const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"
    - const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"
    - const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"
    - const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"
    - const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"
    - const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"
    - const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"
    - const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"
    - const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"
    - const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"
    - const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"
    - const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"
    - const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"
    - const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"
    - const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"
    - const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"
    - const ChatModelGPT4 ChatModel = "gpt-4"
    - const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"
    - const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"
    - const ChatModelGPT4_32k ChatModel = "gpt-4-32k"
    - const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"
    - const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"
    - const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"
    - const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"
    - const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"
    - const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"
    - const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"
    - const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"
    - const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"
  - type ResponsesModel string
    - const ResponsesModelO1Pro ResponsesModel = "o1-pro"
    - const ResponsesModelO1Pro2025_03_19 ResponsesModel = "o1-pro-2025-03-19"
    - const ResponsesModelO3Pro ResponsesModel = "o3-pro"
    - const ResponsesModelO3Pro2025_06_10 ResponsesModel = "o3-pro-2025-06-10"
    - const ResponsesModelO3DeepResearch ResponsesModel = "o3-deep-research"
    - const ResponsesModelO3DeepResearch2025_06_26 ResponsesModel = "o3-deep-research-2025-06-26"
    - const ResponsesModelO4MiniDeepResearch ResponsesModel = "o4-mini-deep-research"
    - const ResponsesModelO4MiniDeepResearch2025_06_26 ResponsesModel = "o4-mini-deep-research-2025-06-26"
    - const ResponsesModelComputerUsePreview ResponsesModel = "computer-use-preview"
    - const ResponsesModelComputerUsePreview2025_03_11 ResponsesModel = "computer-use-preview-2025-03-11"
    - const ResponsesModelGPT5Codex ResponsesModel = "gpt-5-codex"
    - const ResponsesModelGPT5Pro ResponsesModel = "gpt-5-pro"
    - const ResponsesModelGPT5Pro2025_10_06 ResponsesModel = "gpt-5-pro-2025-10-06"
    - const ResponsesModelGPT5_1CodexMax ResponsesModel = "gpt-5.1-codex-max"
- Object Response
  
  The object type of this resource - always set to response.
  - const ResponseResponse Response = "response"
- Output []ResponseOutputItemUnion
  
  An array of content items generated by the model.
  - The length and order of items in the output array is dependent on the model's response.
  - Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.
  - type ResponseOutputMessage struct{…}
    
    An output message from the model.
  - type ResponseFileSearchToolCall struct{…}
    
    The results of a file search tool call. See the file search guide for more information.
  - type ResponseFunctionToolCall struct{…}
    
    A tool call to run a function. See the function calling guide for more information.
  - type ResponseFunctionToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the function call tool output.
    - CallID string
      
      The unique ID of the function tool call generated by the model.
    - Output ResponseFunctionToolCallOutputItemOutputUnion
      
      The output from the function call generated by your code. Can be a string or an list of output content.
      - string
      - type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
    - Status ResponseFunctionToolCallOutputItemStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
      - const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
      - const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
    - Type FunctionCallOutput
      
      The type of the function tool call output. Always function_call_output.
      - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseFunctionWebSearch struct{…}
    
    The results of a web search tool call. See the web search guide for more information.
  - type ResponseComputerToolCall struct{…}
    
    A tool call to a computer use tool. See the computer use guide for more information.
  - type ResponseComputerToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the computer call tool output.
    - CallID string
      
      The ID of the computer tool call that produced the output.
    - Output ResponseComputerToolCallOutputScreenshot
      
      A computer screenshot image used with the computer use tool.
    - Status ResponseComputerToolCallOutputItemStatus
      
      The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
      - const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
      - const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
      - const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
      - const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
    - Type ComputerCallOutput
      
      The type of the computer tool call output. Always computer_call_output.
      - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
    - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
      
      The safety checks reported by the API that have been acknowledged by the developer.
      - ID string
        
        The ID of the pending safety check.
      - Code string
        
        The type of the pending safety check.
      - Message string
        
        Details about the pending safety check.
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseReasoningItem struct{…}
    
    A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
  - type ResponseToolSearchCall struct{…}
    - ID string
      
      The unique ID of the tool search call item.
    - Arguments any
      
      Arguments used for the tool search call.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchCallExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
      - const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
    - Status ResponseToolSearchCallStatus
      
      The status of the tool search call item that was recorded.
      - const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
      - const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
      - const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
    - Type ToolSearchCall
      
      The type of the item. Always tool_search_call.
      - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseToolSearchOutputItem struct{…}
    - ID string
      
      The unique ID of the tool search output item.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchOutputItemExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
      - const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
    - Status ResponseToolSearchOutputItemStatus
      
      The status of the tool search output item that was recorded.
      - const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
      - const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
      - const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
    - Tools []ToolUnion
      
      The loaded tool definitions returned by tool search.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - Type ToolSearchOutput
      
      The type of the item. Always tool_search_output.
      - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemAdditionalTools struct{…}
    - ID string
      
      The unique ID of the additional tools item.
    - Role string
      
      The role that provided the additional tools.
      - const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
      - const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
      - const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
      - const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
      - const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
      - const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
      - const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
      - const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
    - Tools []ToolUnion
      
      The additional tool definitions made available at this item.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - Type AdditionalTools
      
      The type of the item. Always additional_tools.
      - const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
  - type ResponseCompactionItem struct{…}
    
    A compaction item generated by the v1/responses/compact API.
    - ID string
      
      The unique ID of the compaction item.
    - EncryptedContent string
      
      The encrypted content that was produced by compaction.
    - Type Compaction
      
      The type of the item. Always compaction.
      - const CompactionCompaction Compaction = "compaction"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemImageGenerationCall struct{…}
    
    An image generation request made by the model.
    - ID string
      
      The unique ID of the image generation call.
    - Result string
      
      The generated image encoded in base64.
    - Status string
      
      The status of the image generation call.
      - const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
      - const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
      - const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
      - const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
    - Type ImageGenerationCall
      
      The type of the image generation call. Always image_generation_call.
      - const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
  - type ResponseCodeInterpreterToolCall struct{…}
    
    A tool call to run code.
  - type ResponseOutputItemLocalShellCall struct{…}
    
    A tool call to run a command on the local shell.
    - ID string
      
      The unique ID of the local shell call.
    - Action ResponseOutputItemLocalShellCallAction
      
      Execute a shell command on the server.
      - Command []string
        
        The command to run.
      - Env map[string, string]
        
        Environment variables to set for the command.
      - Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
      - User string
        
        Optional user to run the command as.
      - WorkingDirectory string
        
        Optional working directory to run the command in.
    - CallID string
      
      The unique ID of the local shell tool call generated by the model.
    - Status string
      
      The status of the local shell call.
      - const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
      - const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
    - Type LocalShellCall
      
      The type of the local shell call. Always local_shell_call.
      - const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
  - type ResponseOutputItemLocalShellCallOutput struct{…}
    
    The output of a local shell tool call.
    - ID string
      
      The unique ID of the local shell tool call generated by the model.
    - Output string
      
      A JSON string of the output of the local shell tool call.
    - Type LocalShellCallOutput
      
      The type of the local shell tool call output. Always local_shell_call_output.
      - const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete.
      - const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
      - const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
  - type ResponseFunctionShellToolCall struct{…}
    
    A tool call that executes one or more shell commands in a managed environment.
    - ID string
      
      The unique ID of the shell tool call. Populated when this item is returned via API.
    - Action ResponseFunctionShellToolCallAction
      
      The shell commands and limits that describe how to run the tool call.
      - Commands []string
      - MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - Environment ResponseFunctionShellToolCallEnvironmentUnion
      
      Represents the use of a local environment to perform shell actions.
      - type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
      - type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
    - Status ResponseFunctionShellToolCallStatus
      
      The status of the shell call. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
      - const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
      - const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
    - Type ShellCall
      
      The type of the item. Always shell_call.
      - const ShellCallShellCall ShellCall = "shell_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseFunctionShellToolCallOutput struct{…}
    
    The output of a shell tool call that was emitted.
    - ID string
      
      The unique ID of the shell call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - MaxOutputLength int64
      
      The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
    - Output []ResponseFunctionShellToolCallOutputOutput
      
      An array of shell call output contents
      - Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
      - Stderr string
        
        The standard error output that was captured.
      - Stdout string
        
        The standard output that was captured.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - Status ResponseFunctionShellToolCallOutputStatus
      
      The status of the shell call output. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
      - const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
      - const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
    - Type ShellCallOutput
      
      The type of the shell call output. Always shell_call_output.
      - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseApplyPatchToolCall struct{…}
    
    A tool call that applies file diffs by creating, deleting, or updating files.
    - ID string
      
      The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Operation ResponseApplyPatchToolCallOperationUnion
      
      One of the create_file, delete_file, or update_file operations applied via apply_patch.
      - type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
      - type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
      - type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
    - Status ResponseApplyPatchToolCallStatus
      
      The status of the apply patch tool call. One of in_progress or completed.
      - const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
      - const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
    - Type ApplyPatchCall
      
      The type of the item. Always apply_patch_call.
      - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseApplyPatchToolCallOutput struct{…}
    
    The output emitted by an apply patch tool call.
    - ID string
      
      The unique ID of the apply patch tool call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Status ResponseApplyPatchToolCallOutputStatus
      
      The status of the apply patch tool call output. One of completed or failed.
      - const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
      - const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
    - Type ApplyPatchCallOutput
      
      The type of the item. Always apply_patch_call_output.
      - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
    - CreatedBy string
      
      The ID of the entity that created this tool call output.
    - Output string
      
      Optional textual output returned by the apply patch tool.
  - type ResponseOutputItemMcpCall struct{…}
    
    An invocation of a tool on an MCP server.
    - ID string
      
      The unique ID of the tool call.
    - Arguments string
      
      A JSON string of the arguments passed to the tool.
    - Name string
      
      The name of the tool that was run.
    - ServerLabel string
      
      The label of the MCP server running the tool.
    - Type McpCall
      
      The type of the item. Always mcp_call.
      - const McpCallMcpCall McpCall = "mcp_call"
    - ApprovalRequestID string
      
      Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
    - Error string
      
      The error from the tool call, if any.
    - Output string
      
      The output from the tool call.
    - Status string
      
      The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
      - const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
      - const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
      - const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
      - const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
      - const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
  - type ResponseOutputItemMcpListTools struct{…}
    
    A list of tools available on an MCP server.
    - ID string
      
      The unique ID of the list.
    - ServerLabel string
      
      The label of the MCP server.
    - Tools []ResponseOutputItemMcpListToolsTool
      
      The tools available on the server.
      - InputSchema any
        
        The JSON schema describing the tool's input.
      - Name string
        
        The name of the tool.
      - Annotations any
        
        Additional annotations about the tool.
      - Description string
        
        The description of the tool.
    - Type McpListTools
      
      The type of the item. Always mcp_list_tools.
      - const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
    - Error string
      
      Error message if the server could not list tools.
  - type ResponseOutputItemMcpApprovalRequest struct{…}
    
    A request for human approval of a tool invocation.
    - ID string
      
      The unique ID of the approval request.
    - Arguments string
      
      A JSON string of arguments for the tool.
    - Name string
      
      The name of the tool to run.
    - ServerLabel string
      
      The label of the MCP server making the request.
    - Type McpApprovalRequest
      
      The type of the item. Always mcp_approval_request.
      - const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
  - type ResponseOutputItemMcpApprovalResponse struct{…}
    
    A response to an MCP approval request.
    - ID string
      
      The unique ID of the approval response
    - ApprovalRequestID string
      
      The ID of the approval request being answered.
    - Approve bool
      
      Whether the request was approved.
    - Type McpApprovalResponse
      
      The type of the item. Always mcp_approval_response.
      - const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
    - Reason string
      
      Optional reason for the decision.
  - type ResponseCustomToolCall struct{…}
    
    A call to a custom tool created by the model.
  - type ResponseCustomToolCallOutputItem struct{…}
    
    The output of a custom tool call from your code, being sent back to the model.
    - ID string
      
      The unique ID of the custom tool call output item.
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
      - const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
      - const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
    - CreatedBy string
      
      The identifier of the actor that created the item.
- ParallelToolCalls bool
  
  Whether to allow the model to run tool calls in parallel.
- Temperature float64
  
  What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
- ToolChoice ResponseToolChoiceUnion
  
  How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.
  - type ToolChoiceOptions string
    
    Controls which (if any) tool is called by the model.
    
    none means the model will not call any tool and instead generates a message.
    
    auto means the model can pick between generating a message or calling one or more tools.
    
    required means the model must call one or more tools.
    - const ToolChoiceOptionsNone ToolChoiceOptions = "none"
    - const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
    - const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
  - type ToolChoiceAllowed struct{…}
    
    Constrains the tools available to the model to a pre-defined set.
    - Mode ToolChoiceAllowedMode
      
      Constrains the tools available to the model to a pre-defined set.
      
      auto allows the model to pick from among the allowed tools and generate a message.
      
      required requires the model to call one or more of the allowed tools.
      - const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
      - const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
    - Tools []map[string, any]
      
      A list of tool definitions that the model should be allowed to call.
      
      For the Responses API, the list of tool definitions might look like:
```
[
  { "type": "function", "name": "get_weather" },
  { "type": "mcp", "server_label": "deepwiki" },
  { "type": "image_generation" }
]
```
    - Type AllowedTools
      
      Allowed tool configuration type. Always allowed_tools.
      - const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
  - type ToolChoiceTypes struct{…}
    
    Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
    - Type ToolChoiceTypesType
      
      The type of hosted tool the model should to use. Learn more about built-in tools.
      
      Allowed values are:
      - file_search
      - web_search_preview
      - computer
      - computer_use_preview
      - computer_use
      - code_interpreter
      - image_generation
      - const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
      - const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
      - const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
      - const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
      - const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
      - const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
      - const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
      - const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
  - type ToolChoiceFunction struct{…}
    
    Use this option to force the model to call a specific function.
    - Name string
      
      The name of the function to call.
    - Type Function
      
      For function calling, the type is always function.
      - const FunctionFunction Function = "function"
  - type ToolChoiceMcp struct{…}
    
    Use this option to force the model to call a specific tool on a remote MCP server.
    - ServerLabel string
      
      The label of the MCP server to use.
    - Type Mcp
      
      For MCP tools, the type is always mcp.
      - const McpMcp Mcp = "mcp"
    - Name string
      
      The name of the tool to call on the server.
  - type ToolChoiceCustom struct{…}
    
    Use this option to force the model to call a specific custom tool.
    - Name string
      
      The name of the custom tool to call.
    - Type Custom
      
      For custom tool calling, the type is always custom.
      - const CustomCustom Custom = "custom"
  - type ToolChoiceApplyPatch struct{…}
    
    Forces the model to call the apply_patch tool when executing a tool call.
    - Type ApplyPatch
      
      The tool to call. Always apply_patch.
      - const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
  - type ToolChoiceShell struct{…}
    
    Forces the model to call the shell tool when a tool call is required.
    - Type Shell
      
      The tool to call. Always shell.
      - const ShellShell Shell = "shell"
- Tools []ToolUnion
  
  An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
  
  We support the following categories of tools:
  - Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
  - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
  - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
  - type FunctionTool struct{…}
    
    Defines a function in your own code the model can choose to call. Learn more about function calling.
  - type FileSearchTool struct{…}
    
    A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
  - type ComputerTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
  - type ComputerUsePreviewTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
  - type WebSearchTool struct{…}
    
    Search the Internet for sources related to the prompt. Learn more about the web search tool.
  - type ToolMcp struct{…}
    
    Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
  - type ToolCodeInterpreter struct{…}
    
    A tool that runs Python code to help generate a response to a prompt.
  - type ToolImageGeneration struct{…}
    
    A tool that generates images using the GPT image models.
  - type ToolLocalShell struct{…}
    
    A tool that allows the model to execute shell commands in a local environment.
  - type FunctionShellTool struct{…}
    
    A tool that allows the model to execute shell commands.
  - type CustomTool struct{…}
    
    A custom tool that processes input using a specified format. Learn more about custom tools
  - type NamespaceTool struct{…}
    
    Groups function/custom tools under a shared namespace.
  - type ToolSearchTool struct{…}
    
    Hosted or BYOT tool search configuration for deferred tools.
  - type WebSearchPreviewTool struct{…}
    
    This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
  - type ApplyPatchTool struct{…}
    
    Allows the assistant to create, delete, or update files using unified diffs.
- TopP float64
  
  An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
  
  We generally recommend altering this or temperature but not both.
- Background bool
  
  Whether to run the model response in the background. Learn more.
- CompletedAt float64
  
  Unix timestamp (in seconds) of when this Response was completed. Only present when the status is completed.
- Conversation ResponseConversation
  
  The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
  - ID string
    
    The unique ID of the conversation that this response was associated with.
- MaxOutputTokens int64
  
  An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
- MaxToolCalls int64
  
  The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
- Moderation ResponseModeration
  
  Moderation results for the response input and output, if moderated completions were requested.
  - Input ResponseModerationInputUnion
    
    Moderation for the response input.
    - type ResponseModerationInputModerationResult struct{…}
      
      A moderation result produced for the response input or output.
      - Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
      - CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeText ResponseModerationInputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeImage ResponseModerationInputModerationResultCategoryAppliedInputType = "image"
      - CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
      - Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
      - Model string
        
        The moderation model that produced this result.
      - Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
    - type ResponseModerationInputError struct{…}
      
      An error produced while attempting moderation for the response input or output.
      - Code string
        
        The error code.
      - Message string
        
        The error message.
      - Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
  - Output ResponseModerationOutputUnion
    
    Moderation for the response output.
    - type ResponseModerationOutputModerationResult struct{…}
      
      A moderation result produced for the response input or output.
      - Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
      - CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeText ResponseModerationOutputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeImage ResponseModerationOutputModerationResultCategoryAppliedInputType = "image"
      - CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
      - Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
      - Model string
        
        The moderation model that produced this result.
      - Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
    - type ResponseModerationOutputError struct{…}
      
      An error produced while attempting moderation for the response input or output.
      - Code string
        
        The error code.
      - Message string
        
        The error message.
      - Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
- PreviousResponseID string
  
  The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
- Prompt ResponsePrompt
  
  Reference to a prompt template and its variables. Learn more.
  - ID string
    
    The unique identifier of the prompt template to use.
  - Variables map[string, ResponsePromptVariableUnion]
    
    Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
    - string
    - type ResponseInputText struct{…}
      
      A text input to the model.
    - type ResponseInputImage struct{…}
      
      An image input to the model. Learn about image inputs.
    - type ResponseInputFile struct{…}
      
      A file input to the model.
  - Version string
    
    Optional version of the prompt template.
- PromptCacheKey string
  
  Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
- PromptCacheRetention ResponsePromptCacheRetention
  
  The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.
  
  For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:
  - Organizations without ZDR enabled default to 24h.
  - Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.
  - const ResponsePromptCacheRetentionInMemory ResponsePromptCacheRetention = "in_memory"
  - const ResponsePromptCacheRetention24h ResponsePromptCacheRetention = "24h"
- Reasoning Reasoning
  
  gpt-5 and o-series models only
  
  Configuration options for reasoning models.
  - Context ReasoningContext
    
    Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
    - const ReasoningContextAuto ReasoningContext = "auto"
    - const ReasoningContextCurrentTurn ReasoningContext = "current_turn"
    - const ReasoningContextAllTurns ReasoningContext = "all_turns"
  - Effort ReasoningEffort
    
    Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
    - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
    - All models before gpt-5.1 default to medium reasoning effort, and do not support none.
    - The gpt-5-pro model defaults to (and only supports) high reasoning effort.
    - xhigh is supported for all models after gpt-5.1-codex-max.
    - const ReasoningEffortNone ReasoningEffort = "none"
    - const ReasoningEffortMinimal ReasoningEffort = "minimal"
    - const ReasoningEffortLow ReasoningEffort = "low"
    - const ReasoningEffortMedium ReasoningEffort = "medium"
    - const ReasoningEffortHigh ReasoningEffort = "high"
    - const ReasoningEffortXhigh ReasoningEffort = "xhigh"
  - GenerateSummary ReasoningGenerateSummary
    
    Deprecated: use summary instead.
    
    A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
    - const ReasoningGenerateSummaryAuto ReasoningGenerateSummary = "auto"
    - const ReasoningGenerateSummaryConcise ReasoningGenerateSummary = "concise"
    - const ReasoningGenerateSummaryDetailed ReasoningGenerateSummary = "detailed"
  - Summary ReasoningSummary
    
    A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
    
    concise is supported for computer-use-preview models and all reasoning models after gpt-5.
    - const ReasoningSummaryAuto ReasoningSummary = "auto"
    - const ReasoningSummaryConcise ReasoningSummary = "concise"
    - const ReasoningSummaryDetailed ReasoningSummary = "detailed"
- SafetyIdentifier string
  
  A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
- ServiceTier ResponseServiceTier
  
  Specifies the processing type used for serving the request.
  - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
  - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
  - If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
  - When not set, the default behavior is 'auto'.
  When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
  - const ResponseServiceTierAuto ResponseServiceTier = "auto"
  - const ResponseServiceTierDefault ResponseServiceTier = "default"
  - const ResponseServiceTierFlex ResponseServiceTier = "flex"
  - const ResponseServiceTierScale ResponseServiceTier = "scale"
  - const ResponseServiceTierPriority ResponseServiceTier = "priority"
- Status ResponseStatus
  
  The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
  - const ResponseStatusCompleted ResponseStatus = "completed"
  - const ResponseStatusFailed ResponseStatus = "failed"
  - const ResponseStatusInProgress ResponseStatus = "in_progress"
  - const ResponseStatusCancelled ResponseStatus = "cancelled"
  - const ResponseStatusQueued ResponseStatus = "queued"
  - const ResponseStatusIncomplete ResponseStatus = "incomplete"
- Text ResponseTextConfig
  
  Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
  - Text inputs and outputs
  - Structured Outputs
  - Format ResponseFormatTextConfigUnion
    
    An object specifying the format that the model must output.
    
    Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
    
    The default format is { "type": "text" } with no additional options.
    
    Not recommended for gpt-4o and newer models:
    
    Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
    - type ResponseFormatText struct{…}
      
      Default response format. Used to generate text responses.
      - Type Text
        
        The type of response format being defined. Always text.
        
        const TextText Text = "text"
    - type ResponseFormatTextJSONSchemaConfig struct{…}
      
      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
      - Name string
        
        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
      - Schema map[string, any]
        
        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
      - Type JSONSchema
        
        The type of response format being defined. Always json_schema.
        
        const JSONSchemaJSONSchema JSONSchema = "json_schema"
      - Description string
        
        A description of what the response format is for, used by the model to determine how to respond in the format.
      - Strict bool
        
        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
    - type ResponseFormatJSONObject struct{…}
      
      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
      - Type JSONObject
        
        The type of response format being defined. Always json_object.
        
        const JSONObjectJSONObject JSONObject = "json_object"
  - Verbosity ResponseTextConfigVerbosity
    
    Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
    - const ResponseTextConfigVerbosityLow ResponseTextConfigVerbosity = "low"
    - const ResponseTextConfigVerbosityMedium ResponseTextConfigVerbosity = "medium"
    - const ResponseTextConfigVerbosityHigh ResponseTextConfigVerbosity = "high"
- TopLogprobs int64
  
  An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
- Truncation ResponseTruncation
  
  The truncation strategy to use for the model response.
  - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
  - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
  - const ResponseTruncationAuto ResponseTruncation = "auto"
  - const ResponseTruncationDisabled ResponseTruncation = "disabled"
- Usage ResponseUsage
  
  Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
  - InputTokens int64
    
    The number of input tokens.
  - InputTokensDetails ResponseUsageInputTokensDetails
    
    A detailed breakdown of the input tokens.
    - CachedTokens int64
      
      The number of tokens that were retrieved from the cache. More on prompt caching.
  - OutputTokens int64
    
    The number of output tokens.
  - OutputTokensDetails ResponseUsageOutputTokensDetails
    
    A detailed breakdown of the output tokens.
    - ReasoningTokens int64
      
      The number of reasoning tokens.
  - TotalTokens int64
    
    The total number of tokens used.
- User string
  
  This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  response, err := client.Responses.Cancel(context.TODO(), "resp_677efb5139a88190b512bc3fef8e535d")
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", response.ID)
}

Response

{
  "id": "id",
  "created_at": 0,
  "error": {
    "code": "server_error",
    "message": "message"
  },
  "incomplete_details": {
    "reason": "max_output_tokens"
  },
  "instructions": "string",
  "metadata": {
    "foo": "string"
  },
  "model": "gpt-5.1",
  "object": "response",
  "output": [
    {
      "id": "id",
      "content": [
        {
          "annotations": [
            {
              "file_id": "file_id",
              "filename": "filename",
              "index": 0,
              "type": "file_citation"
            }
          ],
          "text": "text",
          "type": "output_text",
          "logprobs": [
            {
              "token": "token",
              "bytes": [
                0
              ],
              "logprob": 0,
              "top_logprobs": [
                {
                  "token": "token",
                  "bytes": [
                    0
                  ],
                  "logprob": 0
                }
              ]
            }
          ]
        }
      ],
      "role": "assistant",
      "status": "in_progress",
      "type": "message",
      "phase": "commentary"
    }
  ],
  "parallel_tool_calls": true,
  "temperature": 1,
  "tool_choice": "none",
  "tools": [
    {
      "name": "name",
      "parameters": {
        "foo": "bar"
      },
      "strict": true,
      "type": "function",
      "defer_loading": true,
      "description": "description"
    }
  ],
  "top_p": 1,
  "background": true,
  "completed_at": 0,
  "conversation": {
    "id": "id"
  },
  "max_output_tokens": 0,
  "max_tool_calls": 0,
  "moderation": {
    "input": {
      "categories": {
        "foo": true
      },
      "category_applied_input_types": {
        "foo": [
          "text"
        ]
      },
      "category_scores": {
        "foo": 0
      },
      "flagged": true,
      "model": "model",
      "type": "moderation_result"
    },
    "output": {
      "categories": {
        "foo": true
      },
      "category_applied_input_types": {
        "foo": [
          "text"
        ]
      },
      "category_scores": {
        "foo": 0
      },
      "flagged": true,
      "model": "model",
      "type": "moderation_result"
    }
  },
  "output_text": "output_text",
  "previous_response_id": "previous_response_id",
  "prompt": {
    "id": "id",
    "variables": {
      "foo": "string"
    },
    "version": "version"
  },
  "prompt_cache_key": "prompt-cache-key-1234",
  "prompt_cache_retention": "in_memory",
  "reasoning": {
    "context": "auto",
    "effort": "none",
    "generate_summary": "auto",
    "summary": "auto"
  },
  "safety_identifier": "safety-identifier-1234",
  "service_tier": "auto",
  "status": "completed",
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "low"
  },
  "top_logprobs": 0,
  "truncation": "auto",
  "usage": {
    "input_tokens": 0,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 0,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 0
  },
  "user": "user-1234"
}

Compact a response

client.Responses.Compact(ctx, body) (*CompactedResponse, error)

post /responses/compact

Compact a conversation. Returns a compacted response object.

Learn when and how to compact long-running conversations in the conversation state guide. For ZDR-compatible compaction details, see Compaction (advanced).

Parameters

body ResponseCompactParams
- Model param.Field[ResponseCompactParamsModel]
  
  Model ID used to generate the response, like gpt-5 or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
  - type ResponseCompactParamsModel string
    
    Model ID used to generate the response, like gpt-5 or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
    - const ResponseCompactParamsModelGPT5_4 ResponseCompactParamsModel = "gpt-5.4"
    - const ResponseCompactParamsModelGPT5_4Mini ResponseCompactParamsModel = "gpt-5.4-mini"
    - const ResponseCompactParamsModelGPT5_4Nano ResponseCompactParamsModel = "gpt-5.4-nano"
    - const ResponseCompactParamsModelGPT5_4Mini2026_03_17 ResponseCompactParamsModel = "gpt-5.4-mini-2026-03-17"
    - const ResponseCompactParamsModelGPT5_4Nano2026_03_17 ResponseCompactParamsModel = "gpt-5.4-nano-2026-03-17"
    - const ResponseCompactParamsModelGPT5_3ChatLatest ResponseCompactParamsModel = "gpt-5.3-chat-latest"
    - const ResponseCompactParamsModelGPT5_2 ResponseCompactParamsModel = "gpt-5.2"
    - const ResponseCompactParamsModelGPT5_2_2025_12_11 ResponseCompactParamsModel = "gpt-5.2-2025-12-11"
    - const ResponseCompactParamsModelGPT5_2ChatLatest ResponseCompactParamsModel = "gpt-5.2-chat-latest"
    - const ResponseCompactParamsModelGPT5_2Pro ResponseCompactParamsModel = "gpt-5.2-pro"
    - const ResponseCompactParamsModelGPT5_2Pro2025_12_11 ResponseCompactParamsModel = "gpt-5.2-pro-2025-12-11"
    - const ResponseCompactParamsModelGPT5_1 ResponseCompactParamsModel = "gpt-5.1"
    - const ResponseCompactParamsModelGPT5_1_2025_11_13 ResponseCompactParamsModel = "gpt-5.1-2025-11-13"
    - const ResponseCompactParamsModelGPT5_1Codex ResponseCompactParamsModel = "gpt-5.1-codex"
    - const ResponseCompactParamsModelGPT5_1Mini ResponseCompactParamsModel = "gpt-5.1-mini"
    - const ResponseCompactParamsModelGPT5_1ChatLatest ResponseCompactParamsModel = "gpt-5.1-chat-latest"
    - const ResponseCompactParamsModelGPT5 ResponseCompactParamsModel = "gpt-5"
    - const ResponseCompactParamsModelGPT5Mini ResponseCompactParamsModel = "gpt-5-mini"
    - const ResponseCompactParamsModelGPT5Nano ResponseCompactParamsModel = "gpt-5-nano"
    - const ResponseCompactParamsModelGPT5_2025_08_07 ResponseCompactParamsModel = "gpt-5-2025-08-07"
    - const ResponseCompactParamsModelGPT5Mini2025_08_07 ResponseCompactParamsModel = "gpt-5-mini-2025-08-07"
    - const ResponseCompactParamsModelGPT5Nano2025_08_07 ResponseCompactParamsModel = "gpt-5-nano-2025-08-07"
    - const ResponseCompactParamsModelGPT5ChatLatest ResponseCompactParamsModel = "gpt-5-chat-latest"
    - const ResponseCompactParamsModelGPT4_1 ResponseCompactParamsModel = "gpt-4.1"
    - const ResponseCompactParamsModelGPT4_1Mini ResponseCompactParamsModel = "gpt-4.1-mini"
    - const ResponseCompactParamsModelGPT4_1Nano ResponseCompactParamsModel = "gpt-4.1-nano"
    - const ResponseCompactParamsModelGPT4_1_2025_04_14 ResponseCompactParamsModel = "gpt-4.1-2025-04-14"
    - const ResponseCompactParamsModelGPT4_1Mini2025_04_14 ResponseCompactParamsModel = "gpt-4.1-mini-2025-04-14"
    - const ResponseCompactParamsModelGPT4_1Nano2025_04_14 ResponseCompactParamsModel = "gpt-4.1-nano-2025-04-14"
    - const ResponseCompactParamsModelO4Mini ResponseCompactParamsModel = "o4-mini"
    - const ResponseCompactParamsModelO4Mini2025_04_16 ResponseCompactParamsModel = "o4-mini-2025-04-16"
    - const ResponseCompactParamsModelO3 ResponseCompactParamsModel = "o3"
    - const ResponseCompactParamsModelO3_2025_04_16 ResponseCompactParamsModel = "o3-2025-04-16"
    - const ResponseCompactParamsModelO3Mini ResponseCompactParamsModel = "o3-mini"
    - const ResponseCompactParamsModelO3Mini2025_01_31 ResponseCompactParamsModel = "o3-mini-2025-01-31"
    - const ResponseCompactParamsModelO1 ResponseCompactParamsModel = "o1"
    - const ResponseCompactParamsModelO1_2024_12_17 ResponseCompactParamsModel = "o1-2024-12-17"
    - const ResponseCompactParamsModelO1Preview ResponseCompactParamsModel = "o1-preview"
    - const ResponseCompactParamsModelO1Preview2024_09_12 ResponseCompactParamsModel = "o1-preview-2024-09-12"
    - const ResponseCompactParamsModelO1Mini ResponseCompactParamsModel = "o1-mini"
    - const ResponseCompactParamsModelO1Mini2024_09_12 ResponseCompactParamsModel = "o1-mini-2024-09-12"
    - const ResponseCompactParamsModelGPT4o ResponseCompactParamsModel = "gpt-4o"
    - const ResponseCompactParamsModelGPT4o2024_11_20 ResponseCompactParamsModel = "gpt-4o-2024-11-20"
    - const ResponseCompactParamsModelGPT4o2024_08_06 ResponseCompactParamsModel = "gpt-4o-2024-08-06"
    - const ResponseCompactParamsModelGPT4o2024_05_13 ResponseCompactParamsModel = "gpt-4o-2024-05-13"
    - const ResponseCompactParamsModelGPT4oAudioPreview ResponseCompactParamsModel = "gpt-4o-audio-preview"
    - const ResponseCompactParamsModelGPT4oAudioPreview2024_10_01 ResponseCompactParamsModel = "gpt-4o-audio-preview-2024-10-01"
    - const ResponseCompactParamsModelGPT4oAudioPreview2024_12_17 ResponseCompactParamsModel = "gpt-4o-audio-preview-2024-12-17"
    - const ResponseCompactParamsModelGPT4oAudioPreview2025_06_03 ResponseCompactParamsModel = "gpt-4o-audio-preview-2025-06-03"
    - const ResponseCompactParamsModelGPT4oMiniAudioPreview ResponseCompactParamsModel = "gpt-4o-mini-audio-preview"
    - const ResponseCompactParamsModelGPT4oMiniAudioPreview2024_12_17 ResponseCompactParamsModel = "gpt-4o-mini-audio-preview-2024-12-17"
    - const ResponseCompactParamsModelGPT4oSearchPreview ResponseCompactParamsModel = "gpt-4o-search-preview"
    - const ResponseCompactParamsModelGPT4oMiniSearchPreview ResponseCompactParamsModel = "gpt-4o-mini-search-preview"
    - const ResponseCompactParamsModelGPT4oSearchPreview2025_03_11 ResponseCompactParamsModel = "gpt-4o-search-preview-2025-03-11"
    - const ResponseCompactParamsModelGPT4oMiniSearchPreview2025_03_11 ResponseCompactParamsModel = "gpt-4o-mini-search-preview-2025-03-11"
    - const ResponseCompactParamsModelChatgpt4oLatest ResponseCompactParamsModel = "chatgpt-4o-latest"
    - const ResponseCompactParamsModelCodexMiniLatest ResponseCompactParamsModel = "codex-mini-latest"
    - const ResponseCompactParamsModelGPT4oMini ResponseCompactParamsModel = "gpt-4o-mini"
    - const ResponseCompactParamsModelGPT4oMini2024_07_18 ResponseCompactParamsModel = "gpt-4o-mini-2024-07-18"
    - const ResponseCompactParamsModelGPT4Turbo ResponseCompactParamsModel = "gpt-4-turbo"
    - const ResponseCompactParamsModelGPT4Turbo2024_04_09 ResponseCompactParamsModel = "gpt-4-turbo-2024-04-09"
    - const ResponseCompactParamsModelGPT4_0125Preview ResponseCompactParamsModel = "gpt-4-0125-preview"
    - const ResponseCompactParamsModelGPT4TurboPreview ResponseCompactParamsModel = "gpt-4-turbo-preview"
    - const ResponseCompactParamsModelGPT4_1106Preview ResponseCompactParamsModel = "gpt-4-1106-preview"
    - const ResponseCompactParamsModelGPT4VisionPreview ResponseCompactParamsModel = "gpt-4-vision-preview"
    - const ResponseCompactParamsModelGPT4 ResponseCompactParamsModel = "gpt-4"
    - const ResponseCompactParamsModelGPT4_0314 ResponseCompactParamsModel = "gpt-4-0314"
    - const ResponseCompactParamsModelGPT4_0613 ResponseCompactParamsModel = "gpt-4-0613"
    - const ResponseCompactParamsModelGPT4_32k ResponseCompactParamsModel = "gpt-4-32k"
    - const ResponseCompactParamsModelGPT4_32k0314 ResponseCompactParamsModel = "gpt-4-32k-0314"
    - const ResponseCompactParamsModelGPT4_32k0613 ResponseCompactParamsModel = "gpt-4-32k-0613"
    - const ResponseCompactParamsModelGPT3_5Turbo ResponseCompactParamsModel = "gpt-3.5-turbo"
    - const ResponseCompactParamsModelGPT3_5Turbo16k ResponseCompactParamsModel = "gpt-3.5-turbo-16k"
    - const ResponseCompactParamsModelGPT3_5Turbo0301 ResponseCompactParamsModel = "gpt-3.5-turbo-0301"
    - const ResponseCompactParamsModelGPT3_5Turbo0613 ResponseCompactParamsModel = "gpt-3.5-turbo-0613"
    - const ResponseCompactParamsModelGPT3_5Turbo1106 ResponseCompactParamsModel = "gpt-3.5-turbo-1106"
    - const ResponseCompactParamsModelGPT3_5Turbo0125 ResponseCompactParamsModel = "gpt-3.5-turbo-0125"
    - const ResponseCompactParamsModelGPT3_5Turbo16k0613 ResponseCompactParamsModel = "gpt-3.5-turbo-16k-0613"
    - const ResponseCompactParamsModelO1Pro ResponseCompactParamsModel = "o1-pro"
    - const ResponseCompactParamsModelO1Pro2025_03_19 ResponseCompactParamsModel = "o1-pro-2025-03-19"
    - const ResponseCompactParamsModelO3Pro ResponseCompactParamsModel = "o3-pro"
    - const ResponseCompactParamsModelO3Pro2025_06_10 ResponseCompactParamsModel = "o3-pro-2025-06-10"
    - const ResponseCompactParamsModelO3DeepResearch ResponseCompactParamsModel = "o3-deep-research"
    - const ResponseCompactParamsModelO3DeepResearch2025_06_26 ResponseCompactParamsModel = "o3-deep-research-2025-06-26"
    - const ResponseCompactParamsModelO4MiniDeepResearch ResponseCompactParamsModel = "o4-mini-deep-research"
    - const ResponseCompactParamsModelO4MiniDeepResearch2025_06_26 ResponseCompactParamsModel = "o4-mini-deep-research-2025-06-26"
    - const ResponseCompactParamsModelComputerUsePreview ResponseCompactParamsModel = "computer-use-preview"
    - const ResponseCompactParamsModelComputerUsePreview2025_03_11 ResponseCompactParamsModel = "computer-use-preview-2025-03-11"
    - const ResponseCompactParamsModelGPT5Codex ResponseCompactParamsModel = "gpt-5-codex"
    - const ResponseCompactParamsModelGPT5Pro ResponseCompactParamsModel = "gpt-5-pro"
    - const ResponseCompactParamsModelGPT5Pro2025_10_06 ResponseCompactParamsModel = "gpt-5-pro-2025-10-06"
    - const ResponseCompactParamsModelGPT5_1CodexMax ResponseCompactParamsModel = "gpt-5.1-codex-max"
  - string
- Input param.Field[ResponseCompactParamsInputUnion]
  
  Text, image, or file inputs to the model, used to generate a response
  - string
  - type ResponseCompactParamsInputArray []ResponseInputItemUnion
    
    A list of one or many input items to the model, containing different content types.
    - type EasyInputMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
      - Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
      - Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
      - Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
    - type ResponseInputItemMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
      - Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
      - Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
      - Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
      - Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
      - ID string
        
        The unique ID of the output message.
      - Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
      - Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
      - Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
      - Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
      - Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
      - ID string
        
        The unique ID of the file search tool call.
      - Queries []string
        
        The queries used to search for files.
      - Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
      - Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
      - Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
      - ID string
        
        The unique ID of the computer call.
      - CallID string
        
        An identifier used when responding to the tool call with output.
      - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
      - Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
      - Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
      - Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
    - type ResponseInputItemComputerCallOutput struct{…}
      
      The output of a computer tool call.
      - CallID string
        
        The ID of the computer tool call that produced the output.
      - Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
      - Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
      - ID string
        
        The ID of the computer tool call output.
      - AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
      - ID string
        
        The unique ID of the web search tool call.
      - Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
      - Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
      - Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
      - Arguments string
        
        A JSON string of the arguments to pass to the function.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Name string
        
        The name of the function to run.
      - Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
      - ID string
        
        The unique ID of the function tool call.
      - Namespace string
        
        The namespace of the function to run.
      - Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
    - type ResponseInputItemFunctionCallOutput struct{…}
      
      The output of a function tool call.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
      - ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
    - type ResponseInputItemToolSearchCall struct{…}
      - Arguments any
        
        The arguments supplied to the tool search call.
      - Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
      - ID string
        
        The unique ID of this tool search call.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
      - Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
    - type ResponseToolSearchOutputItemParamResp struct{…}
      - Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
      - Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
      - ID string
        
        The unique ID of this tool search output.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
      - Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
    - type ResponseInputItemAdditionalTools struct{…}
      - Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
      - Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
      - ID string
        
        The unique ID of this additional tools item.
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
      - ID string
        
        The unique identifier of the reasoning content.
      - Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
      - Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
      - Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
      - EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
      - Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
    - type ResponseCompactionItemParamResp struct{…}
      
      A compaction item generated by the v1/responses/compact API.
      - EncryptedContent string
        
        The encrypted content of the compaction summary.
      - Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
      - ID string
        
        The ID of the compaction item.
    - type ResponseInputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
      - ID string
        
        The unique ID of the image generation call.
      - Result string
        
        The generated image encoded in base64.
      - Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
      - Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
      - ID string
        
        The unique ID of the code interpreter tool call.
      - Code string
        
        The code to run, or null if not available.
      - ContainerID string
        
        The ID of the container used to run the code.
      - Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
      - Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
      - Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
    - type ResponseInputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
      - ID string
        
        The unique ID of the local shell call.
      - Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
      - CallID string
        
        The unique ID of the local shell tool call generated by the model.
      - Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
      - Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
    - type ResponseInputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
      - ID string
        
        The unique ID of the local shell tool call generated by the model.
      - Output string
        
        A JSON string of the output of the local shell tool call.
      - Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
    - type ResponseInputItemShellCall struct{…}
      
      A tool representing a request to execute one or more shell commands.
      - Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
      - ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
      - Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
      - Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
    - type ResponseInputItemShellCallOutput struct{…}
      
      The streamed output items emitted by a shell tool call.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
      - Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
      - ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
      - MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
      - Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
    - type ResponseInputItemApplyPatchCall struct{…}
      
      A tool call representing a request to create, delete, or update files using diff patches.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
      - Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
      - Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
      - ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - type ResponseInputItemApplyPatchCallOutput struct{…}
      
      The streamed output emitted by an apply patch tool call.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
      - Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
      - ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
      - Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
    - type ResponseInputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
      - ID string
        
        The unique ID of the list.
      - ServerLabel string
        
        The label of the MCP server.
      - Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
      - Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
      - Error string
        
        Error message if the server could not list tools.
    - type ResponseInputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
      - ID string
        
        The unique ID of the approval request.
      - Arguments string
        
        A JSON string of arguments for the tool.
      - Name string
        
        The name of the tool to run.
      - ServerLabel string
        
        The label of the MCP server making the request.
      - Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
    - type ResponseInputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
      - ApprovalRequestID string
        
        The ID of the approval request being answered.
      - Approve bool
        
        Whether the request was approved.
      - Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
      - ID string
        
        The unique ID of the approval response
      - Reason string
        
        Optional reason for the decision.
    - type ResponseInputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
      - ID string
        
        The unique ID of the tool call.
      - Arguments string
        
        A JSON string of the arguments passed to the tool.
      - Name string
        
        The name of the tool that was run.
      - ServerLabel string
        
        The label of the MCP server running the tool.
      - Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
      - ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
      - Error string
        
        The error from the tool call, if any.
      - Output string
        
        The output from the tool call.
      - Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
    - type ResponseCustomToolCallOutput struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
      - CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
      - Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
      - ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
      - CallID string
        
        An identifier used to map this custom tool call to a tool call output.
      - Input string
        
        The input for the custom tool call generated by the model.
      - Name string
        
        The name of the custom tool being called.
      - Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
      - ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
      - Namespace string
        
        The namespace of the custom tool being called.
    - type ResponseInputItemCompactionTrigger struct{…}
      
      Compacts the current context. Must be the final input item.
      - Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
    - type ResponseInputItemItemReference struct{…}
      
      An internal identifier for an item to reference.
      - ID string
        
        The ID of the item to reference.
      - Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
- Instructions param.Field[string]
  
  A system (or developer) message inserted into the model's context. When used along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
- PreviousResponseID param.Field[string]
  
  The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
- PromptCacheKey param.Field[string]
  
  A key to use when reading from or writing to the prompt cache.
- PromptCacheRetention param.Field[ResponseCompactParamsPromptCacheRetention]
  
  How long to retain a prompt cache entry created by this request.
  - const ResponseCompactParamsPromptCacheRetentionInMemory ResponseCompactParamsPromptCacheRetention = "in_memory"
  - const ResponseCompactParamsPromptCacheRetention24h ResponseCompactParamsPromptCacheRetention = "24h"
- ServiceTier param.Field[ResponseCompactParamsServiceTier]
  
  The service tier to use for this request.
  - const ResponseCompactParamsServiceTierAuto ResponseCompactParamsServiceTier = "auto"
  - const ResponseCompactParamsServiceTierDefault ResponseCompactParamsServiceTier = "default"
  - const ResponseCompactParamsServiceTierFlex ResponseCompactParamsServiceTier = "flex"
  - const ResponseCompactParamsServiceTierPriority ResponseCompactParamsServiceTier = "priority"

Returns

type CompactedResponse struct{…}
- ID string
  
  The unique identifier for the compacted response.
- CreatedAt int64
  
  Unix timestamp (in seconds) when the compacted conversation was created.
- Object ResponseCompaction
  
  The object type. Always response.compaction.
  - const ResponseCompactionResponseCompaction ResponseCompaction = "response.compaction"
- Output []ResponseOutputItemUnion
  
  The compacted list of output items. This is a list of all user messages, followed by a single compaction item.
  - type ResponseOutputMessage struct{…}
    
    An output message from the model.
    - ID string
      
      The unique ID of the output message.
    - Content []ResponseOutputMessageContentUnion
      
      The content of the output message.
      - type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
      - type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
    - Role Assistant
      
      The role of the output message. Always assistant.
      - const AssistantAssistant Assistant = "assistant"
    - Status ResponseOutputMessageStatus
      
      The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
      - const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
      - const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
      - const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
    - Type Message
      
      The type of the output message. Always message.
      - const MessageMessage Message = "message"
    - Phase ResponseOutputMessagePhase
      
      Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
      - const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
      - const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
  - type ResponseFileSearchToolCall struct{…}
    
    The results of a file search tool call. See the file search guide for more information.
    - ID string
      
      The unique ID of the file search tool call.
    - Queries []string
      
      The queries used to search for files.
    - Status ResponseFileSearchToolCallStatus
      
      The status of the file search tool call. One of in_progress, searching, incomplete or failed,
      - const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
      - const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
      - const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
      - const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
      - const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
    - Type FileSearchCall
      
      The type of the file search tool call. Always file_search_call.
      - const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
    - Results []ResponseFileSearchToolCallResult
      
      The results of the file search tool call.
      - Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
      - FileID string
        
        The unique ID of the file.
      - Filename string
        
        The name of the file.
      - Score float64
        
        The relevance score of the file - a value between 0 and 1.
      - Text string
        
        The text that was retrieved from the file.
  - type ResponseFunctionToolCall struct{…}
    
    A tool call to run a function. See the function calling guide for more information.
    - Arguments string
      
      A JSON string of the arguments to pass to the function.
    - CallID string
      
      The unique ID of the function tool call generated by the model.
    - Name string
      
      The name of the function to run.
    - Type FunctionCall
      
      The type of the function tool call. Always function_call.
      - const FunctionCallFunctionCall FunctionCall = "function_call"
    - ID string
      
      The unique ID of the function tool call.
    - Namespace string
      
      The namespace of the function to run.
    - Status ResponseFunctionToolCallStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
      - const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
      - const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
  - type ResponseFunctionToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the function call tool output.
    - CallID string
      
      The unique ID of the function tool call generated by the model.
    - Output ResponseFunctionToolCallOutputItemOutputUnion
      
      The output from the function call generated by your code. Can be a string or an list of output content.
      - string
      - type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
    - Status ResponseFunctionToolCallOutputItemStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
      - const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
      - const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
    - Type FunctionCallOutput
      
      The type of the function tool call output. Always function_call_output.
      - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseFunctionWebSearch struct{…}
    
    The results of a web search tool call. See the web search guide for more information.
    - ID string
      
      The unique ID of the web search tool call.
    - Action ResponseFunctionWebSearchActionUnion
      
      An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
      - type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
      - type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
      - type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
    - Status ResponseFunctionWebSearchStatus
      
      The status of the web search tool call.
      - const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
      - const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
      - const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
      - const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
    - Type WebSearchCall
      
      The type of the web search tool call. Always web_search_call.
      - const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
  - type ResponseComputerToolCall struct{…}
    
    A tool call to a computer use tool. See the computer use guide for more information.
    - ID string
      
      The unique ID of the computer call.
    - CallID string
      
      An identifier used when responding to the tool call with output.
    - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
      
      The pending safety checks for the computer call.
      - ID string
        
        The ID of the pending safety check.
      - Code string
        
        The type of the pending safety check.
      - Message string
        
        Details about the pending safety check.
    - Status ResponseComputerToolCallStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
      - const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
      - const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
    - Type ResponseComputerToolCallType
      
      The type of the computer call. Always computer_call.
      - const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
    - Action ResponseComputerToolCallActionUnion
      
      A click action.
      - type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
      - type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
      - type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
      - type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
      - type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
      - type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
      - type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
      - type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
      - type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
    - Actions ComputerActionList
      
      Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
      - type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
      - type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
      - type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
      - type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
      - type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
      - type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
      - type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
      - type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
      - type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
  - type ResponseComputerToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the computer call tool output.
    - CallID string
      
      The ID of the computer tool call that produced the output.
    - Output ResponseComputerToolCallOutputScreenshot
      
      A computer screenshot image used with the computer use tool.
      - Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
      - FileID string
        
        The identifier of an uploaded file that contains the screenshot.
      - ImageURL string
        
        The URL of the screenshot image.
    - Status ResponseComputerToolCallOutputItemStatus
      
      The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
      - const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
      - const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
      - const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
      - const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
    - Type ComputerCallOutput
      
      The type of the computer tool call output. Always computer_call_output.
      - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
    - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
      
      The safety checks reported by the API that have been acknowledged by the developer.
      - ID string
        
        The ID of the pending safety check.
      - Code string
        
        The type of the pending safety check.
      - Message string
        
        Details about the pending safety check.
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseReasoningItem struct{…}
    
    A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
    - ID string
      
      The unique identifier of the reasoning content.
    - Summary []ResponseReasoningItemSummary
      
      Reasoning summary content.
      - Text string
        
        A summary of the reasoning output from the model so far.
      - Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
    - Type Reasoning
      
      The type of the object. Always reasoning.
      - const ReasoningReasoning Reasoning = "reasoning"
    - Content []ResponseReasoningItemContent
      
      Reasoning text content.
      - Text string
        
        The reasoning text from the model.
      - Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
    - EncryptedContent string
      
      The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
    - Status ResponseReasoningItemStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
      - const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
      - const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
  - type ResponseToolSearchCall struct{…}
    - ID string
      
      The unique ID of the tool search call item.
    - Arguments any
      
      Arguments used for the tool search call.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchCallExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
      - const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
    - Status ResponseToolSearchCallStatus
      
      The status of the tool search call item that was recorded.
      - const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
      - const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
      - const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
    - Type ToolSearchCall
      
      The type of the item. Always tool_search_call.
      - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseToolSearchOutputItem struct{…}
    - ID string
      
      The unique ID of the tool search output item.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchOutputItemExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
      - const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
    - Status ResponseToolSearchOutputItemStatus
      
      The status of the tool search output item that was recorded.
      - const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
      - const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
      - const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
    - Tools []ToolUnion
      
      The loaded tool definitions returned by tool search.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
    - Type ToolSearchOutput
      
      The type of the item. Always tool_search_output.
      - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemAdditionalTools struct{…}
    - ID string
      
      The unique ID of the additional tools item.
    - Role string
      
      The role that provided the additional tools.
      - const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
      - const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
      - const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
      - const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
      - const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
      - const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
      - const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
      - const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
    - Tools []ToolUnion
      
      The additional tool definitions made available at this item.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - Type AdditionalTools
      
      The type of the item. Always additional_tools.
      - const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
  - type ResponseCompactionItem struct{…}
    
    A compaction item generated by the v1/responses/compact API.
    - ID string
      
      The unique ID of the compaction item.
    - EncryptedContent string
      
      The encrypted content that was produced by compaction.
    - Type Compaction
      
      The type of the item. Always compaction.
      - const CompactionCompaction Compaction = "compaction"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemImageGenerationCall struct{…}
    
    An image generation request made by the model.
    - ID string
      
      The unique ID of the image generation call.
    - Result string
      
      The generated image encoded in base64.
    - Status string
      
      The status of the image generation call.
      - const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
      - const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
      - const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
      - const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
    - Type ImageGenerationCall
      
      The type of the image generation call. Always image_generation_call.
      - const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
  - type ResponseCodeInterpreterToolCall struct{…}
    
    A tool call to run code.
    - ID string
      
      The unique ID of the code interpreter tool call.
    - Code string
      
      The code to run, or null if not available.
    - ContainerID string
      
      The ID of the container used to run the code.
    - Outputs []ResponseCodeInterpreterToolCallOutputUnion
      
      The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
      - type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
      - type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
    - Status ResponseCodeInterpreterToolCallStatus
      
      The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
      - const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
      - const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
      - const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
      - const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
      - const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
    - Type CodeInterpreterCall
      
      The type of the code interpreter tool call. Always code_interpreter_call.
      - const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
  - type ResponseOutputItemLocalShellCall struct{…}
    
    A tool call to run a command on the local shell.
    - ID string
      
      The unique ID of the local shell call.
    - Action ResponseOutputItemLocalShellCallAction
      
      Execute a shell command on the server.
      - Command []string
        
        The command to run.
      - Env map[string, string]
        
        Environment variables to set for the command.
      - Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
      - User string
        
        Optional user to run the command as.
      - WorkingDirectory string
        
        Optional working directory to run the command in.
    - CallID string
      
      The unique ID of the local shell tool call generated by the model.
    - Status string
      
      The status of the local shell call.
      - const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
      - const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
    - Type LocalShellCall
      
      The type of the local shell call. Always local_shell_call.
      - const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
  - type ResponseOutputItemLocalShellCallOutput struct{…}
    
    The output of a local shell tool call.
    - ID string
      
      The unique ID of the local shell tool call generated by the model.
    - Output string
      
      A JSON string of the output of the local shell tool call.
    - Type LocalShellCallOutput
      
      The type of the local shell tool call output. Always local_shell_call_output.
      - const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete.
      - const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
      - const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
  - type ResponseFunctionShellToolCall struct{…}
    
    A tool call that executes one or more shell commands in a managed environment.
    - ID string
      
      The unique ID of the shell tool call. Populated when this item is returned via API.
    - Action ResponseFunctionShellToolCallAction
      
      The shell commands and limits that describe how to run the tool call.
      - Commands []string
      - MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - Environment ResponseFunctionShellToolCallEnvironmentUnion
      
      Represents the use of a local environment to perform shell actions.
      - type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
      - type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
    - Status ResponseFunctionShellToolCallStatus
      
      The status of the shell call. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
      - const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
      - const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
    - Type ShellCall
      
      The type of the item. Always shell_call.
      - const ShellCallShellCall ShellCall = "shell_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseFunctionShellToolCallOutput struct{…}
    
    The output of a shell tool call that was emitted.
    - ID string
      
      The unique ID of the shell call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - MaxOutputLength int64
      
      The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
    - Output []ResponseFunctionShellToolCallOutputOutput
      
      An array of shell call output contents
      - Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
      - Stderr string
        
        The standard error output that was captured.
      - Stdout string
        
        The standard output that was captured.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - Status ResponseFunctionShellToolCallOutputStatus
      
      The status of the shell call output. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
      - const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
      - const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
    - Type ShellCallOutput
      
      The type of the shell call output. Always shell_call_output.
      - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseApplyPatchToolCall struct{…}
    
    A tool call that applies file diffs by creating, deleting, or updating files.
    - ID string
      
      The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Operation ResponseApplyPatchToolCallOperationUnion
      
      One of the create_file, delete_file, or update_file operations applied via apply_patch.
      - type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
      - type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
      - type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
    - Status ResponseApplyPatchToolCallStatus
      
      The status of the apply patch tool call. One of in_progress or completed.
      - const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
      - const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
    - Type ApplyPatchCall
      
      The type of the item. Always apply_patch_call.
      - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseApplyPatchToolCallOutput struct{…}
    
    The output emitted by an apply patch tool call.
    - ID string
      
      The unique ID of the apply patch tool call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Status ResponseApplyPatchToolCallOutputStatus
      
      The status of the apply patch tool call output. One of completed or failed.
      - const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
      - const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
    - Type ApplyPatchCallOutput
      
      The type of the item. Always apply_patch_call_output.
      - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
    - CreatedBy string
      
      The ID of the entity that created this tool call output.
    - Output string
      
      Optional textual output returned by the apply patch tool.
  - type ResponseOutputItemMcpCall struct{…}
    
    An invocation of a tool on an MCP server.
    - ID string
      
      The unique ID of the tool call.
    - Arguments string
      
      A JSON string of the arguments passed to the tool.
    - Name string
      
      The name of the tool that was run.
    - ServerLabel string
      
      The label of the MCP server running the tool.
    - Type McpCall
      
      The type of the item. Always mcp_call.
      - const McpCallMcpCall McpCall = "mcp_call"
    - ApprovalRequestID string
      
      Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
    - Error string
      
      The error from the tool call, if any.
    - Output string
      
      The output from the tool call.
    - Status string
      
      The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
      - const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
      - const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
      - const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
      - const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
      - const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
  - type ResponseOutputItemMcpListTools struct{…}
    
    A list of tools available on an MCP server.
    - ID string
      
      The unique ID of the list.
    - ServerLabel string
      
      The label of the MCP server.
    - Tools []ResponseOutputItemMcpListToolsTool
      
      The tools available on the server.
      - InputSchema any
        
        The JSON schema describing the tool's input.
      - Name string
        
        The name of the tool.
      - Annotations any
        
        Additional annotations about the tool.
      - Description string
        
        The description of the tool.
    - Type McpListTools
      
      The type of the item. Always mcp_list_tools.
      - const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
    - Error string
      
      Error message if the server could not list tools.
  - type ResponseOutputItemMcpApprovalRequest struct{…}
    
    A request for human approval of a tool invocation.
    - ID string
      
      The unique ID of the approval request.
    - Arguments string
      
      A JSON string of arguments for the tool.
    - Name string
      
      The name of the tool to run.
    - ServerLabel string
      
      The label of the MCP server making the request.
    - Type McpApprovalRequest
      
      The type of the item. Always mcp_approval_request.
      - const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
  - type ResponseOutputItemMcpApprovalResponse struct{…}
    
    A response to an MCP approval request.
    - ID string
      
      The unique ID of the approval response
    - ApprovalRequestID string
      
      The ID of the approval request being answered.
    - Approve bool
      
      Whether the request was approved.
    - Type McpApprovalResponse
      
      The type of the item. Always mcp_approval_response.
      - const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
    - Reason string
      
      Optional reason for the decision.
  - type ResponseCustomToolCall struct{…}
    
    A call to a custom tool created by the model.
    - CallID string
      
      An identifier used to map this custom tool call to a tool call output.
    - Input string
      
      The input for the custom tool call generated by the model.
    - Name string
      
      The name of the custom tool being called.
    - Type CustomToolCall
      
      The type of the custom tool call. Always custom_tool_call.
      - const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
    - ID string
      
      The unique ID of the custom tool call in the OpenAI platform.
    - Namespace string
      
      The namespace of the custom tool being called.
  - type ResponseCustomToolCallOutputItem struct{…}
    
    The output of a custom tool call from your code, being sent back to the model.
    - ID string
      
      The unique ID of the custom tool call output item.
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
      - const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
      - const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
    - CreatedBy string
      
      The identifier of the actor that created the item.
- Usage ResponseUsage
  
  Token accounting for the compaction pass, including cached, reasoning, and total tokens.
  - InputTokens int64
    
    The number of input tokens.
  - InputTokensDetails ResponseUsageInputTokensDetails
    
    A detailed breakdown of the input tokens.
    - CachedTokens int64
      
      The number of tokens that were retrieved from the cache. More on prompt caching.
  - OutputTokens int64
    
    The number of output tokens.
  - OutputTokensDetails ResponseUsageOutputTokensDetails
    
    A detailed breakdown of the output tokens.
    - ReasoningTokens int64
      
      The number of reasoning tokens.
  - TotalTokens int64
    
    The total number of tokens used.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
  "github.com/openai/openai-go/responses"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  compactedResponse, err := client.Responses.Compact(context.TODO(), responses.ResponseCompactParams{
    Model: responses.ResponseCompactParamsModelGPT5_4,
  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", compactedResponse.ID)
}

Response

{
  "id": "id",
  "created_at": 0,
  "object": "response.compaction",
  "output": [
    {
      "id": "id",
      "content": [
        {
          "annotations": [
            {
              "file_id": "file_id",
              "filename": "filename",
              "index": 0,
              "type": "file_citation"
            }
          ],
          "text": "text",
          "type": "output_text",
          "logprobs": [
            {
              "token": "token",
              "bytes": [
                0
              ],
              "logprob": 0,
              "top_logprobs": [
                {
                  "token": "token",
                  "bytes": [
                    0
                  ],
                  "logprob": 0
                }
              ]
            }
          ]
        }
      ],
      "role": "assistant",
      "status": "in_progress",
      "type": "message",
      "phase": "commentary"
    }
  ],
  "usage": {
    "input_tokens": 0,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 0,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 0
  }
}

Domain Types

Apply Patch Tool

type ApplyPatchTool struct{…}

Allows the assistant to create, delete, or update files using unified diffs.
- Type ApplyPatch
  
  The type of the tool. Always apply_patch.
  - const ApplyPatchApplyPatch ApplyPatch = "apply_patch"

Compacted Response

type CompactedResponse struct{…}
- ID string
  
  The unique identifier for the compacted response.
- CreatedAt int64
  
  Unix timestamp (in seconds) when the compacted conversation was created.
- Object ResponseCompaction
  
  The object type. Always response.compaction.
  - const ResponseCompactionResponseCompaction ResponseCompaction = "response.compaction"
- Output []ResponseOutputItemUnion
  
  The compacted list of output items. This is a list of all user messages, followed by a single compaction item.
  - type ResponseOutputMessage struct{…}
    
    An output message from the model.
    - ID string
      
      The unique ID of the output message.
    - Content []ResponseOutputMessageContentUnion
      
      The content of the output message.
      - type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
      - type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
    - Role Assistant
      
      The role of the output message. Always assistant.
      - const AssistantAssistant Assistant = "assistant"
    - Status ResponseOutputMessageStatus
      
      The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
      - const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
      - const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
      - const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
    - Type Message
      
      The type of the output message. Always message.
      - const MessageMessage Message = "message"
    - Phase ResponseOutputMessagePhase
      
      Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
      - const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
      - const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
  - type ResponseFileSearchToolCall struct{…}
    
    The results of a file search tool call. See the file search guide for more information.
    - ID string
      
      The unique ID of the file search tool call.
    - Queries []string
      
      The queries used to search for files.
    - Status ResponseFileSearchToolCallStatus
      
      The status of the file search tool call. One of in_progress, searching, incomplete or failed,
      - const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
      - const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
      - const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
      - const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
      - const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
    - Type FileSearchCall
      
      The type of the file search tool call. Always file_search_call.
      - const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
    - Results []ResponseFileSearchToolCallResult
      
      The results of the file search tool call.
      - Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
      - FileID string
        
        The unique ID of the file.
      - Filename string
        
        The name of the file.
      - Score float64
        
        The relevance score of the file - a value between 0 and 1.
      - Text string
        
        The text that was retrieved from the file.
  - type ResponseFunctionToolCall struct{…}
    
    A tool call to run a function. See the function calling guide for more information.
    - Arguments string
      
      A JSON string of the arguments to pass to the function.
    - CallID string
      
      The unique ID of the function tool call generated by the model.
    - Name string
      
      The name of the function to run.
    - Type FunctionCall
      
      The type of the function tool call. Always function_call.
      - const FunctionCallFunctionCall FunctionCall = "function_call"
    - ID string
      
      The unique ID of the function tool call.
    - Namespace string
      
      The namespace of the function to run.
    - Status ResponseFunctionToolCallStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
      - const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
      - const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
  - type ResponseFunctionToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the function call tool output.
    - CallID string
      
      The unique ID of the function tool call generated by the model.
    - Output ResponseFunctionToolCallOutputItemOutputUnion
      
      The output from the function call generated by your code. Can be a string or an list of output content.
      - string
      - type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
    - Status ResponseFunctionToolCallOutputItemStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
      - const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
      - const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
    - Type FunctionCallOutput
      
      The type of the function tool call output. Always function_call_output.
      - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseFunctionWebSearch struct{…}
    
    The results of a web search tool call. See the web search guide for more information.
    - ID string
      
      The unique ID of the web search tool call.
    - Action ResponseFunctionWebSearchActionUnion
      
      An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
      - type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
      - type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
      - type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
    - Status ResponseFunctionWebSearchStatus
      
      The status of the web search tool call.
      - const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
      - const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
      - const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
      - const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
    - Type WebSearchCall
      
      The type of the web search tool call. Always web_search_call.
      - const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
  - type ResponseComputerToolCall struct{…}
    
    A tool call to a computer use tool. See the computer use guide for more information.
    - ID string
      
      The unique ID of the computer call.
    - CallID string
      
      An identifier used when responding to the tool call with output.
    - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
      
      The pending safety checks for the computer call.
      - ID string
        
        The ID of the pending safety check.
      - Code string
        
        The type of the pending safety check.
      - Message string
        
        Details about the pending safety check.
    - Status ResponseComputerToolCallStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
      - const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
      - const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
    - Type ResponseComputerToolCallType
      
      The type of the computer call. Always computer_call.
      - const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
    - Action ResponseComputerToolCallActionUnion
      
      A click action.
      - type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
      - type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
      - type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
      - type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
      - type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
      - type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
      - type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
      - type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
      - type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
    - Actions ComputerActionList
      
      Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
      - type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
      - type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
      - type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
      - type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
      - type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
      - type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
      - type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
      - type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
      - type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
  - type ResponseComputerToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the computer call tool output.
    - CallID string
      
      The ID of the computer tool call that produced the output.
    - Output ResponseComputerToolCallOutputScreenshot
      
      A computer screenshot image used with the computer use tool.
      - Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
      - FileID string
        
        The identifier of an uploaded file that contains the screenshot.
      - ImageURL string
        
        The URL of the screenshot image.
    - Status ResponseComputerToolCallOutputItemStatus
      
      The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
      - const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
      - const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
      - const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
      - const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
    - Type ComputerCallOutput
      
      The type of the computer tool call output. Always computer_call_output.
      - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
    - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
      
      The safety checks reported by the API that have been acknowledged by the developer.
      - ID string
        
        The ID of the pending safety check.
      - Code string
        
        The type of the pending safety check.
      - Message string
        
        Details about the pending safety check.
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseReasoningItem struct{…}
    
    A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
    - ID string
      
      The unique identifier of the reasoning content.
    - Summary []ResponseReasoningItemSummary
      
      Reasoning summary content.
      - Text string
        
        A summary of the reasoning output from the model so far.
      - Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
    - Type Reasoning
      
      The type of the object. Always reasoning.
      - const ReasoningReasoning Reasoning = "reasoning"
    - Content []ResponseReasoningItemContent
      
      Reasoning text content.
      - Text string
        
        The reasoning text from the model.
      - Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
    - EncryptedContent string
      
      The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
    - Status ResponseReasoningItemStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
      - const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
      - const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
  - type ResponseToolSearchCall struct{…}
    - ID string
      
      The unique ID of the tool search call item.
    - Arguments any
      
      Arguments used for the tool search call.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchCallExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
      - const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
    - Status ResponseToolSearchCallStatus
      
      The status of the tool search call item that was recorded.
      - const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
      - const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
      - const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
    - Type ToolSearchCall
      
      The type of the item. Always tool_search_call.
      - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseToolSearchOutputItem struct{…}
    - ID string
      
      The unique ID of the tool search output item.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchOutputItemExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
      - const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
    - Status ResponseToolSearchOutputItemStatus
      
      The status of the tool search output item that was recorded.
      - const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
      - const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
      - const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
    - Tools []ToolUnion
      
      The loaded tool definitions returned by tool search.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
    - Type ToolSearchOutput
      
      The type of the item. Always tool_search_output.
      - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemAdditionalTools struct{…}
    - ID string
      
      The unique ID of the additional tools item.
    - Role string
      
      The role that provided the additional tools.
      - const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
      - const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
      - const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
      - const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
      - const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
      - const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
      - const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
      - const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
    - Tools []ToolUnion
      
      The additional tool definitions made available at this item.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - Type AdditionalTools
      
      The type of the item. Always additional_tools.
      - const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
  - type ResponseCompactionItem struct{…}
    
    A compaction item generated by the v1/responses/compact API.
    - ID string
      
      The unique ID of the compaction item.
    - EncryptedContent string
      
      The encrypted content that was produced by compaction.
    - Type Compaction
      
      The type of the item. Always compaction.
      - const CompactionCompaction Compaction = "compaction"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemImageGenerationCall struct{…}
    
    An image generation request made by the model.
    - ID string
      
      The unique ID of the image generation call.
    - Result string
      
      The generated image encoded in base64.
    - Status string
      
      The status of the image generation call.
      - const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
      - const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
      - const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
      - const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
    - Type ImageGenerationCall
      
      The type of the image generation call. Always image_generation_call.
      - const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
  - type ResponseCodeInterpreterToolCall struct{…}
    
    A tool call to run code.
    - ID string
      
      The unique ID of the code interpreter tool call.
    - Code string
      
      The code to run, or null if not available.
    - ContainerID string
      
      The ID of the container used to run the code.
    - Outputs []ResponseCodeInterpreterToolCallOutputUnion
      
      The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
      - type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
      - type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
    - Status ResponseCodeInterpreterToolCallStatus
      
      The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
      - const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
      - const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
      - const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
      - const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
      - const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
    - Type CodeInterpreterCall
      
      The type of the code interpreter tool call. Always code_interpreter_call.
      - const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
  - type ResponseOutputItemLocalShellCall struct{…}
    
    A tool call to run a command on the local shell.
    - ID string
      
      The unique ID of the local shell call.
    - Action ResponseOutputItemLocalShellCallAction
      
      Execute a shell command on the server.
      - Command []string
        
        The command to run.
      - Env map[string, string]
        
        Environment variables to set for the command.
      - Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
      - User string
        
        Optional user to run the command as.
      - WorkingDirectory string
        
        Optional working directory to run the command in.
    - CallID string
      
      The unique ID of the local shell tool call generated by the model.
    - Status string
      
      The status of the local shell call.
      - const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
      - const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
    - Type LocalShellCall
      
      The type of the local shell call. Always local_shell_call.
      - const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
  - type ResponseOutputItemLocalShellCallOutput struct{…}
    
    The output of a local shell tool call.
    - ID string
      
      The unique ID of the local shell tool call generated by the model.
    - Output string
      
      A JSON string of the output of the local shell tool call.
    - Type LocalShellCallOutput
      
      The type of the local shell tool call output. Always local_shell_call_output.
      - const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete.
      - const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
      - const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
  - type ResponseFunctionShellToolCall struct{…}
    
    A tool call that executes one or more shell commands in a managed environment.
    - ID string
      
      The unique ID of the shell tool call. Populated when this item is returned via API.
    - Action ResponseFunctionShellToolCallAction
      
      The shell commands and limits that describe how to run the tool call.
      - Commands []string
      - MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - Environment ResponseFunctionShellToolCallEnvironmentUnion
      
      Represents the use of a local environment to perform shell actions.
      - type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
      - type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
    - Status ResponseFunctionShellToolCallStatus
      
      The status of the shell call. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
      - const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
      - const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
    - Type ShellCall
      
      The type of the item. Always shell_call.
      - const ShellCallShellCall ShellCall = "shell_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseFunctionShellToolCallOutput struct{…}
    
    The output of a shell tool call that was emitted.
    - ID string
      
      The unique ID of the shell call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - MaxOutputLength int64
      
      The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
    - Output []ResponseFunctionShellToolCallOutputOutput
      
      An array of shell call output contents
      - Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
      - Stderr string
        
        The standard error output that was captured.
      - Stdout string
        
        The standard output that was captured.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - Status ResponseFunctionShellToolCallOutputStatus
      
      The status of the shell call output. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
      - const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
      - const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
    - Type ShellCallOutput
      
      The type of the shell call output. Always shell_call_output.
      - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseApplyPatchToolCall struct{…}
    
    A tool call that applies file diffs by creating, deleting, or updating files.
    - ID string
      
      The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Operation ResponseApplyPatchToolCallOperationUnion
      
      One of the create_file, delete_file, or update_file operations applied via apply_patch.
      - type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
      - type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
      - type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
    - Status ResponseApplyPatchToolCallStatus
      
      The status of the apply patch tool call. One of in_progress or completed.
      - const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
      - const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
    - Type ApplyPatchCall
      
      The type of the item. Always apply_patch_call.
      - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseApplyPatchToolCallOutput struct{…}
    
    The output emitted by an apply patch tool call.
    - ID string
      
      The unique ID of the apply patch tool call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Status ResponseApplyPatchToolCallOutputStatus
      
      The status of the apply patch tool call output. One of completed or failed.
      - const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
      - const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
    - Type ApplyPatchCallOutput
      
      The type of the item. Always apply_patch_call_output.
      - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
    - CreatedBy string
      
      The ID of the entity that created this tool call output.
    - Output string
      
      Optional textual output returned by the apply patch tool.
  - type ResponseOutputItemMcpCall struct{…}
    
    An invocation of a tool on an MCP server.
    - ID string
      
      The unique ID of the tool call.
    - Arguments string
      
      A JSON string of the arguments passed to the tool.
    - Name string
      
      The name of the tool that was run.
    - ServerLabel string
      
      The label of the MCP server running the tool.
    - Type McpCall
      
      The type of the item. Always mcp_call.
      - const McpCallMcpCall McpCall = "mcp_call"
    - ApprovalRequestID string
      
      Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
    - Error string
      
      The error from the tool call, if any.
    - Output string
      
      The output from the tool call.
    - Status string
      
      The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
      - const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
      - const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
      - const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
      - const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
      - const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
  - type ResponseOutputItemMcpListTools struct{…}
    
    A list of tools available on an MCP server.
    - ID string
      
      The unique ID of the list.
    - ServerLabel string
      
      The label of the MCP server.
    - Tools []ResponseOutputItemMcpListToolsTool
      
      The tools available on the server.
      - InputSchema any
        
        The JSON schema describing the tool's input.
      - Name string
        
        The name of the tool.
      - Annotations any
        
        Additional annotations about the tool.
      - Description string
        
        The description of the tool.
    - Type McpListTools
      
      The type of the item. Always mcp_list_tools.
      - const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
    - Error string
      
      Error message if the server could not list tools.
  - type ResponseOutputItemMcpApprovalRequest struct{…}
    
    A request for human approval of a tool invocation.
    - ID string
      
      The unique ID of the approval request.
    - Arguments string
      
      A JSON string of arguments for the tool.
    - Name string
      
      The name of the tool to run.
    - ServerLabel string
      
      The label of the MCP server making the request.
    - Type McpApprovalRequest
      
      The type of the item. Always mcp_approval_request.
      - const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
  - type ResponseOutputItemMcpApprovalResponse struct{…}
    
    A response to an MCP approval request.
    - ID string
      
      The unique ID of the approval response
    - ApprovalRequestID string
      
      The ID of the approval request being answered.
    - Approve bool
      
      Whether the request was approved.
    - Type McpApprovalResponse
      
      The type of the item. Always mcp_approval_response.
      - const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
    - Reason string
      
      Optional reason for the decision.
  - type ResponseCustomToolCall struct{…}
    
    A call to a custom tool created by the model.
    - CallID string
      
      An identifier used to map this custom tool call to a tool call output.
    - Input string
      
      The input for the custom tool call generated by the model.
    - Name string
      
      The name of the custom tool being called.
    - Type CustomToolCall
      
      The type of the custom tool call. Always custom_tool_call.
      - const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
    - ID string
      
      The unique ID of the custom tool call in the OpenAI platform.
    - Namespace string
      
      The namespace of the custom tool being called.
  - type ResponseCustomToolCallOutputItem struct{…}
    
    The output of a custom tool call from your code, being sent back to the model.
    - ID string
      
      The unique ID of the custom tool call output item.
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
      - const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
      - const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
    - CreatedBy string
      
      The identifier of the actor that created the item.
- Usage ResponseUsage
  
  Token accounting for the compaction pass, including cached, reasoning, and total tokens.
  - InputTokens int64
    
    The number of input tokens.
  - InputTokensDetails ResponseUsageInputTokensDetails
    
    A detailed breakdown of the input tokens.
    - CachedTokens int64
      
      The number of tokens that were retrieved from the cache. More on prompt caching.
  - OutputTokens int64
    
    The number of output tokens.
  - OutputTokensDetails ResponseUsageOutputTokensDetails
    
    A detailed breakdown of the output tokens.
    - ReasoningTokens int64
      
      The number of reasoning tokens.
  - TotalTokens int64
    
    The total number of tokens used.

Computer Action

type ComputerActionUnion interface{…}

A click action.
- type ComputerActionClick struct{…}
  
  A click action.
  - Button string
    
    Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
    - const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
    - const ComputerActionClickButtonRight ComputerActionClickButton = "right"
    - const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
    - const ComputerActionClickButtonBack ComputerActionClickButton = "back"
    - const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
  - Type Click
    
    Specifies the event type. For a click action, this property is always click.
    - const ClickClick Click = "click"
  - X int64
    
    The x-coordinate where the click occurred.
  - Y int64
    
    The y-coordinate where the click occurred.
  - Keys []string
    
    The keys being held while clicking.
- type ComputerActionDoubleClick struct{…}
  
  A double click action.
  - Keys []string
    
    The keys being held while double-clicking.
  - Type DoubleClick
    
    Specifies the event type. For a double click action, this property is always set to double_click.
    - const DoubleClickDoubleClick DoubleClick = "double_click"
  - X int64
    
    The x-coordinate where the double click occurred.
  - Y int64
    
    The y-coordinate where the double click occurred.
- type ComputerActionDrag struct{…}
  
  A drag action.
  - Path []ComputerActionDragPath
    
    An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
```
[
  { x: 100, y: 200 },
  { x: 200, y: 300 }
]
```
    - X int64
      
      The x-coordinate.
    - Y int64
      
      The y-coordinate.
  - Type Drag
    
    Specifies the event type. For a drag action, this property is always set to drag.
    - const DragDrag Drag = "drag"
  - Keys []string
    
    The keys being held while dragging the mouse.
- type ComputerActionKeypress struct{…}
  
  A collection of keypresses the model would like to perform.
  - Keys []string
    
    The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
  - Type Keypress
    
    Specifies the event type. For a keypress action, this property is always set to keypress.
    - const KeypressKeypress Keypress = "keypress"
- type ComputerActionMove struct{…}
  
  A mouse move action.
  - Type Move
    
    Specifies the event type. For a move action, this property is always set to move.
    - const MoveMove Move = "move"
  - X int64
    
    The x-coordinate to move to.
  - Y int64
    
    The y-coordinate to move to.
  - Keys []string
    
    The keys being held while moving the mouse.
- type ComputerActionScreenshot struct{…}
  
  A screenshot action.
  - Type Screenshot
    
    Specifies the event type. For a screenshot action, this property is always set to screenshot.
    - const ScreenshotScreenshot Screenshot = "screenshot"
- type ComputerActionScroll struct{…}
  
  A scroll action.
  - ScrollX int64
    
    The horizontal scroll distance.
  - ScrollY int64
    
    The vertical scroll distance.
  - Type Scroll
    
    Specifies the event type. For a scroll action, this property is always set to scroll.
    - const ScrollScroll Scroll = "scroll"
  - X int64
    
    The x-coordinate where the scroll occurred.
  - Y int64
    
    The y-coordinate where the scroll occurred.
  - Keys []string
    
    The keys being held while scrolling.
- type ComputerActionType struct{…}
  
  An action to type in text.
  - Text string
    
    The text to type.
  - Type Type
    
    Specifies the event type. For a type action, this property is always set to type.
    - const TypeType Type = "type"
- type ComputerActionWait struct{…}
  
  A wait action.
  - Type Wait
    
    Specifies the event type. For a wait action, this property is always set to wait.
    - const WaitWait Wait = "wait"

Computer Action List

type ComputerActionList []ComputerActionUnion

Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
- type ComputerActionClick struct{…}
  
  A click action.
  - Button string
    
    Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
    - const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
    - const ComputerActionClickButtonRight ComputerActionClickButton = "right"
    - const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
    - const ComputerActionClickButtonBack ComputerActionClickButton = "back"
    - const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
  - Type Click
    
    Specifies the event type. For a click action, this property is always click.
    - const ClickClick Click = "click"
  - X int64
    
    The x-coordinate where the click occurred.
  - Y int64
    
    The y-coordinate where the click occurred.
  - Keys []string
    
    The keys being held while clicking.
- type ComputerActionDoubleClick struct{…}
  
  A double click action.
  - Keys []string
    
    The keys being held while double-clicking.
  - Type DoubleClick
    
    Specifies the event type. For a double click action, this property is always set to double_click.
    - const DoubleClickDoubleClick DoubleClick = "double_click"
  - X int64
    
    The x-coordinate where the double click occurred.
  - Y int64
    
    The y-coordinate where the double click occurred.
- type ComputerActionDrag struct{…}
  
  A drag action.
  - Path []ComputerActionDragPath
    
    An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
```
[
  { x: 100, y: 200 },
  { x: 200, y: 300 }
]
```
    - X int64
      
      The x-coordinate.
    - Y int64
      
      The y-coordinate.
  - Type Drag
    
    Specifies the event type. For a drag action, this property is always set to drag.
    - const DragDrag Drag = "drag"
  - Keys []string
    
    The keys being held while dragging the mouse.
- type ComputerActionKeypress struct{…}
  
  A collection of keypresses the model would like to perform.
  - Keys []string
    
    The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
  - Type Keypress
    
    Specifies the event type. For a keypress action, this property is always set to keypress.
    - const KeypressKeypress Keypress = "keypress"
- type ComputerActionMove struct{…}
  
  A mouse move action.
  - Type Move
    
    Specifies the event type. For a move action, this property is always set to move.
    - const MoveMove Move = "move"
  - X int64
    
    The x-coordinate to move to.
  - Y int64
    
    The y-coordinate to move to.
  - Keys []string
    
    The keys being held while moving the mouse.
- type ComputerActionScreenshot struct{…}
  
  A screenshot action.
  - Type Screenshot
    
    Specifies the event type. For a screenshot action, this property is always set to screenshot.
    - const ScreenshotScreenshot Screenshot = "screenshot"
- type ComputerActionScroll struct{…}
  
  A scroll action.
  - ScrollX int64
    
    The horizontal scroll distance.
  - ScrollY int64
    
    The vertical scroll distance.
  - Type Scroll
    
    Specifies the event type. For a scroll action, this property is always set to scroll.
    - const ScrollScroll Scroll = "scroll"
  - X int64
    
    The x-coordinate where the scroll occurred.
  - Y int64
    
    The y-coordinate where the scroll occurred.
  - Keys []string
    
    The keys being held while scrolling.
- type ComputerActionType struct{…}
  
  An action to type in text.
  - Text string
    
    The text to type.
  - Type Type
    
    Specifies the event type. For a type action, this property is always set to type.
    - const TypeType Type = "type"
- type ComputerActionWait struct{…}
  
  A wait action.
  - Type Wait
    
    Specifies the event type. For a wait action, this property is always set to wait.
    - const WaitWait Wait = "wait"

Computer Tool

type ComputerTool struct{…}

A tool that controls a virtual computer. Learn more about the computer tool.
- Type Computer
  
  The type of the computer tool. Always computer.
  - const ComputerComputer Computer = "computer"

Computer Use Preview Tool

type ComputerUsePreviewTool struct{…}

A tool that controls a virtual computer. Learn more about the computer tool.
- DisplayHeight int64
  
  The height of the computer display.
- DisplayWidth int64
  
  The width of the computer display.
- Environment ComputerUsePreviewToolEnvironment
  
  The type of computer environment to control.
  - const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
  - const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
  - const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
  - const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
  - const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
- Type ComputerUsePreview
  
  The type of the computer use tool. Always computer_use_preview.
  - const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"

Container Auto

type ContainerAuto struct{…}
- Type ContainerAuto
  
  Automatically creates a container for this request
  - const ContainerAutoContainerAuto ContainerAuto = "container_auto"
- FileIDs []string
  
  An optional list of uploaded files to make available to your code.
- MemoryLimit ContainerAutoMemoryLimit
  
  The memory limit for the container.
  - const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
  - const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
  - const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
  - const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
- NetworkPolicy ContainerAutoNetworkPolicyUnion
  
  Network access policy for the container.
  - type ContainerNetworkPolicyDisabled struct{…}
    - Type Disabled
      
      Disable outbound network access. Always disabled.
      - const DisabledDisabled Disabled = "disabled"
  - type ContainerNetworkPolicyAllowlist struct{…}
    - AllowedDomains []string
      
      A list of allowed domains when type is allowlist.
    - Type Allowlist
      
      Allow outbound network access only to specified domains. Always allowlist.
      - const AllowlistAllowlist Allowlist = "allowlist"
    - DomainSecrets []ContainerNetworkPolicyDomainSecret
      
      Optional domain-scoped secrets for allowlisted domains.
      - Domain string
        
        The domain associated with the secret.
      - Name string
        
        The name of the secret to inject for the domain.
      - Value string
        
        The secret value to inject for the domain.
- Skills []ContainerAutoSkillUnion
  
  An optional list of skills referenced by id or inline data.
  - type SkillReference struct{…}
    - SkillID string
      
      The ID of the referenced skill.
    - Type SkillReference
      
      References a skill created with the /v1/skills endpoint.
      - const SkillReferenceSkillReference SkillReference = "skill_reference"
    - Version string
      
      Optional skill version. Use a positive integer or 'latest'. Omit for default.
  - type InlineSkill struct{…}
    - Description string
      
      The description of the skill.
    - Name string
      
      The name of the skill.
    - Source InlineSkillSource
      
      Inline skill payload
      - Data string
        
        Base64-encoded skill zip bundle.
      - MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
      - Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
    - Type Inline
      
      Defines an inline skill for this request.
      - const InlineInline Inline = "inline"

Container Network Policy Allowlist

type ContainerNetworkPolicyAllowlist struct{…}
- AllowedDomains []string
  
  A list of allowed domains when type is allowlist.
- Type Allowlist
  
  Allow outbound network access only to specified domains. Always allowlist.
  - const AllowlistAllowlist Allowlist = "allowlist"
- DomainSecrets []ContainerNetworkPolicyDomainSecret
  
  Optional domain-scoped secrets for allowlisted domains.
  - Domain string
    
    The domain associated with the secret.
  - Name string
    
    The name of the secret to inject for the domain.
  - Value string
    
    The secret value to inject for the domain.

Container Network Policy Disabled

type ContainerNetworkPolicyDisabled struct{…}
- Type Disabled
  
  Disable outbound network access. Always disabled.
  - const DisabledDisabled Disabled = "disabled"

Container Network Policy Domain Secret

type ContainerNetworkPolicyDomainSecret struct{…}
- Domain string
  
  The domain associated with the secret.
- Name string
  
  The name of the secret to inject for the domain.
- Value string
  
  The secret value to inject for the domain.

Container Reference

type ContainerReference struct{…}
- ContainerID string
  
  The ID of the referenced container.
- Type ContainerReference
  
  References a container created with the /v1/containers endpoint
  - const ContainerReferenceContainerReference ContainerReference = "container_reference"

Custom Tool

type CustomTool struct{…}

A custom tool that processes input using a specified format. Learn more about custom tools
- Name string
  
  The name of the custom tool, used to identify it in tool calls.
- Type Custom
  
  The type of the custom tool. Always custom.
  - const CustomCustom Custom = "custom"
- DeferLoading bool
  
  Whether this tool should be deferred and discovered via tool search.
- Description string
  
  Optional description of the custom tool, used to provide more context.
- Format CustomToolInputFormatUnion
  
  The input format for the custom tool. Default is unconstrained text.
  - type CustomToolInputFormatText struct{…}
    
    Unconstrained free-form text.
    - Type Text
      
      Unconstrained text format. Always text.
      - const TextText Text = "text"
  - type CustomToolInputFormatGrammar struct{…}
    
    A grammar defined by the user.
    - Definition string
      
      The grammar definition.
    - Syntax string
      
      The syntax of the grammar definition. One of lark or regex.
      - const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
      - const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
    - Type Grammar
      
      Grammar format. Always grammar.
      - const GrammarGrammar Grammar = "grammar"

Easy Input Message

type EasyInputMessage struct{…}

A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
- Content EasyInputMessageContentUnion
  
  Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
  - string
  - type ResponseInputMessageContentList []ResponseInputContentUnion
    
    A list of one or many input items to the model, containing different content types.
    - type ResponseInputText struct{…}
      
      A text input to the model.
      - Text string
        
        The text input to the model.
      - Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
    - type ResponseInputImage struct{…}
      
      An image input to the model. Learn about image inputs.
      - Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
      - Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
      - FileID string
        
        The ID of the file to be sent to the model.
      - ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
    - type ResponseInputFile struct{…}
      
      A file input to the model.
      - Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
      - Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
      - FileData string
        
        The content of the file to be sent to the model.
      - FileID string
        
        The ID of the file to be sent to the model.
      - FileURL string
        
        The URL of the file to be sent to the model.
      - Filename string
        
        The name of the file to be sent to the model.
- Role EasyInputMessageRole
  
  The role of the message input. One of user, assistant, system, or developer.
  - const EasyInputMessageRoleUser EasyInputMessageRole = "user"
  - const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
  - const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
  - const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
- Phase EasyInputMessagePhase
  
  Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
  - const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
  - const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
- Type EasyInputMessageType
  
  The type of the message input. Always message.
  - const EasyInputMessageTypeMessage EasyInputMessageType = "message"

File Search Tool

type FileSearchTool struct{…}

A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
- Type FileSearch
  
  The type of the file search tool. Always file_search.
  - const FileSearchFileSearch FileSearch = "file_search"
- VectorStoreIDs []string
  
  The IDs of the vector stores to search.
- Filters FileSearchToolFiltersUnion
  
  A filter to apply.
  - type ComparisonFilter struct{…}
    
    A filter used to compare a specified attribute key to a given value using a defined comparison operation.
    - Key string
      
      The key to compare against the value.
    - Type ComparisonFilterType
      
      Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
      - eq: equals
      - ne: not equal
      - gt: greater than
      - gte: greater than or equal
      - lt: less than
      - lte: less than or equal
      - in: in
      - nin: not in
      - const ComparisonFilterTypeEq ComparisonFilterType = "eq"
      - const ComparisonFilterTypeNe ComparisonFilterType = "ne"
      - const ComparisonFilterTypeGt ComparisonFilterType = "gt"
      - const ComparisonFilterTypeGte ComparisonFilterType = "gte"
      - const ComparisonFilterTypeLt ComparisonFilterType = "lt"
      - const ComparisonFilterTypeLte ComparisonFilterType = "lte"
      - const ComparisonFilterTypeIn ComparisonFilterType = "in"
      - const ComparisonFilterTypeNin ComparisonFilterType = "nin"
    - Value ComparisonFilterValueUnion
      
      The value to compare against the attribute key; supports string, number, or boolean types.
      - string
      - float64
      - bool
      - type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
  - type CompoundFilter struct{…}
    
    Combine multiple filters using and or or.
    - Filters []ComparisonFilter
      
      Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
      - type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
    - Type CompoundFilterType
      
      Type of operation: and or or.
      - const CompoundFilterTypeAnd CompoundFilterType = "and"
      - const CompoundFilterTypeOr CompoundFilterType = "or"
- MaxNumResults int64
  
  The maximum number of results to return. This number should be between 1 and 50 inclusive.
- RankingOptions FileSearchToolRankingOptions
  
  Ranking options for search.
  - HybridSearch FileSearchToolRankingOptionsHybridSearch
    
    Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
    - EmbeddingWeight float64
      
      The weight of the embedding in the reciprocal ranking fusion.
    - TextWeight float64
      
      The weight of the text in the reciprocal ranking fusion.
  - Ranker string
    
    The ranker to use for the file search.
    - const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
    - const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
  - ScoreThreshold float64
    
    The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.

Function Shell Tool

type FunctionShellTool struct{…}

A tool that allows the model to execute shell commands.
- Type Shell
  
  The type of the shell tool. Always shell.
  - const ShellShell Shell = "shell"
- Environment FunctionShellToolEnvironmentUnion
  - type ContainerAuto struct{…}
    - Type ContainerAuto
      
      Automatically creates a container for this request
      - const ContainerAutoContainerAuto ContainerAuto = "container_auto"
    - FileIDs []string
      
      An optional list of uploaded files to make available to your code.
    - MemoryLimit ContainerAutoMemoryLimit
      
      The memory limit for the container.
      - const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
      - const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
      - const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
      - const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
    - NetworkPolicy ContainerAutoNetworkPolicyUnion
      
      Network access policy for the container.
      - type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
      - type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
    - Skills []ContainerAutoSkillUnion
      
      An optional list of skills referenced by id or inline data.
      - type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
      - type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
  - type LocalEnvironment struct{…}
    - Type Local
      
      Use a local computer environment.
      - const LocalLocal Local = "local"
    - Skills []LocalSkill
      
      An optional list of skills.
      - Description string
        
        The description of the skill.
      - Name string
        
        The name of the skill.
      - Path string
        
        The path to the directory containing the skill.
  - type ContainerReference struct{…}
    - ContainerID string
      
      The ID of the referenced container.
    - Type ContainerReference
      
      References a container created with the /v1/containers endpoint
      - const ContainerReferenceContainerReference ContainerReference = "container_reference"

Function Tool

type FunctionTool struct{…}

Defines a function in your own code the model can choose to call. Learn more about function calling.
- Name string
  
  The name of the function to call.
- Parameters map[string, any]
  
  A JSON schema object describing the parameters of the function.
- Strict bool
  
  Whether to enforce strict parameter validation. Default true.
- Type Function
  
  The type of the function tool. Always function.
  - const FunctionFunction Function = "function"
- DeferLoading bool
  
  Whether this function is deferred and loaded via tool search.
- Description string
  
  A description of the function. Used by the model to determine whether or not to call the function.

Inline Skill

type InlineSkill struct{…}
- Description string
  
  The description of the skill.
- Name string
  
  The name of the skill.
- Source InlineSkillSource
  
  Inline skill payload
  - Data string
    
    Base64-encoded skill zip bundle.
  - MediaType ApplicationZip
    
    The media type of the inline skill payload. Must be application/zip.
    - const ApplicationZipApplicationZip ApplicationZip = "application/zip"
  - Type Base64
    
    The type of the inline skill source. Must be base64.
    - const Base64Base64 Base64 = "base64"
- Type Inline
  
  Defines an inline skill for this request.
  - const InlineInline Inline = "inline"

Inline Skill Source

type InlineSkillSource struct{…}

Inline skill payload
- Data string
  
  Base64-encoded skill zip bundle.
- MediaType ApplicationZip
  
  The media type of the inline skill payload. Must be application/zip.
  - const ApplicationZipApplicationZip ApplicationZip = "application/zip"
- Type Base64
  
  The type of the inline skill source. Must be base64.
  - const Base64Base64 Base64 = "base64"

Local Environment

type LocalEnvironment struct{…}
- Type Local
  
  Use a local computer environment.
  - const LocalLocal Local = "local"
- Skills []LocalSkill
  
  An optional list of skills.
  - Description string
    
    The description of the skill.
  - Name string
    
    The name of the skill.
  - Path string
    
    The path to the directory containing the skill.

Local Skill

type LocalSkill struct{…}
- Description string
  
  The description of the skill.
- Name string
  
  The name of the skill.
- Path string
  
  The path to the directory containing the skill.

Namespace Tool

type NamespaceTool struct{…}

Groups function/custom tools under a shared namespace.
- Description string
  
  A description of the namespace shown to the model.
- Name string
  
  The namespace name used in tool calls (for example, crm).
- Tools []NamespaceToolToolUnion
  
  The function/custom tools available inside this namespace.
  - type NamespaceToolToolFunction struct{…}
    - Name string
    - Type Function
      - const FunctionFunction Function = "function"
    - DeferLoading bool
      
      Whether this function should be deferred and discovered via tool search.
    - Description string
    - Parameters any
    - Strict bool
  - type CustomTool struct{…}
    
    A custom tool that processes input using a specified format. Learn more about custom tools
    - Name string
      
      The name of the custom tool, used to identify it in tool calls.
    - Type Custom
      
      The type of the custom tool. Always custom.
      - const CustomCustom Custom = "custom"
    - DeferLoading bool
      
      Whether this tool should be deferred and discovered via tool search.
    - Description string
      
      Optional description of the custom tool, used to provide more context.
    - Format CustomToolInputFormatUnion
      
      The input format for the custom tool. Default is unconstrained text.
      - type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
      - type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
- Type Namespace
  
  The type of the tool. Always namespace.
  - const NamespaceNamespace Namespace = "namespace"

Response

type Response struct{…}
- ID string
  
  Unique identifier for this Response.
- CreatedAt float64
  
  Unix timestamp (in seconds) of when this Response was created.
- Error ResponseError
  
  An error object returned when the model fails to generate a Response.
  - Code ResponseErrorCode
    
    The error code for the response.
    - const ResponseErrorCodeServerError ResponseErrorCode = "server_error"
    - const ResponseErrorCodeRateLimitExceeded ResponseErrorCode = "rate_limit_exceeded"
    - const ResponseErrorCodeInvalidPrompt ResponseErrorCode = "invalid_prompt"
    - const ResponseErrorCodeVectorStoreTimeout ResponseErrorCode = "vector_store_timeout"
    - const ResponseErrorCodeInvalidImage ResponseErrorCode = "invalid_image"
    - const ResponseErrorCodeInvalidImageFormat ResponseErrorCode = "invalid_image_format"
    - const ResponseErrorCodeInvalidBase64Image ResponseErrorCode = "invalid_base64_image"
    - const ResponseErrorCodeInvalidImageURL ResponseErrorCode = "invalid_image_url"
    - const ResponseErrorCodeImageTooLarge ResponseErrorCode = "image_too_large"
    - const ResponseErrorCodeImageTooSmall ResponseErrorCode = "image_too_small"
    - const ResponseErrorCodeImageParseError ResponseErrorCode = "image_parse_error"
    - const ResponseErrorCodeImageContentPolicyViolation ResponseErrorCode = "image_content_policy_violation"
    - const ResponseErrorCodeInvalidImageMode ResponseErrorCode = "invalid_image_mode"
    - const ResponseErrorCodeImageFileTooLarge ResponseErrorCode = "image_file_too_large"
    - const ResponseErrorCodeUnsupportedImageMediaType ResponseErrorCode = "unsupported_image_media_type"
    - const ResponseErrorCodeEmptyImageFile ResponseErrorCode = "empty_image_file"
    - const ResponseErrorCodeFailedToDownloadImage ResponseErrorCode = "failed_to_download_image"
    - const ResponseErrorCodeImageFileNotFound ResponseErrorCode = "image_file_not_found"
  - Message string
    
    A human-readable description of the error.
- IncompleteDetails ResponseIncompleteDetails
  
  Details about why the response is incomplete.
  - Reason string
    
    The reason why the response is incomplete.
    - const ResponseIncompleteDetailsReasonMaxOutputTokens ResponseIncompleteDetailsReason = "max_output_tokens"
    - const ResponseIncompleteDetailsReasonContentFilter ResponseIncompleteDetailsReason = "content_filter"
- Instructions ResponseInstructionsUnion
  
  A system (or developer) message inserted into the model's context.
  
  When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
  - string
  - type ResponseInstructionsInputItemList []ResponseInputItemUnion
    
    A list of one or many input items to the model, containing different content types.
    - type EasyInputMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
      - Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
      - Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
      - Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
    - type ResponseInputItemMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
      - Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
      - Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
      - Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
      - Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
      - ID string
        
        The unique ID of the output message.
      - Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
      - Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
      - Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
      - Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
      - Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
      - ID string
        
        The unique ID of the file search tool call.
      - Queries []string
        
        The queries used to search for files.
      - Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
      - Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
      - Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
      - ID string
        
        The unique ID of the computer call.
      - CallID string
        
        An identifier used when responding to the tool call with output.
      - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
      - Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
      - Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
      - Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
    - type ResponseInputItemComputerCallOutput struct{…}
      
      The output of a computer tool call.
      - CallID string
        
        The ID of the computer tool call that produced the output.
      - Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
      - Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
      - ID string
        
        The ID of the computer tool call output.
      - AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
      - ID string
        
        The unique ID of the web search tool call.
      - Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
      - Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
      - Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
      - Arguments string
        
        A JSON string of the arguments to pass to the function.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Name string
        
        The name of the function to run.
      - Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
      - ID string
        
        The unique ID of the function tool call.
      - Namespace string
        
        The namespace of the function to run.
      - Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
    - type ResponseInputItemFunctionCallOutput struct{…}
      
      The output of a function tool call.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
      - ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
    - type ResponseInputItemToolSearchCall struct{…}
      - Arguments any
        
        The arguments supplied to the tool search call.
      - Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
      - ID string
        
        The unique ID of this tool search call.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
      - Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
    - type ResponseToolSearchOutputItemParamResp struct{…}
      - Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
      - Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
      - ID string
        
        The unique ID of this tool search output.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
      - Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
    - type ResponseInputItemAdditionalTools struct{…}
      - Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
      - Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
      - ID string
        
        The unique ID of this additional tools item.
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
      - ID string
        
        The unique identifier of the reasoning content.
      - Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
      - Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
      - Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
      - EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
      - Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
    - type ResponseCompactionItemParamResp struct{…}
      
      A compaction item generated by the v1/responses/compact API.
      - EncryptedContent string
        
        The encrypted content of the compaction summary.
      - Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
      - ID string
        
        The ID of the compaction item.
    - type ResponseInputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
      - ID string
        
        The unique ID of the image generation call.
      - Result string
        
        The generated image encoded in base64.
      - Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
      - Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
      - ID string
        
        The unique ID of the code interpreter tool call.
      - Code string
        
        The code to run, or null if not available.
      - ContainerID string
        
        The ID of the container used to run the code.
      - Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
      - Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
      - Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
    - type ResponseInputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
      - ID string
        
        The unique ID of the local shell call.
      - Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
      - CallID string
        
        The unique ID of the local shell tool call generated by the model.
      - Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
      - Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
    - type ResponseInputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
      - ID string
        
        The unique ID of the local shell tool call generated by the model.
      - Output string
        
        A JSON string of the output of the local shell tool call.
      - Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
    - type ResponseInputItemShellCall struct{…}
      
      A tool representing a request to execute one or more shell commands.
      - Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
      - ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
      - Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
      - Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
    - type ResponseInputItemShellCallOutput struct{…}
      
      The streamed output items emitted by a shell tool call.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
      - Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
      - ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
      - MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
      - Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
    - type ResponseInputItemApplyPatchCall struct{…}
      
      A tool call representing a request to create, delete, or update files using diff patches.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
      - Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
      - Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
      - ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - type ResponseInputItemApplyPatchCallOutput struct{…}
      
      The streamed output emitted by an apply patch tool call.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
      - Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
      - ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
      - Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
    - type ResponseInputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
      - ID string
        
        The unique ID of the list.
      - ServerLabel string
        
        The label of the MCP server.
      - Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
      - Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
      - Error string
        
        Error message if the server could not list tools.
    - type ResponseInputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
      - ID string
        
        The unique ID of the approval request.
      - Arguments string
        
        A JSON string of arguments for the tool.
      - Name string
        
        The name of the tool to run.
      - ServerLabel string
        
        The label of the MCP server making the request.
      - Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
    - type ResponseInputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
      - ApprovalRequestID string
        
        The ID of the approval request being answered.
      - Approve bool
        
        Whether the request was approved.
      - Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
      - ID string
        
        The unique ID of the approval response
      - Reason string
        
        Optional reason for the decision.
    - type ResponseInputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
      - ID string
        
        The unique ID of the tool call.
      - Arguments string
        
        A JSON string of the arguments passed to the tool.
      - Name string
        
        The name of the tool that was run.
      - ServerLabel string
        
        The label of the MCP server running the tool.
      - Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
      - ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
      - Error string
        
        The error from the tool call, if any.
      - Output string
        
        The output from the tool call.
      - Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
    - type ResponseCustomToolCallOutput struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
      - CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
      - Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
      - ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
      - CallID string
        
        An identifier used to map this custom tool call to a tool call output.
      - Input string
        
        The input for the custom tool call generated by the model.
      - Name string
        
        The name of the custom tool being called.
      - Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
      - ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
      - Namespace string
        
        The namespace of the custom tool being called.
    - type ResponseInputItemCompactionTrigger struct{…}
      
      Compacts the current context. Must be the final input item.
      - Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
    - type ResponseInputItemItemReference struct{…}
      
      An internal identifier for an item to reference.
      - ID string
        
        The ID of the item to reference.
      - Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
- Metadata Metadata
  
  Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
  
  Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
- Model ResponsesModel
  
  Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
  - string
  - type ChatModel string
    - const ChatModelGPT5_4 ChatModel = "gpt-5.4"
    - const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"
    - const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"
    - const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"
    - const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"
    - const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"
    - const ChatModelGPT5_2 ChatModel = "gpt-5.2"
    - const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"
    - const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"
    - const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"
    - const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"
    - const ChatModelGPT5_1 ChatModel = "gpt-5.1"
    - const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"
    - const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"
    - const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"
    - const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"
    - const ChatModelGPT5 ChatModel = "gpt-5"
    - const ChatModelGPT5Mini ChatModel = "gpt-5-mini"
    - const ChatModelGPT5Nano ChatModel = "gpt-5-nano"
    - const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"
    - const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"
    - const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"
    - const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"
    - const ChatModelGPT4_1 ChatModel = "gpt-4.1"
    - const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"
    - const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"
    - const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"
    - const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"
    - const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"
    - const ChatModelO4Mini ChatModel = "o4-mini"
    - const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"
    - const ChatModelO3 ChatModel = "o3"
    - const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"
    - const ChatModelO3Mini ChatModel = "o3-mini"
    - const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"
    - const ChatModelO1 ChatModel = "o1"
    - const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"
    - const ChatModelO1Preview ChatModel = "o1-preview"
    - const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"
    - const ChatModelO1Mini ChatModel = "o1-mini"
    - const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"
    - const ChatModelGPT4o ChatModel = "gpt-4o"
    - const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"
    - const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"
    - const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"
    - const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"
    - const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"
    - const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"
    - const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"
    - const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"
    - const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"
    - const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"
    - const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"
    - const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"
    - const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"
    - const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"
    - const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"
    - const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"
    - const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"
    - const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"
    - const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"
    - const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"
    - const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"
    - const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"
    - const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"
    - const ChatModelGPT4 ChatModel = "gpt-4"
    - const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"
    - const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"
    - const ChatModelGPT4_32k ChatModel = "gpt-4-32k"
    - const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"
    - const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"
    - const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"
    - const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"
    - const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"
    - const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"
    - const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"
    - const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"
    - const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"
  - type ResponsesModel string
    - const ResponsesModelO1Pro ResponsesModel = "o1-pro"
    - const ResponsesModelO1Pro2025_03_19 ResponsesModel = "o1-pro-2025-03-19"
    - const ResponsesModelO3Pro ResponsesModel = "o3-pro"
    - const ResponsesModelO3Pro2025_06_10 ResponsesModel = "o3-pro-2025-06-10"
    - const ResponsesModelO3DeepResearch ResponsesModel = "o3-deep-research"
    - const ResponsesModelO3DeepResearch2025_06_26 ResponsesModel = "o3-deep-research-2025-06-26"
    - const ResponsesModelO4MiniDeepResearch ResponsesModel = "o4-mini-deep-research"
    - const ResponsesModelO4MiniDeepResearch2025_06_26 ResponsesModel = "o4-mini-deep-research-2025-06-26"
    - const ResponsesModelComputerUsePreview ResponsesModel = "computer-use-preview"
    - const ResponsesModelComputerUsePreview2025_03_11 ResponsesModel = "computer-use-preview-2025-03-11"
    - const ResponsesModelGPT5Codex ResponsesModel = "gpt-5-codex"
    - const ResponsesModelGPT5Pro ResponsesModel = "gpt-5-pro"
    - const ResponsesModelGPT5Pro2025_10_06 ResponsesModel = "gpt-5-pro-2025-10-06"
    - const ResponsesModelGPT5_1CodexMax ResponsesModel = "gpt-5.1-codex-max"
- Object Response
  
  The object type of this resource - always set to response.
  - const ResponseResponse Response = "response"
- Output []ResponseOutputItemUnion
  
  An array of content items generated by the model.
  - The length and order of items in the output array is dependent on the model's response.
  - Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.
  - type ResponseOutputMessage struct{…}
    
    An output message from the model.
  - type ResponseFileSearchToolCall struct{…}
    
    The results of a file search tool call. See the file search guide for more information.
  - type ResponseFunctionToolCall struct{…}
    
    A tool call to run a function. See the function calling guide for more information.
  - type ResponseFunctionToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the function call tool output.
    - CallID string
      
      The unique ID of the function tool call generated by the model.
    - Output ResponseFunctionToolCallOutputItemOutputUnion
      
      The output from the function call generated by your code. Can be a string or an list of output content.
      - string
      - type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
    - Status ResponseFunctionToolCallOutputItemStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
      - const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
      - const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
    - Type FunctionCallOutput
      
      The type of the function tool call output. Always function_call_output.
      - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseFunctionWebSearch struct{…}
    
    The results of a web search tool call. See the web search guide for more information.
  - type ResponseComputerToolCall struct{…}
    
    A tool call to a computer use tool. See the computer use guide for more information.
  - type ResponseComputerToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the computer call tool output.
    - CallID string
      
      The ID of the computer tool call that produced the output.
    - Output ResponseComputerToolCallOutputScreenshot
      
      A computer screenshot image used with the computer use tool.
    - Status ResponseComputerToolCallOutputItemStatus
      
      The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
      - const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
      - const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
      - const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
      - const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
    - Type ComputerCallOutput
      
      The type of the computer tool call output. Always computer_call_output.
      - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
    - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
      
      The safety checks reported by the API that have been acknowledged by the developer.
      - ID string
        
        The ID of the pending safety check.
      - Code string
        
        The type of the pending safety check.
      - Message string
        
        Details about the pending safety check.
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseReasoningItem struct{…}
    
    A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
  - type ResponseToolSearchCall struct{…}
    - ID string
      
      The unique ID of the tool search call item.
    - Arguments any
      
      Arguments used for the tool search call.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchCallExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
      - const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
    - Status ResponseToolSearchCallStatus
      
      The status of the tool search call item that was recorded.
      - const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
      - const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
      - const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
    - Type ToolSearchCall
      
      The type of the item. Always tool_search_call.
      - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseToolSearchOutputItem struct{…}
    - ID string
      
      The unique ID of the tool search output item.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchOutputItemExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
      - const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
    - Status ResponseToolSearchOutputItemStatus
      
      The status of the tool search output item that was recorded.
      - const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
      - const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
      - const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
    - Tools []ToolUnion
      
      The loaded tool definitions returned by tool search.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - Type ToolSearchOutput
      
      The type of the item. Always tool_search_output.
      - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemAdditionalTools struct{…}
    - ID string
      
      The unique ID of the additional tools item.
    - Role string
      
      The role that provided the additional tools.
      - const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
      - const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
      - const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
      - const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
      - const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
      - const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
      - const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
      - const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
    - Tools []ToolUnion
      
      The additional tool definitions made available at this item.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - Type AdditionalTools
      
      The type of the item. Always additional_tools.
      - const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
  - type ResponseCompactionItem struct{…}
    
    A compaction item generated by the v1/responses/compact API.
    - ID string
      
      The unique ID of the compaction item.
    - EncryptedContent string
      
      The encrypted content that was produced by compaction.
    - Type Compaction
      
      The type of the item. Always compaction.
      - const CompactionCompaction Compaction = "compaction"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemImageGenerationCall struct{…}
    
    An image generation request made by the model.
    - ID string
      
      The unique ID of the image generation call.
    - Result string
      
      The generated image encoded in base64.
    - Status string
      
      The status of the image generation call.
      - const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
      - const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
      - const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
      - const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
    - Type ImageGenerationCall
      
      The type of the image generation call. Always image_generation_call.
      - const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
  - type ResponseCodeInterpreterToolCall struct{…}
    
    A tool call to run code.
  - type ResponseOutputItemLocalShellCall struct{…}
    
    A tool call to run a command on the local shell.
    - ID string
      
      The unique ID of the local shell call.
    - Action ResponseOutputItemLocalShellCallAction
      
      Execute a shell command on the server.
      - Command []string
        
        The command to run.
      - Env map[string, string]
        
        Environment variables to set for the command.
      - Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
      - User string
        
        Optional user to run the command as.
      - WorkingDirectory string
        
        Optional working directory to run the command in.
    - CallID string
      
      The unique ID of the local shell tool call generated by the model.
    - Status string
      
      The status of the local shell call.
      - const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
      - const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
    - Type LocalShellCall
      
      The type of the local shell call. Always local_shell_call.
      - const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
  - type ResponseOutputItemLocalShellCallOutput struct{…}
    
    The output of a local shell tool call.
    - ID string
      
      The unique ID of the local shell tool call generated by the model.
    - Output string
      
      A JSON string of the output of the local shell tool call.
    - Type LocalShellCallOutput
      
      The type of the local shell tool call output. Always local_shell_call_output.
      - const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete.
      - const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
      - const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
  - type ResponseFunctionShellToolCall struct{…}
    
    A tool call that executes one or more shell commands in a managed environment.
    - ID string
      
      The unique ID of the shell tool call. Populated when this item is returned via API.
    - Action ResponseFunctionShellToolCallAction
      
      The shell commands and limits that describe how to run the tool call.
      - Commands []string
      - MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - Environment ResponseFunctionShellToolCallEnvironmentUnion
      
      Represents the use of a local environment to perform shell actions.
      - type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
      - type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
    - Status ResponseFunctionShellToolCallStatus
      
      The status of the shell call. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
      - const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
      - const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
    - Type ShellCall
      
      The type of the item. Always shell_call.
      - const ShellCallShellCall ShellCall = "shell_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseFunctionShellToolCallOutput struct{…}
    
    The output of a shell tool call that was emitted.
    - ID string
      
      The unique ID of the shell call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - MaxOutputLength int64
      
      The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
    - Output []ResponseFunctionShellToolCallOutputOutput
      
      An array of shell call output contents
      - Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
      - Stderr string
        
        The standard error output that was captured.
      - Stdout string
        
        The standard output that was captured.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - Status ResponseFunctionShellToolCallOutputStatus
      
      The status of the shell call output. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
      - const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
      - const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
    - Type ShellCallOutput
      
      The type of the shell call output. Always shell_call_output.
      - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseApplyPatchToolCall struct{…}
    
    A tool call that applies file diffs by creating, deleting, or updating files.
    - ID string
      
      The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Operation ResponseApplyPatchToolCallOperationUnion
      
      One of the create_file, delete_file, or update_file operations applied via apply_patch.
      - type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
      - type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
      - type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
    - Status ResponseApplyPatchToolCallStatus
      
      The status of the apply patch tool call. One of in_progress or completed.
      - const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
      - const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
    - Type ApplyPatchCall
      
      The type of the item. Always apply_patch_call.
      - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseApplyPatchToolCallOutput struct{…}
    
    The output emitted by an apply patch tool call.
    - ID string
      
      The unique ID of the apply patch tool call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Status ResponseApplyPatchToolCallOutputStatus
      
      The status of the apply patch tool call output. One of completed or failed.
      - const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
      - const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
    - Type ApplyPatchCallOutput
      
      The type of the item. Always apply_patch_call_output.
      - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
    - CreatedBy string
      
      The ID of the entity that created this tool call output.
    - Output string
      
      Optional textual output returned by the apply patch tool.
  - type ResponseOutputItemMcpCall struct{…}
    
    An invocation of a tool on an MCP server.
    - ID string
      
      The unique ID of the tool call.
    - Arguments string
      
      A JSON string of the arguments passed to the tool.
    - Name string
      
      The name of the tool that was run.
    - ServerLabel string
      
      The label of the MCP server running the tool.
    - Type McpCall
      
      The type of the item. Always mcp_call.
      - const McpCallMcpCall McpCall = "mcp_call"
    - ApprovalRequestID string
      
      Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
    - Error string
      
      The error from the tool call, if any.
    - Output string
      
      The output from the tool call.
    - Status string
      
      The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
      - const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
      - const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
      - const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
      - const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
      - const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
  - type ResponseOutputItemMcpListTools struct{…}
    
    A list of tools available on an MCP server.
    - ID string
      
      The unique ID of the list.
    - ServerLabel string
      
      The label of the MCP server.
    - Tools []ResponseOutputItemMcpListToolsTool
      
      The tools available on the server.
      - InputSchema any
        
        The JSON schema describing the tool's input.
      - Name string
        
        The name of the tool.
      - Annotations any
        
        Additional annotations about the tool.
      - Description string
        
        The description of the tool.
    - Type McpListTools
      
      The type of the item. Always mcp_list_tools.
      - const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
    - Error string
      
      Error message if the server could not list tools.
  - type ResponseOutputItemMcpApprovalRequest struct{…}
    
    A request for human approval of a tool invocation.
    - ID string
      
      The unique ID of the approval request.
    - Arguments string
      
      A JSON string of arguments for the tool.
    - Name string
      
      The name of the tool to run.
    - ServerLabel string
      
      The label of the MCP server making the request.
    - Type McpApprovalRequest
      
      The type of the item. Always mcp_approval_request.
      - const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
  - type ResponseOutputItemMcpApprovalResponse struct{…}
    
    A response to an MCP approval request.
    - ID string
      
      The unique ID of the approval response
    - ApprovalRequestID string
      
      The ID of the approval request being answered.
    - Approve bool
      
      Whether the request was approved.
    - Type McpApprovalResponse
      
      The type of the item. Always mcp_approval_response.
      - const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
    - Reason string
      
      Optional reason for the decision.
  - type ResponseCustomToolCall struct{…}
    
    A call to a custom tool created by the model.
  - type ResponseCustomToolCallOutputItem struct{…}
    
    The output of a custom tool call from your code, being sent back to the model.
    - ID string
      
      The unique ID of the custom tool call output item.
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
      - const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
      - const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
    - CreatedBy string
      
      The identifier of the actor that created the item.
- ParallelToolCalls bool
  
  Whether to allow the model to run tool calls in parallel.
- Temperature float64
  
  What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
- ToolChoice ResponseToolChoiceUnion
  
  How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.
  - type ToolChoiceOptions string
    
    Controls which (if any) tool is called by the model.
    
    none means the model will not call any tool and instead generates a message.
    
    auto means the model can pick between generating a message or calling one or more tools.
    
    required means the model must call one or more tools.
    - const ToolChoiceOptionsNone ToolChoiceOptions = "none"
    - const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
    - const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
  - type ToolChoiceAllowed struct{…}
    
    Constrains the tools available to the model to a pre-defined set.
    - Mode ToolChoiceAllowedMode
      
      Constrains the tools available to the model to a pre-defined set.
      
      auto allows the model to pick from among the allowed tools and generate a message.
      
      required requires the model to call one or more of the allowed tools.
      - const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
      - const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
    - Tools []map[string, any]
      
      A list of tool definitions that the model should be allowed to call.
      
      For the Responses API, the list of tool definitions might look like:
```
[
  { "type": "function", "name": "get_weather" },
  { "type": "mcp", "server_label": "deepwiki" },
  { "type": "image_generation" }
]
```
    - Type AllowedTools
      
      Allowed tool configuration type. Always allowed_tools.
      - const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
  - type ToolChoiceTypes struct{…}
    
    Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
    - Type ToolChoiceTypesType
      
      The type of hosted tool the model should to use. Learn more about built-in tools.
      
      Allowed values are:
      - file_search
      - web_search_preview
      - computer
      - computer_use_preview
      - computer_use
      - code_interpreter
      - image_generation
      - const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
      - const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
      - const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
      - const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
      - const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
      - const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
      - const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
      - const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
  - type ToolChoiceFunction struct{…}
    
    Use this option to force the model to call a specific function.
    - Name string
      
      The name of the function to call.
    - Type Function
      
      For function calling, the type is always function.
      - const FunctionFunction Function = "function"
  - type ToolChoiceMcp struct{…}
    
    Use this option to force the model to call a specific tool on a remote MCP server.
    - ServerLabel string
      
      The label of the MCP server to use.
    - Type Mcp
      
      For MCP tools, the type is always mcp.
      - const McpMcp Mcp = "mcp"
    - Name string
      
      The name of the tool to call on the server.
  - type ToolChoiceCustom struct{…}
    
    Use this option to force the model to call a specific custom tool.
    - Name string
      
      The name of the custom tool to call.
    - Type Custom
      
      For custom tool calling, the type is always custom.
      - const CustomCustom Custom = "custom"
  - type ToolChoiceApplyPatch struct{…}
    
    Forces the model to call the apply_patch tool when executing a tool call.
    - Type ApplyPatch
      
      The tool to call. Always apply_patch.
      - const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
  - type ToolChoiceShell struct{…}
    
    Forces the model to call the shell tool when a tool call is required.
    - Type Shell
      
      The tool to call. Always shell.
      - const ShellShell Shell = "shell"
- Tools []ToolUnion
  
  An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
  
  We support the following categories of tools:
  - Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
  - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
  - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
  - type FunctionTool struct{…}
    
    Defines a function in your own code the model can choose to call. Learn more about function calling.
  - type FileSearchTool struct{…}
    
    A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
  - type ComputerTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
  - type ComputerUsePreviewTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
  - type WebSearchTool struct{…}
    
    Search the Internet for sources related to the prompt. Learn more about the web search tool.
  - type ToolMcp struct{…}
    
    Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
  - type ToolCodeInterpreter struct{…}
    
    A tool that runs Python code to help generate a response to a prompt.
  - type ToolImageGeneration struct{…}
    
    A tool that generates images using the GPT image models.
  - type ToolLocalShell struct{…}
    
    A tool that allows the model to execute shell commands in a local environment.
  - type FunctionShellTool struct{…}
    
    A tool that allows the model to execute shell commands.
  - type CustomTool struct{…}
    
    A custom tool that processes input using a specified format. Learn more about custom tools
  - type NamespaceTool struct{…}
    
    Groups function/custom tools under a shared namespace.
  - type ToolSearchTool struct{…}
    
    Hosted or BYOT tool search configuration for deferred tools.
  - type WebSearchPreviewTool struct{…}
    
    This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
  - type ApplyPatchTool struct{…}
    
    Allows the assistant to create, delete, or update files using unified diffs.
- TopP float64
  
  An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
  
  We generally recommend altering this or temperature but not both.
- Background bool
  
  Whether to run the model response in the background. Learn more.
- CompletedAt float64
  
  Unix timestamp (in seconds) of when this Response was completed. Only present when the status is completed.
- Conversation ResponseConversation
  
  The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
  - ID string
    
    The unique ID of the conversation that this response was associated with.
- MaxOutputTokens int64
  
  An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
- MaxToolCalls int64
  
  The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
- Moderation ResponseModeration
  
  Moderation results for the response input and output, if moderated completions were requested.
  - Input ResponseModerationInputUnion
    
    Moderation for the response input.
    - type ResponseModerationInputModerationResult struct{…}
      
      A moderation result produced for the response input or output.
      - Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
      - CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeText ResponseModerationInputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeImage ResponseModerationInputModerationResultCategoryAppliedInputType = "image"
      - CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
      - Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
      - Model string
        
        The moderation model that produced this result.
      - Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
    - type ResponseModerationInputError struct{…}
      
      An error produced while attempting moderation for the response input or output.
      - Code string
        
        The error code.
      - Message string
        
        The error message.
      - Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
  - Output ResponseModerationOutputUnion
    
    Moderation for the response output.
    - type ResponseModerationOutputModerationResult struct{…}
      
      A moderation result produced for the response input or output.
      - Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
      - CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeText ResponseModerationOutputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeImage ResponseModerationOutputModerationResultCategoryAppliedInputType = "image"
      - CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
      - Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
      - Model string
        
        The moderation model that produced this result.
      - Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
    - type ResponseModerationOutputError struct{…}
      
      An error produced while attempting moderation for the response input or output.
      - Code string
        
        The error code.
      - Message string
        
        The error message.
      - Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
- PreviousResponseID string
  
  The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
- Prompt ResponsePrompt
  
  Reference to a prompt template and its variables. Learn more.
  - ID string
    
    The unique identifier of the prompt template to use.
  - Variables map[string, ResponsePromptVariableUnion]
    
    Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
    - string
    - type ResponseInputText struct{…}
      
      A text input to the model.
    - type ResponseInputImage struct{…}
      
      An image input to the model. Learn about image inputs.
    - type ResponseInputFile struct{…}
      
      A file input to the model.
  - Version string
    
    Optional version of the prompt template.
- PromptCacheKey string
  
  Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
- PromptCacheRetention ResponsePromptCacheRetention
  
  The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.
  
  For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:
  - Organizations without ZDR enabled default to 24h.
  - Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.
  - const ResponsePromptCacheRetentionInMemory ResponsePromptCacheRetention = "in_memory"
  - const ResponsePromptCacheRetention24h ResponsePromptCacheRetention = "24h"
- Reasoning Reasoning
  
  gpt-5 and o-series models only
  
  Configuration options for reasoning models.
  - Context ReasoningContext
    
    Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
    - const ReasoningContextAuto ReasoningContext = "auto"
    - const ReasoningContextCurrentTurn ReasoningContext = "current_turn"
    - const ReasoningContextAllTurns ReasoningContext = "all_turns"
  - Effort ReasoningEffort
    
    Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
    - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
    - All models before gpt-5.1 default to medium reasoning effort, and do not support none.
    - The gpt-5-pro model defaults to (and only supports) high reasoning effort.
    - xhigh is supported for all models after gpt-5.1-codex-max.
    - const ReasoningEffortNone ReasoningEffort = "none"
    - const ReasoningEffortMinimal ReasoningEffort = "minimal"
    - const ReasoningEffortLow ReasoningEffort = "low"
    - const ReasoningEffortMedium ReasoningEffort = "medium"
    - const ReasoningEffortHigh ReasoningEffort = "high"
    - const ReasoningEffortXhigh ReasoningEffort = "xhigh"
  - GenerateSummary ReasoningGenerateSummary
    
    Deprecated: use summary instead.
    
    A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
    - const ReasoningGenerateSummaryAuto ReasoningGenerateSummary = "auto"
    - const ReasoningGenerateSummaryConcise ReasoningGenerateSummary = "concise"
    - const ReasoningGenerateSummaryDetailed ReasoningGenerateSummary = "detailed"
  - Summary ReasoningSummary
    
    A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
    
    concise is supported for computer-use-preview models and all reasoning models after gpt-5.
    - const ReasoningSummaryAuto ReasoningSummary = "auto"
    - const ReasoningSummaryConcise ReasoningSummary = "concise"
    - const ReasoningSummaryDetailed ReasoningSummary = "detailed"
- SafetyIdentifier string
  
  A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
- ServiceTier ResponseServiceTier
  
  Specifies the processing type used for serving the request.
  - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
  - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
  - If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
  - When not set, the default behavior is 'auto'.
  When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
  - const ResponseServiceTierAuto ResponseServiceTier = "auto"
  - const ResponseServiceTierDefault ResponseServiceTier = "default"
  - const ResponseServiceTierFlex ResponseServiceTier = "flex"
  - const ResponseServiceTierScale ResponseServiceTier = "scale"
  - const ResponseServiceTierPriority ResponseServiceTier = "priority"
- Status ResponseStatus
  
  The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
  - const ResponseStatusCompleted ResponseStatus = "completed"
  - const ResponseStatusFailed ResponseStatus = "failed"
  - const ResponseStatusInProgress ResponseStatus = "in_progress"
  - const ResponseStatusCancelled ResponseStatus = "cancelled"
  - const ResponseStatusQueued ResponseStatus = "queued"
  - const ResponseStatusIncomplete ResponseStatus = "incomplete"
- Text ResponseTextConfig
  
  Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
  - Text inputs and outputs
  - Structured Outputs
  - Format ResponseFormatTextConfigUnion
    
    An object specifying the format that the model must output.
    
    Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
    
    The default format is { "type": "text" } with no additional options.
    
    Not recommended for gpt-4o and newer models:
    
    Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
    - type ResponseFormatText struct{…}
      
      Default response format. Used to generate text responses.
      - Type Text
        
        The type of response format being defined. Always text.
        
        const TextText Text = "text"
    - type ResponseFormatTextJSONSchemaConfig struct{…}
      
      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
      - Name string
        
        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
      - Schema map[string, any]
        
        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
      - Type JSONSchema
        
        The type of response format being defined. Always json_schema.
        
        const JSONSchemaJSONSchema JSONSchema = "json_schema"
      - Description string
        
        A description of what the response format is for, used by the model to determine how to respond in the format.
      - Strict bool
        
        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
    - type ResponseFormatJSONObject struct{…}
      
      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
      - Type JSONObject
        
        The type of response format being defined. Always json_object.
        
        const JSONObjectJSONObject JSONObject = "json_object"
  - Verbosity ResponseTextConfigVerbosity
    
    Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
    - const ResponseTextConfigVerbosityLow ResponseTextConfigVerbosity = "low"
    - const ResponseTextConfigVerbosityMedium ResponseTextConfigVerbosity = "medium"
    - const ResponseTextConfigVerbosityHigh ResponseTextConfigVerbosity = "high"
- TopLogprobs int64
  
  An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
- Truncation ResponseTruncation
  
  The truncation strategy to use for the model response.
  - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
  - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
  - const ResponseTruncationAuto ResponseTruncation = "auto"
  - const ResponseTruncationDisabled ResponseTruncation = "disabled"
- Usage ResponseUsage
  
  Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
  - InputTokens int64
    
    The number of input tokens.
  - InputTokensDetails ResponseUsageInputTokensDetails
    
    A detailed breakdown of the input tokens.
    - CachedTokens int64
      
      The number of tokens that were retrieved from the cache. More on prompt caching.
  - OutputTokens int64
    
    The number of output tokens.
  - OutputTokensDetails ResponseUsageOutputTokensDetails
    
    A detailed breakdown of the output tokens.
    - ReasoningTokens int64
      
      The number of reasoning tokens.
  - TotalTokens int64
    
    The total number of tokens used.
- User string
  
  This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.

Response Apply Patch Tool Call

type ResponseApplyPatchToolCall struct{…}

A tool call that applies file diffs by creating, deleting, or updating files.
- ID string
  
  The unique ID of the apply patch tool call. Populated when this item is returned via API.
- CallID string
  
  The unique ID of the apply patch tool call generated by the model.
- Operation ResponseApplyPatchToolCallOperationUnion
  
  One of the create_file, delete_file, or update_file operations applied via apply_patch.
  - type ResponseApplyPatchToolCallOperationCreateFile struct{…}
    
    Instruction describing how to create a file via the apply_patch tool.
    - Diff string
      
      Diff to apply.
    - Path string
      
      Path of the file to create.
    - Type CreateFile
      
      Create a new file with the provided diff.
      - const CreateFileCreateFile CreateFile = "create_file"
  - type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
    
    Instruction describing how to delete a file via the apply_patch tool.
    - Path string
      
      Path of the file to delete.
    - Type DeleteFile
      
      Delete the specified file.
      - const DeleteFileDeleteFile DeleteFile = "delete_file"
  - type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
    
    Instruction describing how to update a file via the apply_patch tool.
    - Diff string
      
      Diff to apply.
    - Path string
      
      Path of the file to update.
    - Type UpdateFile
      
      Update an existing file with the provided diff.
      - const UpdateFileUpdateFile UpdateFile = "update_file"
- Status ResponseApplyPatchToolCallStatus
  
  The status of the apply patch tool call. One of in_progress or completed.
  - const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
  - const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
- Type ApplyPatchCall
  
  The type of the item. Always apply_patch_call.
  - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
- CreatedBy string
  
  The ID of the entity that created this tool call.

Response Apply Patch Tool Call Output

type ResponseApplyPatchToolCallOutput struct{…}

The output emitted by an apply patch tool call.
- ID string
  
  The unique ID of the apply patch tool call output. Populated when this item is returned via API.
- CallID string
  
  The unique ID of the apply patch tool call generated by the model.
- Status ResponseApplyPatchToolCallOutputStatus
  
  The status of the apply patch tool call output. One of completed or failed.
  - const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
  - const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
- Type ApplyPatchCallOutput
  
  The type of the item. Always apply_patch_call_output.
  - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
- CreatedBy string
  
  The ID of the entity that created this tool call output.
- Output string
  
  Optional textual output returned by the apply patch tool.

Response Audio Delta Event

type ResponseAudioDeltaEvent struct{…}

Emitted when there is a partial audio response.
- Delta string
  
  A chunk of Base64 encoded response audio bytes.
- SequenceNumber int64
  
  A sequence number for this chunk of the stream response.
- Type ResponseAudioDelta
  
  The type of the event. Always response.audio.delta.
  - const ResponseAudioDeltaResponseAudioDelta ResponseAudioDelta = "response.audio.delta"

Response Audio Done Event

type ResponseAudioDoneEvent struct{…}

Emitted when the audio response is complete.
- SequenceNumber int64
  
  The sequence number of the delta.
- Type ResponseAudioDone
  
  The type of the event. Always response.audio.done.
  - const ResponseAudioDoneResponseAudioDone ResponseAudioDone = "response.audio.done"

Response Audio Transcript Delta Event

type ResponseAudioTranscriptDeltaEvent struct{…}

Emitted when there is a partial transcript of audio.
- Delta string
  
  The partial transcript of the audio response.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseAudioTranscriptDelta
  
  The type of the event. Always response.audio.transcript.delta.
  - const ResponseAudioTranscriptDeltaResponseAudioTranscriptDelta ResponseAudioTranscriptDelta = "response.audio.transcript.delta"

Response Audio Transcript Done Event

type ResponseAudioTranscriptDoneEvent struct{…}

Emitted when the full audio transcript is completed.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseAudioTranscriptDone
  
  The type of the event. Always response.audio.transcript.done.
  - const ResponseAudioTranscriptDoneResponseAudioTranscriptDone ResponseAudioTranscriptDone = "response.audio.transcript.done"

Response Code Interpreter Call Code Delta Event

type ResponseCodeInterpreterCallCodeDeltaEvent struct{…}

Emitted when a partial code snippet is streamed by the code interpreter.
- Delta string
  
  The partial code snippet being streamed by the code interpreter.
- ItemID string
  
  The unique identifier of the code interpreter tool call item.
- OutputIndex int64
  
  The index of the output item in the response for which the code is being streamed.
- SequenceNumber int64
  
  The sequence number of this event, used to order streaming events.
- Type ResponseCodeInterpreterCallCodeDelta
  
  The type of the event. Always response.code_interpreter_call_code.delta.
  - const ResponseCodeInterpreterCallCodeDeltaResponseCodeInterpreterCallCodeDelta ResponseCodeInterpreterCallCodeDelta = "response.code_interpreter_call_code.delta"

Response Code Interpreter Call Code Done Event

type ResponseCodeInterpreterCallCodeDoneEvent struct{…}

Emitted when the code snippet is finalized by the code interpreter.
- Code string
  
  The final code snippet output by the code interpreter.
- ItemID string
  
  The unique identifier of the code interpreter tool call item.
- OutputIndex int64
  
  The index of the output item in the response for which the code is finalized.
- SequenceNumber int64
  
  The sequence number of this event, used to order streaming events.
- Type ResponseCodeInterpreterCallCodeDone
  
  The type of the event. Always response.code_interpreter_call_code.done.
  - const ResponseCodeInterpreterCallCodeDoneResponseCodeInterpreterCallCodeDone ResponseCodeInterpreterCallCodeDone = "response.code_interpreter_call_code.done"

Response Code Interpreter Call Completed Event

type ResponseCodeInterpreterCallCompletedEvent struct{…}

Emitted when the code interpreter call is completed.
- ItemID string
  
  The unique identifier of the code interpreter tool call item.
- OutputIndex int64
  
  The index of the output item in the response for which the code interpreter call is completed.
- SequenceNumber int64
  
  The sequence number of this event, used to order streaming events.
- Type ResponseCodeInterpreterCallCompleted
  
  The type of the event. Always response.code_interpreter_call.completed.
  - const ResponseCodeInterpreterCallCompletedResponseCodeInterpreterCallCompleted ResponseCodeInterpreterCallCompleted = "response.code_interpreter_call.completed"

Response Code Interpreter Call In Progress Event

type ResponseCodeInterpreterCallInProgressEvent struct{…}

Emitted when a code interpreter call is in progress.
- ItemID string
  
  The unique identifier of the code interpreter tool call item.
- OutputIndex int64
  
  The index of the output item in the response for which the code interpreter call is in progress.
- SequenceNumber int64
  
  The sequence number of this event, used to order streaming events.
- Type ResponseCodeInterpreterCallInProgress
  
  The type of the event. Always response.code_interpreter_call.in_progress.
  - const ResponseCodeInterpreterCallInProgressResponseCodeInterpreterCallInProgress ResponseCodeInterpreterCallInProgress = "response.code_interpreter_call.in_progress"

Response Code Interpreter Call Interpreting Event

type ResponseCodeInterpreterCallInterpretingEvent struct{…}

Emitted when the code interpreter is actively interpreting the code snippet.
- ItemID string
  
  The unique identifier of the code interpreter tool call item.
- OutputIndex int64
  
  The index of the output item in the response for which the code interpreter is interpreting code.
- SequenceNumber int64
  
  The sequence number of this event, used to order streaming events.
- Type ResponseCodeInterpreterCallInterpreting
  
  The type of the event. Always response.code_interpreter_call.interpreting.
  - const ResponseCodeInterpreterCallInterpretingResponseCodeInterpreterCallInterpreting ResponseCodeInterpreterCallInterpreting = "response.code_interpreter_call.interpreting"

Response Code Interpreter Tool Call

type ResponseCodeInterpreterToolCall struct{…}

A tool call to run code.
- ID string
  
  The unique ID of the code interpreter tool call.
- Code string
  
  The code to run, or null if not available.
- ContainerID string
  
  The ID of the container used to run the code.
- Outputs []ResponseCodeInterpreterToolCallOutputUnion
  
  The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
  - type ResponseCodeInterpreterToolCallOutputLogs struct{…}
    
    The logs output from the code interpreter.
    - Logs string
      
      The logs output from the code interpreter.
    - Type Logs
      
      The type of the output. Always logs.
      - const LogsLogs Logs = "logs"
  - type ResponseCodeInterpreterToolCallOutputImage struct{…}
    
    The image output from the code interpreter.
    - Type Image
      
      The type of the output. Always image.
      - const ImageImage Image = "image"
    - URL string
      
      The URL of the image output from the code interpreter.
- Status ResponseCodeInterpreterToolCallStatus
  
  The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
  - const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
  - const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
  - const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
  - const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
  - const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
- Type CodeInterpreterCall
  
  The type of the code interpreter tool call. Always code_interpreter_call.
  - const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"

Response Compaction Item

type ResponseCompactionItem struct{…}

A compaction item generated by the v1/responses/compact API.
- ID string
  
  The unique ID of the compaction item.
- EncryptedContent string
  
  The encrypted content that was produced by compaction.
- Type Compaction
  
  The type of the item. Always compaction.
  - const CompactionCompaction Compaction = "compaction"
- CreatedBy string
  
  The identifier of the actor that created the item.

Response Compaction Item Param

type ResponseCompactionItemParamResp struct{…}

A compaction item generated by the v1/responses/compact API.
- EncryptedContent string
  
  The encrypted content of the compaction summary.
- Type Compaction
  
  The type of the item. Always compaction.
  - const CompactionCompaction Compaction = "compaction"
- ID string
  
  The ID of the compaction item.

Response Completed Event

type ResponseCompletedEvent struct{…}

Emitted when the model response is complete.
- Response Response
  
  Properties of the completed response.
  - ID string
    
    Unique identifier for this Response.
  - CreatedAt float64
    
    Unix timestamp (in seconds) of when this Response was created.
  - Error ResponseError
    
    An error object returned when the model fails to generate a Response.
    - Code ResponseErrorCode
      
      The error code for the response.
      - const ResponseErrorCodeServerError ResponseErrorCode = "server_error"
      - const ResponseErrorCodeRateLimitExceeded ResponseErrorCode = "rate_limit_exceeded"
      - const ResponseErrorCodeInvalidPrompt ResponseErrorCode = "invalid_prompt"
      - const ResponseErrorCodeVectorStoreTimeout ResponseErrorCode = "vector_store_timeout"
      - const ResponseErrorCodeInvalidImage ResponseErrorCode = "invalid_image"
      - const ResponseErrorCodeInvalidImageFormat ResponseErrorCode = "invalid_image_format"
      - const ResponseErrorCodeInvalidBase64Image ResponseErrorCode = "invalid_base64_image"
      - const ResponseErrorCodeInvalidImageURL ResponseErrorCode = "invalid_image_url"
      - const ResponseErrorCodeImageTooLarge ResponseErrorCode = "image_too_large"
      - const ResponseErrorCodeImageTooSmall ResponseErrorCode = "image_too_small"
      - const ResponseErrorCodeImageParseError ResponseErrorCode = "image_parse_error"
      - const ResponseErrorCodeImageContentPolicyViolation ResponseErrorCode = "image_content_policy_violation"
      - const ResponseErrorCodeInvalidImageMode ResponseErrorCode = "invalid_image_mode"
      - const ResponseErrorCodeImageFileTooLarge ResponseErrorCode = "image_file_too_large"
      - const ResponseErrorCodeUnsupportedImageMediaType ResponseErrorCode = "unsupported_image_media_type"
      - const ResponseErrorCodeEmptyImageFile ResponseErrorCode = "empty_image_file"
      - const ResponseErrorCodeFailedToDownloadImage ResponseErrorCode = "failed_to_download_image"
      - const ResponseErrorCodeImageFileNotFound ResponseErrorCode = "image_file_not_found"
    - Message string
      
      A human-readable description of the error.
  - IncompleteDetails ResponseIncompleteDetails
    
    Details about why the response is incomplete.
    - Reason string
      
      The reason why the response is incomplete.
      - const ResponseIncompleteDetailsReasonMaxOutputTokens ResponseIncompleteDetailsReason = "max_output_tokens"
      - const ResponseIncompleteDetailsReasonContentFilter ResponseIncompleteDetailsReason = "content_filter"
  - Instructions ResponseInstructionsUnion
    
    A system (or developer) message inserted into the model's context.
    
    When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
    - string
    - type ResponseInstructionsInputItemList []ResponseInputItemUnion
      
      A list of one or many input items to the model, containing different content types.
      - type EasyInputMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
        
        Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
        
        Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
        
        Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
      - type ResponseInputItemMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
        
        Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
        
        Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
        
        Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
        
        Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
      - type ResponseOutputMessage struct{…}
        
        An output message from the model.
        
        ID string
        
        The unique ID of the output message.
        
        Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
        
        Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
        
        Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
        
        Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
        
        Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
      - type ResponseFileSearchToolCall struct{…}
        
        The results of a file search tool call. See the file search guide for more information.
        
        ID string
        
        The unique ID of the file search tool call.
        
        Queries []string
        
        The queries used to search for files.
        
        Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
        
        Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
        
        Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
      - type ResponseComputerToolCall struct{…}
        
        A tool call to a computer use tool. See the computer use guide for more information.
        
        ID string
        
        The unique ID of the computer call.
        
        CallID string
        
        An identifier used when responding to the tool call with output.
        
        PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
        
        Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
        
        Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
        
        Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
      - type ResponseInputItemComputerCallOutput struct{…}
        
        The output of a computer tool call.
        
        CallID string
        
        The ID of the computer tool call that produced the output.
        
        Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
        
        Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
        
        ID string
        
        The ID of the computer tool call output.
        
        AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
      - type ResponseFunctionWebSearch struct{…}
        
        The results of a web search tool call. See the web search guide for more information.
        
        ID string
        
        The unique ID of the web search tool call.
        
        Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
        
        Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
        
        Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
      - type ResponseFunctionToolCall struct{…}
        
        A tool call to run a function. See the function calling guide for more information.
        
        Arguments string
        
        A JSON string of the arguments to pass to the function.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Name string
        
        The name of the function to run.
        
        Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
        
        ID string
        
        The unique ID of the function tool call.
        
        Namespace string
        
        The namespace of the function to run.
        
        Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
      - type ResponseInputItemFunctionCallOutput struct{…}
        
        The output of a function tool call.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
        
        ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
      - type ResponseInputItemToolSearchCall struct{…}
        
        Arguments any
        
        The arguments supplied to the tool search call.
        
        Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
        
        ID string
        
        The unique ID of this tool search call.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
        
        Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
      - type ResponseToolSearchOutputItemParamResp struct{…}
        
        Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
        
        Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
        
        ID string
        
        The unique ID of this tool search output.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
        
        Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
      - type ResponseInputItemAdditionalTools struct{…}
        
        Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
        
        Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
        
        ID string
        
        The unique ID of this additional tools item.
      - type ResponseReasoningItem struct{…}
        
        A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
        
        ID string
        
        The unique identifier of the reasoning content.
        
        Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
        
        Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
        
        Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
        
        EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
        
        Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
      - type ResponseCompactionItemParamResp struct{…}
        
        A compaction item generated by the v1/responses/compact API.
        
        EncryptedContent string
        
        The encrypted content of the compaction summary.
        
        Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
        
        ID string
        
        The ID of the compaction item.
      - type ResponseInputItemImageGenerationCall struct{…}
        
        An image generation request made by the model.
        
        ID string
        
        The unique ID of the image generation call.
        
        Result string
        
        The generated image encoded in base64.
        
        Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
        
        Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
      - type ResponseCodeInterpreterToolCall struct{…}
        
        A tool call to run code.
        
        ID string
        
        The unique ID of the code interpreter tool call.
        
        Code string
        
        The code to run, or null if not available.
        
        ContainerID string
        
        The ID of the container used to run the code.
        
        Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
        
        Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
        
        Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
      - type ResponseInputItemLocalShellCall struct{…}
        
        A tool call to run a command on the local shell.
        
        ID string
        
        The unique ID of the local shell call.
        
        Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
        
        CallID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
        
        Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
      - type ResponseInputItemLocalShellCallOutput struct{…}
        
        The output of a local shell tool call.
        
        ID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Output string
        
        A JSON string of the output of the local shell tool call.
        
        Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
      - type ResponseInputItemShellCall struct{…}
        
        A tool representing a request to execute one or more shell commands.
        
        Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
        
        ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
        
        Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
        
        Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
      - type ResponseInputItemShellCallOutput struct{…}
        
        The streamed output items emitted by a shell tool call.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
        
        Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
        
        ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
        
        MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
        
        Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
      - type ResponseInputItemApplyPatchCall struct{…}
        
        A tool call representing a request to create, delete, or update files using diff patches.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
        
        Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
        
        Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
        
        ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
      - type ResponseInputItemApplyPatchCallOutput struct{…}
        
        The streamed output emitted by an apply patch tool call.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
        
        Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
        
        ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
        
        Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
      - type ResponseInputItemMcpListTools struct{…}
        
        A list of tools available on an MCP server.
        
        ID string
        
        The unique ID of the list.
        
        ServerLabel string
        
        The label of the MCP server.
        
        Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
        
        Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
        
        Error string
        
        Error message if the server could not list tools.
      - type ResponseInputItemMcpApprovalRequest struct{…}
        
        A request for human approval of a tool invocation.
        
        ID string
        
        The unique ID of the approval request.
        
        Arguments string
        
        A JSON string of arguments for the tool.
        
        Name string
        
        The name of the tool to run.
        
        ServerLabel string
        
        The label of the MCP server making the request.
        
        Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
      - type ResponseInputItemMcpApprovalResponse struct{…}
        
        A response to an MCP approval request.
        
        ApprovalRequestID string
        
        The ID of the approval request being answered.
        
        Approve bool
        
        Whether the request was approved.
        
        Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
        
        ID string
        
        The unique ID of the approval response
        
        Reason string
        
        Optional reason for the decision.
      - type ResponseInputItemMcpCall struct{…}
        
        An invocation of a tool on an MCP server.
        
        ID string
        
        The unique ID of the tool call.
        
        Arguments string
        
        A JSON string of the arguments passed to the tool.
        
        Name string
        
        The name of the tool that was run.
        
        ServerLabel string
        
        The label of the MCP server running the tool.
        
        Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
        
        ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
        
        Error string
        
        The error from the tool call, if any.
        
        Output string
        
        The output from the tool call.
        
        Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
      - type ResponseCustomToolCallOutput struct{…}
        
        The output of a custom tool call from your code, being sent back to the model.
        
        CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
        
        Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
        
        ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
      - type ResponseCustomToolCall struct{…}
        
        A call to a custom tool created by the model.
        
        CallID string
        
        An identifier used to map this custom tool call to a tool call output.
        
        Input string
        
        The input for the custom tool call generated by the model.
        
        Name string
        
        The name of the custom tool being called.
        
        Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
        
        ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
        
        Namespace string
        
        The namespace of the custom tool being called.
      - type ResponseInputItemCompactionTrigger struct{…}
        
        Compacts the current context. Must be the final input item.
        
        Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
      - type ResponseInputItemItemReference struct{…}
        
        An internal identifier for an item to reference.
        
        ID string
        
        The ID of the item to reference.
        
        Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
  - Metadata Metadata
    
    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
    
    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
  - Model ResponsesModel
    
    Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
    - string
    - type ChatModel string
      - const ChatModelGPT5_4 ChatModel = "gpt-5.4"
      - const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"
      - const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"
      - const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"
      - const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"
      - const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"
      - const ChatModelGPT5_2 ChatModel = "gpt-5.2"
      - const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"
      - const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"
      - const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"
      - const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"
      - const ChatModelGPT5_1 ChatModel = "gpt-5.1"
      - const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"
      - const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"
      - const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"
      - const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"
      - const ChatModelGPT5 ChatModel = "gpt-5"
      - const ChatModelGPT5Mini ChatModel = "gpt-5-mini"
      - const ChatModelGPT5Nano ChatModel = "gpt-5-nano"
      - const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"
      - const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"
      - const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"
      - const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"
      - const ChatModelGPT4_1 ChatModel = "gpt-4.1"
      - const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"
      - const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"
      - const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"
      - const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"
      - const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"
      - const ChatModelO4Mini ChatModel = "o4-mini"
      - const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"
      - const ChatModelO3 ChatModel = "o3"
      - const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"
      - const ChatModelO3Mini ChatModel = "o3-mini"
      - const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"
      - const ChatModelO1 ChatModel = "o1"
      - const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"
      - const ChatModelO1Preview ChatModel = "o1-preview"
      - const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"
      - const ChatModelO1Mini ChatModel = "o1-mini"
      - const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"
      - const ChatModelGPT4o ChatModel = "gpt-4o"
      - const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"
      - const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"
      - const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"
      - const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"
      - const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"
      - const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"
      - const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"
      - const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"
      - const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"
      - const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"
      - const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"
      - const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"
      - const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"
      - const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"
      - const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"
      - const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"
      - const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"
      - const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"
      - const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"
      - const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"
      - const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"
      - const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"
      - const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"
      - const ChatModelGPT4 ChatModel = "gpt-4"
      - const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"
      - const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"
      - const ChatModelGPT4_32k ChatModel = "gpt-4-32k"
      - const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"
      - const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"
      - const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"
      - const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"
      - const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"
      - const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"
      - const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"
      - const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"
      - const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"
    - type ResponsesModel string
      - const ResponsesModelO1Pro ResponsesModel = "o1-pro"
      - const ResponsesModelO1Pro2025_03_19 ResponsesModel = "o1-pro-2025-03-19"
      - const ResponsesModelO3Pro ResponsesModel = "o3-pro"
      - const ResponsesModelO3Pro2025_06_10 ResponsesModel = "o3-pro-2025-06-10"
      - const ResponsesModelO3DeepResearch ResponsesModel = "o3-deep-research"
      - const ResponsesModelO3DeepResearch2025_06_26 ResponsesModel = "o3-deep-research-2025-06-26"
      - const ResponsesModelO4MiniDeepResearch ResponsesModel = "o4-mini-deep-research"
      - const ResponsesModelO4MiniDeepResearch2025_06_26 ResponsesModel = "o4-mini-deep-research-2025-06-26"
      - const ResponsesModelComputerUsePreview ResponsesModel = "computer-use-preview"
      - const ResponsesModelComputerUsePreview2025_03_11 ResponsesModel = "computer-use-preview-2025-03-11"
      - const ResponsesModelGPT5Codex ResponsesModel = "gpt-5-codex"
      - const ResponsesModelGPT5Pro ResponsesModel = "gpt-5-pro"
      - const ResponsesModelGPT5Pro2025_10_06 ResponsesModel = "gpt-5-pro-2025-10-06"
      - const ResponsesModelGPT5_1CodexMax ResponsesModel = "gpt-5.1-codex-max"
  - Object Response
    
    The object type of this resource - always set to response.
    - const ResponseResponse Response = "response"
  - Output []ResponseOutputItemUnion
    
    An array of content items generated by the model.
    - The length and order of items in the output array is dependent on the model's response.
    - Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
    - type ResponseFunctionToolCallOutputItem struct{…}
      - ID string
        
        The unique ID of the function call tool output.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Output ResponseFunctionToolCallOutputItemOutputUnion
        
        The output from the function call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Status ResponseFunctionToolCallOutputItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
        
        const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
        
        const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
      - Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
    - type ResponseComputerToolCallOutputItem struct{…}
      - ID string
        
        The unique ID of the computer call tool output.
      - CallID string
        
        The ID of the computer tool call that produced the output.
      - Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
      - Status ResponseComputerToolCallOutputItemStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
        
        const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
        
        const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
        
        const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
      - Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
      - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
    - type ResponseToolSearchCall struct{…}
      - ID string
        
        The unique ID of the tool search call item.
      - Arguments any
        
        Arguments used for the tool search call.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchCallExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
        
        const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
      - Status ResponseToolSearchCallStatus
        
        The status of the tool search call item that was recorded.
        
        const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
        
        const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
        
        const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
      - Type ToolSearchCall
        
        The type of the item. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseToolSearchOutputItem struct{…}
      - ID string
        
        The unique ID of the tool search output item.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchOutputItemExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
        
        const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
      - Status ResponseToolSearchOutputItemStatus
        
        The status of the tool search output item that was recorded.
        
        const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
        
        const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
        
        const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
      - Tools []ToolUnion
        
        The loaded tool definitions returned by tool search.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type ToolSearchOutput
        
        The type of the item. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseOutputItemAdditionalTools struct{…}
      - ID string
        
        The unique ID of the additional tools item.
      - Role string
        
        The role that provided the additional tools.
        
        const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
        
        const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
        
        const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
        
        const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
        
        const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
        
        const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
        
        const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
        
        const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
      - Tools []ToolUnion
        
        The additional tool definitions made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type AdditionalTools
        
        The type of the item. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
    - type ResponseCompactionItem struct{…}
      
      A compaction item generated by the v1/responses/compact API.
      - ID string
        
        The unique ID of the compaction item.
      - EncryptedContent string
        
        The encrypted content that was produced by compaction.
      - Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseOutputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
      - ID string
        
        The unique ID of the image generation call.
      - Result string
        
        The generated image encoded in base64.
      - Status string
        
        The status of the image generation call.
        
        const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
        
        const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
        
        const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
      - Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
    - type ResponseOutputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
      - ID string
        
        The unique ID of the local shell call.
      - Action ResponseOutputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
      - CallID string
        
        The unique ID of the local shell tool call generated by the model.
      - Status string
        
        The status of the local shell call.
        
        const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
        
        const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
      - Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
    - type ResponseOutputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
      - ID string
        
        The unique ID of the local shell tool call generated by the model.
      - Output string
        
        A JSON string of the output of the local shell tool call.
      - Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
    - type ResponseFunctionShellToolCall struct{…}
      
      A tool call that executes one or more shell commands in a managed environment.
      - ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
      - Action ResponseFunctionShellToolCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Environment ResponseFunctionShellToolCallEnvironmentUnion
        
        Represents the use of a local environment to perform shell actions.
        
        type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
        
        type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
      - Status ResponseFunctionShellToolCallStatus
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
        
        const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
        
        const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
      - Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
      - CreatedBy string
        
        The ID of the entity that created this tool call.
    - type ResponseFunctionShellToolCallOutput struct{…}
      
      The output of a shell tool call that was emitted.
      - ID string
        
        The unique ID of the shell call output. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - MaxOutputLength int64
        
        The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
      - Output []ResponseFunctionShellToolCallOutputOutput
        
        An array of shell call output contents
        
        Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        The standard error output that was captured.
        
        Stdout string
        
        The standard output that was captured.
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - Status ResponseFunctionShellToolCallOutputStatus
        
        The status of the shell call output. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
        
        const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
        
        const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
      - Type ShellCallOutput
        
        The type of the shell call output. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseApplyPatchToolCall struct{…}
      
      A tool call that applies file diffs by creating, deleting, or updating files.
      - ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Operation ResponseApplyPatchToolCallOperationUnion
        
        One of the create_file, delete_file, or update_file operations applied via apply_patch.
        
        type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
      - Status ResponseApplyPatchToolCallStatus
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
        
        const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
      - Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
      - CreatedBy string
        
        The ID of the entity that created this tool call.
    - type ResponseApplyPatchToolCallOutput struct{…}
      
      The output emitted by an apply patch tool call.
      - ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Status ResponseApplyPatchToolCallOutputStatus
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
        
        const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
      - Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
      - CreatedBy string
        
        The ID of the entity that created this tool call output.
      - Output string
        
        Optional textual output returned by the apply patch tool.
    - type ResponseOutputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
      - ID string
        
        The unique ID of the tool call.
      - Arguments string
        
        A JSON string of the arguments passed to the tool.
      - Name string
        
        The name of the tool that was run.
      - ServerLabel string
        
        The label of the MCP server running the tool.
      - Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
      - ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
      - Error string
        
        The error from the tool call, if any.
      - Output string
        
        The output from the tool call.
      - Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
        
        const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
        
        const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
        
        const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
        
        const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
    - type ResponseOutputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
      - ID string
        
        The unique ID of the list.
      - ServerLabel string
        
        The label of the MCP server.
      - Tools []ResponseOutputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
      - Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
      - Error string
        
        Error message if the server could not list tools.
    - type ResponseOutputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
      - ID string
        
        The unique ID of the approval request.
      - Arguments string
        
        A JSON string of arguments for the tool.
      - Name string
        
        The name of the tool to run.
      - ServerLabel string
        
        The label of the MCP server making the request.
      - Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
    - type ResponseOutputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
      - ID string
        
        The unique ID of the approval response
      - ApprovalRequestID string
        
        The ID of the approval request being answered.
      - Approve bool
        
        Whether the request was approved.
      - Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
      - Reason string
        
        Optional reason for the decision.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
    - type ResponseCustomToolCallOutputItem struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
      - ID string
        
        The unique ID of the custom tool call output item.
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
        
        const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
        
        const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
      - CreatedBy string
        
        The identifier of the actor that created the item.
  - ParallelToolCalls bool
    
    Whether to allow the model to run tool calls in parallel.
  - Temperature float64
    
    What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
  - ToolChoice ResponseToolChoiceUnion
    
    How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.
    - type ToolChoiceOptions string
      
      Controls which (if any) tool is called by the model.
      
      none means the model will not call any tool and instead generates a message.
      
      auto means the model can pick between generating a message or calling one or more tools.
      
      required means the model must call one or more tools.
      - const ToolChoiceOptionsNone ToolChoiceOptions = "none"
      - const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
      - const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
    - type ToolChoiceAllowed struct{…}
      
      Constrains the tools available to the model to a pre-defined set.
      - Mode ToolChoiceAllowedMode
        
        Constrains the tools available to the model to a pre-defined set.
        
        auto allows the model to pick from among the allowed tools and generate a message.
        
        required requires the model to call one or more of the allowed tools.
        
        const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
        
        const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
      - Tools []map[string, any]
        
        A list of tool definitions that the model should be allowed to call.
        
        For the Responses API, the list of tool definitions might look like:
        
        [ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ]
      - Type AllowedTools
        
        Allowed tool configuration type. Always allowed_tools.
        
        const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
    - type ToolChoiceTypes struct{…}
      
      Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
      - Type ToolChoiceTypesType
        
        The type of hosted tool the model should to use. Learn more about built-in tools.
        
        Allowed values are:
        
        file_search
        
        web_search_preview
        
        computer
        
        computer_use_preview
        
        computer_use
        
        code_interpreter
        
        image_generation
        
        const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
        
        const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
        
        const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
        
        const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
        
        const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
        
        const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
        
        const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
        
        const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
    - type ToolChoiceFunction struct{…}
      
      Use this option to force the model to call a specific function.
      - Name string
        
        The name of the function to call.
      - Type Function
        
        For function calling, the type is always function.
        
        const FunctionFunction Function = "function"
    - type ToolChoiceMcp struct{…}
      
      Use this option to force the model to call a specific tool on a remote MCP server.
      - ServerLabel string
        
        The label of the MCP server to use.
      - Type Mcp
        
        For MCP tools, the type is always mcp.
        
        const McpMcp Mcp = "mcp"
      - Name string
        
        The name of the tool to call on the server.
    - type ToolChoiceCustom struct{…}
      
      Use this option to force the model to call a specific custom tool.
      - Name string
        
        The name of the custom tool to call.
      - Type Custom
        
        For custom tool calling, the type is always custom.
        
        const CustomCustom Custom = "custom"
    - type ToolChoiceApplyPatch struct{…}
      
      Forces the model to call the apply_patch tool when executing a tool call.
      - Type ApplyPatch
        
        The tool to call. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
    - type ToolChoiceShell struct{…}
      
      Forces the model to call the shell tool when a tool call is required.
      - Type Shell
        
        The tool to call. Always shell.
        
        const ShellShell Shell = "shell"
  - Tools []ToolUnion
    
    An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
    
    We support the following categories of tools:
    - Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
    - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
    - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
  - TopP float64
    
    An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
    
    We generally recommend altering this or temperature but not both.
  - Background bool
    
    Whether to run the model response in the background. Learn more.
  - CompletedAt float64
    
    Unix timestamp (in seconds) of when this Response was completed. Only present when the status is completed.
  - Conversation ResponseConversation
    
    The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
    - ID string
      
      The unique ID of the conversation that this response was associated with.
  - MaxOutputTokens int64
    
    An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
  - MaxToolCalls int64
    
    The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
  - Moderation ResponseModeration
    
    Moderation results for the response input and output, if moderated completions were requested.
    - Input ResponseModerationInputUnion
      
      Moderation for the response input.
      - type ResponseModerationInputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeText ResponseModerationInputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeImage ResponseModerationInputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
      - type ResponseModerationInputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
    - Output ResponseModerationOutputUnion
      
      Moderation for the response output.
      - type ResponseModerationOutputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeText ResponseModerationOutputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeImage ResponseModerationOutputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
      - type ResponseModerationOutputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
  - PreviousResponseID string
    
    The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
  - Prompt ResponsePrompt
    
    Reference to a prompt template and its variables. Learn more.
    - ID string
      
      The unique identifier of the prompt template to use.
    - Variables map[string, ResponsePromptVariableUnion]
      
      Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
      - string
      - type ResponseInputText struct{…}
        
        A text input to the model.
      - type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
      - type ResponseInputFile struct{…}
        
        A file input to the model.
    - Version string
      
      Optional version of the prompt template.
  - PromptCacheKey string
    
    Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
  - PromptCacheRetention ResponsePromptCacheRetention
    
    The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.
    
    For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:
    - Organizations without ZDR enabled default to 24h.
    - Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.
    - const ResponsePromptCacheRetentionInMemory ResponsePromptCacheRetention = "in_memory"
    - const ResponsePromptCacheRetention24h ResponsePromptCacheRetention = "24h"
  - Reasoning Reasoning
    
    gpt-5 and o-series models only
    
    Configuration options for reasoning models.
    - Context ReasoningContext
      
      Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
      - const ReasoningContextAuto ReasoningContext = "auto"
      - const ReasoningContextCurrentTurn ReasoningContext = "current_turn"
      - const ReasoningContextAllTurns ReasoningContext = "all_turns"
    - Effort ReasoningEffort
      
      Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
      - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
      - All models before gpt-5.1 default to medium reasoning effort, and do not support none.
      - The gpt-5-pro model defaults to (and only supports) high reasoning effort.
      - xhigh is supported for all models after gpt-5.1-codex-max.
      - const ReasoningEffortNone ReasoningEffort = "none"
      - const ReasoningEffortMinimal ReasoningEffort = "minimal"
      - const ReasoningEffortLow ReasoningEffort = "low"
      - const ReasoningEffortMedium ReasoningEffort = "medium"
      - const ReasoningEffortHigh ReasoningEffort = "high"
      - const ReasoningEffortXhigh ReasoningEffort = "xhigh"
    - GenerateSummary ReasoningGenerateSummary
      
      Deprecated: use summary instead.
      
      A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
      - const ReasoningGenerateSummaryAuto ReasoningGenerateSummary = "auto"
      - const ReasoningGenerateSummaryConcise ReasoningGenerateSummary = "concise"
      - const ReasoningGenerateSummaryDetailed ReasoningGenerateSummary = "detailed"
    - Summary ReasoningSummary
      
      A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
      
      concise is supported for computer-use-preview models and all reasoning models after gpt-5.
      - const ReasoningSummaryAuto ReasoningSummary = "auto"
      - const ReasoningSummaryConcise ReasoningSummary = "concise"
      - const ReasoningSummaryDetailed ReasoningSummary = "detailed"
  - SafetyIdentifier string
    
    A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
  - ServiceTier ResponseServiceTier
    
    Specifies the processing type used for serving the request.
    - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
    - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
    - If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
    - When not set, the default behavior is 'auto'.
    When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
    - const ResponseServiceTierAuto ResponseServiceTier = "auto"
    - const ResponseServiceTierDefault ResponseServiceTier = "default"
    - const ResponseServiceTierFlex ResponseServiceTier = "flex"
    - const ResponseServiceTierScale ResponseServiceTier = "scale"
    - const ResponseServiceTierPriority ResponseServiceTier = "priority"
  - Status ResponseStatus
    
    The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
    - const ResponseStatusCompleted ResponseStatus = "completed"
    - const ResponseStatusFailed ResponseStatus = "failed"
    - const ResponseStatusInProgress ResponseStatus = "in_progress"
    - const ResponseStatusCancelled ResponseStatus = "cancelled"
    - const ResponseStatusQueued ResponseStatus = "queued"
    - const ResponseStatusIncomplete ResponseStatus = "incomplete"
  - Text ResponseTextConfig
    
    Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
    - Text inputs and outputs
    - Structured Outputs
    - Format ResponseFormatTextConfigUnion
      
      An object specifying the format that the model must output.
      
      Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
      
      The default format is { "type": "text" } with no additional options.
      
      Not recommended for gpt-4o and newer models:
      
      Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
      - type ResponseFormatText struct{…}
        
        Default response format. Used to generate text responses.
        
        Type Text
        
        The type of response format being defined. Always text.
        
        const TextText Text = "text"
      - type ResponseFormatTextJSONSchemaConfig struct{…}
        
        JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
        
        Name string
        
        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
        
        Schema map[string, any]
        
        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
        
        Type JSONSchema
        
        The type of response format being defined. Always json_schema.
        
        const JSONSchemaJSONSchema JSONSchema = "json_schema"
        
        Description string
        
        A description of what the response format is for, used by the model to determine how to respond in the format.
        
        Strict bool
        
        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
      - type ResponseFormatJSONObject struct{…}
        
        JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
        
        Type JSONObject
        
        The type of response format being defined. Always json_object.
        
        const JSONObjectJSONObject JSONObject = "json_object"
    - Verbosity ResponseTextConfigVerbosity
      
      Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
      - const ResponseTextConfigVerbosityLow ResponseTextConfigVerbosity = "low"
      - const ResponseTextConfigVerbosityMedium ResponseTextConfigVerbosity = "medium"
      - const ResponseTextConfigVerbosityHigh ResponseTextConfigVerbosity = "high"
  - TopLogprobs int64
    
    An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
  - Truncation ResponseTruncation
    
    The truncation strategy to use for the model response.
    - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
    - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
    - const ResponseTruncationAuto ResponseTruncation = "auto"
    - const ResponseTruncationDisabled ResponseTruncation = "disabled"
  - Usage ResponseUsage
    
    Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
    - InputTokens int64
      
      The number of input tokens.
    - InputTokensDetails ResponseUsageInputTokensDetails
      
      A detailed breakdown of the input tokens.
      - CachedTokens int64
        
        The number of tokens that were retrieved from the cache. More on prompt caching.
    - OutputTokens int64
      
      The number of output tokens.
    - OutputTokensDetails ResponseUsageOutputTokensDetails
      
      A detailed breakdown of the output tokens.
      - ReasoningTokens int64
        
        The number of reasoning tokens.
    - TotalTokens int64
      
      The total number of tokens used.
  - User string
    
    This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
- SequenceNumber int64
  
  The sequence number for this event.
- Type ResponseCompleted
  
  The type of the event. Always response.completed.
  - const ResponseCompletedResponseCompleted ResponseCompleted = "response.completed"

Response Computer Tool Call

type ResponseComputerToolCall struct{…}

A tool call to a computer use tool. See the computer use guide for more information.
- ID string
  
  The unique ID of the computer call.
- CallID string
  
  An identifier used when responding to the tool call with output.
- PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
  
  The pending safety checks for the computer call.
  - ID string
    
    The ID of the pending safety check.
  - Code string
    
    The type of the pending safety check.
  - Message string
    
    Details about the pending safety check.
- Status ResponseComputerToolCallStatus
  
  The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
  - const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
  - const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
  - const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
- Type ResponseComputerToolCallType
  
  The type of the computer call. Always computer_call.
  - const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
- Action ResponseComputerToolCallActionUnion
  
  A click action.
  - type ResponseComputerToolCallActionClick struct{…}
    
    A click action.
    - Button string
      
      Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
      - const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
      - const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
      - const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
      - const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
      - const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
    - Type Click
      
      Specifies the event type. For a click action, this property is always click.
      - const ClickClick Click = "click"
    - X int64
      
      The x-coordinate where the click occurred.
    - Y int64
      
      The y-coordinate where the click occurred.
    - Keys []string
      
      The keys being held while clicking.
  - type ResponseComputerToolCallActionDoubleClick struct{…}
    
    A double click action.
    - Keys []string
      
      The keys being held while double-clicking.
    - Type DoubleClick
      
      Specifies the event type. For a double click action, this property is always set to double_click.
      - const DoubleClickDoubleClick DoubleClick = "double_click"
    - X int64
      
      The x-coordinate where the double click occurred.
    - Y int64
      
      The y-coordinate where the double click occurred.
  - type ResponseComputerToolCallActionDrag struct{…}
    
    A drag action.
    - Path []ResponseComputerToolCallActionDragPath
      
      An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
```
[
  { x: 100, y: 200 },
  { x: 200, y: 300 }
]
```
      - X int64
        
        The x-coordinate.
      - Y int64
        
        The y-coordinate.
    - Type Drag
      
      Specifies the event type. For a drag action, this property is always set to drag.
      - const DragDrag Drag = "drag"
    - Keys []string
      
      The keys being held while dragging the mouse.
  - type ResponseComputerToolCallActionKeypress struct{…}
    
    A collection of keypresses the model would like to perform.
    - Keys []string
      
      The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
    - Type Keypress
      
      Specifies the event type. For a keypress action, this property is always set to keypress.
      - const KeypressKeypress Keypress = "keypress"
  - type ResponseComputerToolCallActionMove struct{…}
    
    A mouse move action.
    - Type Move
      
      Specifies the event type. For a move action, this property is always set to move.
      - const MoveMove Move = "move"
    - X int64
      
      The x-coordinate to move to.
    - Y int64
      
      The y-coordinate to move to.
    - Keys []string
      
      The keys being held while moving the mouse.
  - type ResponseComputerToolCallActionScreenshot struct{…}
    
    A screenshot action.
    - Type Screenshot
      
      Specifies the event type. For a screenshot action, this property is always set to screenshot.
      - const ScreenshotScreenshot Screenshot = "screenshot"
  - type ResponseComputerToolCallActionScroll struct{…}
    
    A scroll action.
    - ScrollX int64
      
      The horizontal scroll distance.
    - ScrollY int64
      
      The vertical scroll distance.
    - Type Scroll
      
      Specifies the event type. For a scroll action, this property is always set to scroll.
      - const ScrollScroll Scroll = "scroll"
    - X int64
      
      The x-coordinate where the scroll occurred.
    - Y int64
      
      The y-coordinate where the scroll occurred.
    - Keys []string
      
      The keys being held while scrolling.
  - type ResponseComputerToolCallActionType struct{…}
    
    An action to type in text.
    - Text string
      
      The text to type.
    - Type Type
      
      Specifies the event type. For a type action, this property is always set to type.
      - const TypeType Type = "type"
  - type ResponseComputerToolCallActionWait struct{…}
    
    A wait action.
    - Type Wait
      
      Specifies the event type. For a wait action, this property is always set to wait.
      - const WaitWait Wait = "wait"
- Actions ComputerActionList
  
  Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
  - type ComputerActionClick struct{…}
    
    A click action.
    - Button string
      
      Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
      - const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
      - const ComputerActionClickButtonRight ComputerActionClickButton = "right"
      - const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
      - const ComputerActionClickButtonBack ComputerActionClickButton = "back"
      - const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
    - Type Click
      
      Specifies the event type. For a click action, this property is always click.
      - const ClickClick Click = "click"
    - X int64
      
      The x-coordinate where the click occurred.
    - Y int64
      
      The y-coordinate where the click occurred.
    - Keys []string
      
      The keys being held while clicking.
  - type ComputerActionDoubleClick struct{…}
    
    A double click action.
    - Keys []string
      
      The keys being held while double-clicking.
    - Type DoubleClick
      
      Specifies the event type. For a double click action, this property is always set to double_click.
      - const DoubleClickDoubleClick DoubleClick = "double_click"
    - X int64
      
      The x-coordinate where the double click occurred.
    - Y int64
      
      The y-coordinate where the double click occurred.
  - type ComputerActionDrag struct{…}
    
    A drag action.
    - Path []ComputerActionDragPath
      
      An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
```
[
  { x: 100, y: 200 },
  { x: 200, y: 300 }
]
```
      - X int64
        
        The x-coordinate.
      - Y int64
        
        The y-coordinate.
    - Type Drag
      
      Specifies the event type. For a drag action, this property is always set to drag.
      - const DragDrag Drag = "drag"
    - Keys []string
      
      The keys being held while dragging the mouse.
  - type ComputerActionKeypress struct{…}
    
    A collection of keypresses the model would like to perform.
    - Keys []string
      
      The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
    - Type Keypress
      
      Specifies the event type. For a keypress action, this property is always set to keypress.
      - const KeypressKeypress Keypress = "keypress"
  - type ComputerActionMove struct{…}
    
    A mouse move action.
    - Type Move
      
      Specifies the event type. For a move action, this property is always set to move.
      - const MoveMove Move = "move"
    - X int64
      
      The x-coordinate to move to.
    - Y int64
      
      The y-coordinate to move to.
    - Keys []string
      
      The keys being held while moving the mouse.
  - type ComputerActionScreenshot struct{…}
    
    A screenshot action.
    - Type Screenshot
      
      Specifies the event type. For a screenshot action, this property is always set to screenshot.
      - const ScreenshotScreenshot Screenshot = "screenshot"
  - type ComputerActionScroll struct{…}
    
    A scroll action.
    - ScrollX int64
      
      The horizontal scroll distance.
    - ScrollY int64
      
      The vertical scroll distance.
    - Type Scroll
      
      Specifies the event type. For a scroll action, this property is always set to scroll.
      - const ScrollScroll Scroll = "scroll"
    - X int64
      
      The x-coordinate where the scroll occurred.
    - Y int64
      
      The y-coordinate where the scroll occurred.
    - Keys []string
      
      The keys being held while scrolling.
  - type ComputerActionType struct{…}
    
    An action to type in text.
    - Text string
      
      The text to type.
    - Type Type
      
      Specifies the event type. For a type action, this property is always set to type.
      - const TypeType Type = "type"
  - type ComputerActionWait struct{…}
    
    A wait action.
    - Type Wait
      
      Specifies the event type. For a wait action, this property is always set to wait.
      - const WaitWait Wait = "wait"

Response Computer Tool Call Output Item

type ResponseComputerToolCallOutputItem struct{…}
- ID string
  
  The unique ID of the computer call tool output.
- CallID string
  
  The ID of the computer tool call that produced the output.
- Output ResponseComputerToolCallOutputScreenshot
  
  A computer screenshot image used with the computer use tool.
  - Type ComputerScreenshot
    
    Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
    - const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
  - FileID string
    
    The identifier of an uploaded file that contains the screenshot.
  - ImageURL string
    
    The URL of the screenshot image.
- Status ResponseComputerToolCallOutputItemStatus
  
  The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
  - const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
  - const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
  - const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
  - const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
- Type ComputerCallOutput
  
  The type of the computer tool call output. Always computer_call_output.
  - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
- AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
  
  The safety checks reported by the API that have been acknowledged by the developer.
  - ID string
    
    The ID of the pending safety check.
  - Code string
    
    The type of the pending safety check.
  - Message string
    
    Details about the pending safety check.
- CreatedBy string
  
  The identifier of the actor that created the item.

Response Computer Tool Call Output Screenshot

type ResponseComputerToolCallOutputScreenshot struct{…}

A computer screenshot image used with the computer use tool.
- Type ComputerScreenshot
  
  Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
  - const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
- FileID string
  
  The identifier of an uploaded file that contains the screenshot.
- ImageURL string
  
  The URL of the screenshot image.

Response Container Reference

type ResponseContainerReference struct{…}

Represents a container created with /v1/containers.
- ContainerID string
- Type ContainerReference
  
  The environment type. Always container_reference.
  - const ContainerReferenceContainerReference ContainerReference = "container_reference"

Response Content

type ResponseContentUnion interface{…}

Multi-modal input and output contents.
- type ResponseInputText struct{…}
  
  A text input to the model.
  - Text string
    
    The text input to the model.
  - Type InputText
    
    The type of the input item. Always input_text.
    - const InputTextInputText InputText = "input_text"
- type ResponseInputImage struct{…}
  
  An image input to the model. Learn about image inputs.
  - Detail ResponseInputImageDetail
    
    The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
    - const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
    - const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
    - const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
    - const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
  - Type InputImage
    
    The type of the input item. Always input_image.
    - const InputImageInputImage InputImage = "input_image"
  - FileID string
    
    The ID of the file to be sent to the model.
  - ImageURL string
    
    The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
- type ResponseInputFile struct{…}
  
  A file input to the model.
  - Type InputFile
    
    The type of the input item. Always input_file.
    - const InputFileInputFile InputFile = "input_file"
  - Detail ResponseInputFileDetail
    
    The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
    - const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
    - const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
  - FileData string
    
    The content of the file to be sent to the model.
  - FileID string
    
    The ID of the file to be sent to the model.
  - FileURL string
    
    The URL of the file to be sent to the model.
  - Filename string
    
    The name of the file to be sent to the model.
- type ResponseOutputText struct{…}
  
  A text output from the model.
  - Annotations []ResponseOutputTextAnnotationUnion
    
    The annotations of the text output.
    - type ResponseOutputTextAnnotationFileCitation struct{…}
      
      A citation to a file.
      - FileID string
        
        The ID of the file.
      - Filename string
        
        The filename of the file cited.
      - Index int64
        
        The index of the file in the list of files.
      - Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
    - type ResponseOutputTextAnnotationURLCitation struct{…}
      
      A citation for a web resource used to generate a model response.
      - EndIndex int64
        
        The index of the last character of the URL citation in the message.
      - StartIndex int64
        
        The index of the first character of the URL citation in the message.
      - Title string
        
        The title of the web resource.
      - Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
      - URL string
        
        The URL of the web resource.
    - type ResponseOutputTextAnnotationContainerFileCitation struct{…}
      
      A citation for a container file used to generate a model response.
      - ContainerID string
        
        The ID of the container file.
      - EndIndex int64
        
        The index of the last character of the container file citation in the message.
      - FileID string
        
        The ID of the file.
      - Filename string
        
        The filename of the container file cited.
      - StartIndex int64
        
        The index of the first character of the container file citation in the message.
      - Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
    - type ResponseOutputTextAnnotationFilePath struct{…}
      
      A path to a file.
      - FileID string
        
        The ID of the file.
      - Index int64
        
        The index of the file in the list of files.
      - Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
  - Text string
    
    The text output from the model.
  - Type OutputText
    
    The type of the output text. Always output_text.
    - const OutputTextOutputText OutputText = "output_text"
  - Logprobs []ResponseOutputTextLogprob
    - Token string
    - Bytes []int64
    - Logprob float64
    - TopLogprobs []ResponseOutputTextLogprobTopLogprob
      - Token string
      - Bytes []int64
      - Logprob float64
- type ResponseOutputRefusal struct{…}
  
  A refusal from the model.
  - Refusal string
    
    The refusal explanation from the model.
  - Type Refusal
    
    The type of the refusal. Always refusal.
    - const RefusalRefusal Refusal = "refusal"
- ResponseContentReasoningTextContent
  - Text string
    
    The reasoning text from the model.
  - Type ReasoningText
    
    The type of the reasoning text. Always reasoning_text.
    - const ReasoningTextReasoningText ReasoningText = "reasoning_text"

Response Content Part Added Event

type ResponseContentPartAddedEvent struct{…}

Emitted when a new content part is added.
- ContentIndex int64
  
  The index of the content part that was added.
- ItemID string
  
  The ID of the output item that the content part was added to.
- OutputIndex int64
  
  The index of the output item that the content part was added to.
- Part ResponseContentPartAddedEventPartUnion
  
  The content part that was added.
  - type ResponseOutputText struct{…}
    
    A text output from the model.
    - Annotations []ResponseOutputTextAnnotationUnion
      
      The annotations of the text output.
      - type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
      - type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
      - type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
      - type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
    - Text string
      
      The text output from the model.
    - Type OutputText
      
      The type of the output text. Always output_text.
      - const OutputTextOutputText OutputText = "output_text"
    - Logprobs []ResponseOutputTextLogprob
      - Token string
      - Bytes []int64
      - Logprob float64
      - TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
  - type ResponseOutputRefusal struct{…}
    
    A refusal from the model.
    - Refusal string
      
      The refusal explanation from the model.
    - Type Refusal
      
      The type of the refusal. Always refusal.
      - const RefusalRefusal Refusal = "refusal"
  - type ResponseContentPartAddedEventPartReasoningText struct{…}
    
    Reasoning text from the model.
    - Text string
      
      The reasoning text from the model.
    - Type ReasoningText
      
      The type of the reasoning text. Always reasoning_text.
      - const ReasoningTextReasoningText ReasoningText = "reasoning_text"
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseContentPartAdded
  
  The type of the event. Always response.content_part.added.
  - const ResponseContentPartAddedResponseContentPartAdded ResponseContentPartAdded = "response.content_part.added"

Response Content Part Done Event

type ResponseContentPartDoneEvent struct{…}

Emitted when a content part is done.
- ContentIndex int64
  
  The index of the content part that is done.
- ItemID string
  
  The ID of the output item that the content part was added to.
- OutputIndex int64
  
  The index of the output item that the content part was added to.
- Part ResponseContentPartDoneEventPartUnion
  
  The content part that is done.
  - type ResponseOutputText struct{…}
    
    A text output from the model.
    - Annotations []ResponseOutputTextAnnotationUnion
      
      The annotations of the text output.
      - type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
      - type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
      - type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
      - type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
    - Text string
      
      The text output from the model.
    - Type OutputText
      
      The type of the output text. Always output_text.
      - const OutputTextOutputText OutputText = "output_text"
    - Logprobs []ResponseOutputTextLogprob
      - Token string
      - Bytes []int64
      - Logprob float64
      - TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
  - type ResponseOutputRefusal struct{…}
    
    A refusal from the model.
    - Refusal string
      
      The refusal explanation from the model.
    - Type Refusal
      
      The type of the refusal. Always refusal.
      - const RefusalRefusal Refusal = "refusal"
  - type ResponseContentPartDoneEventPartReasoningText struct{…}
    
    Reasoning text from the model.
    - Text string
      
      The reasoning text from the model.
    - Type ReasoningText
      
      The type of the reasoning text. Always reasoning_text.
      - const ReasoningTextReasoningText ReasoningText = "reasoning_text"
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseContentPartDone
  
  The type of the event. Always response.content_part.done.
  - const ResponseContentPartDoneResponseContentPartDone ResponseContentPartDone = "response.content_part.done"

Response Conversation Param

type ResponseConversationParamResp struct{…}

The conversation that this response belongs to.
- ID string
  
  The unique ID of the conversation.

Response Created Event

type ResponseCreatedEvent struct{…}

An event that is emitted when a response is created.
- Response Response
  
  The response that was created.
  - ID string
    
    Unique identifier for this Response.
  - CreatedAt float64
    
    Unix timestamp (in seconds) of when this Response was created.
  - Error ResponseError
    
    An error object returned when the model fails to generate a Response.
    - Code ResponseErrorCode
      
      The error code for the response.
      - const ResponseErrorCodeServerError ResponseErrorCode = "server_error"
      - const ResponseErrorCodeRateLimitExceeded ResponseErrorCode = "rate_limit_exceeded"
      - const ResponseErrorCodeInvalidPrompt ResponseErrorCode = "invalid_prompt"
      - const ResponseErrorCodeVectorStoreTimeout ResponseErrorCode = "vector_store_timeout"
      - const ResponseErrorCodeInvalidImage ResponseErrorCode = "invalid_image"
      - const ResponseErrorCodeInvalidImageFormat ResponseErrorCode = "invalid_image_format"
      - const ResponseErrorCodeInvalidBase64Image ResponseErrorCode = "invalid_base64_image"
      - const ResponseErrorCodeInvalidImageURL ResponseErrorCode = "invalid_image_url"
      - const ResponseErrorCodeImageTooLarge ResponseErrorCode = "image_too_large"
      - const ResponseErrorCodeImageTooSmall ResponseErrorCode = "image_too_small"
      - const ResponseErrorCodeImageParseError ResponseErrorCode = "image_parse_error"
      - const ResponseErrorCodeImageContentPolicyViolation ResponseErrorCode = "image_content_policy_violation"
      - const ResponseErrorCodeInvalidImageMode ResponseErrorCode = "invalid_image_mode"
      - const ResponseErrorCodeImageFileTooLarge ResponseErrorCode = "image_file_too_large"
      - const ResponseErrorCodeUnsupportedImageMediaType ResponseErrorCode = "unsupported_image_media_type"
      - const ResponseErrorCodeEmptyImageFile ResponseErrorCode = "empty_image_file"
      - const ResponseErrorCodeFailedToDownloadImage ResponseErrorCode = "failed_to_download_image"
      - const ResponseErrorCodeImageFileNotFound ResponseErrorCode = "image_file_not_found"
    - Message string
      
      A human-readable description of the error.
  - IncompleteDetails ResponseIncompleteDetails
    
    Details about why the response is incomplete.
    - Reason string
      
      The reason why the response is incomplete.
      - const ResponseIncompleteDetailsReasonMaxOutputTokens ResponseIncompleteDetailsReason = "max_output_tokens"
      - const ResponseIncompleteDetailsReasonContentFilter ResponseIncompleteDetailsReason = "content_filter"
  - Instructions ResponseInstructionsUnion
    
    A system (or developer) message inserted into the model's context.
    
    When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
    - string
    - type ResponseInstructionsInputItemList []ResponseInputItemUnion
      
      A list of one or many input items to the model, containing different content types.
      - type EasyInputMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
        
        Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
        
        Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
        
        Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
      - type ResponseInputItemMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
        
        Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
        
        Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
        
        Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
        
        Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
      - type ResponseOutputMessage struct{…}
        
        An output message from the model.
        
        ID string
        
        The unique ID of the output message.
        
        Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
        
        Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
        
        Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
        
        Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
        
        Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
      - type ResponseFileSearchToolCall struct{…}
        
        The results of a file search tool call. See the file search guide for more information.
        
        ID string
        
        The unique ID of the file search tool call.
        
        Queries []string
        
        The queries used to search for files.
        
        Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
        
        Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
        
        Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
      - type ResponseComputerToolCall struct{…}
        
        A tool call to a computer use tool. See the computer use guide for more information.
        
        ID string
        
        The unique ID of the computer call.
        
        CallID string
        
        An identifier used when responding to the tool call with output.
        
        PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
        
        Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
        
        Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
        
        Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
      - type ResponseInputItemComputerCallOutput struct{…}
        
        The output of a computer tool call.
        
        CallID string
        
        The ID of the computer tool call that produced the output.
        
        Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
        
        Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
        
        ID string
        
        The ID of the computer tool call output.
        
        AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
      - type ResponseFunctionWebSearch struct{…}
        
        The results of a web search tool call. See the web search guide for more information.
        
        ID string
        
        The unique ID of the web search tool call.
        
        Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
        
        Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
        
        Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
      - type ResponseFunctionToolCall struct{…}
        
        A tool call to run a function. See the function calling guide for more information.
        
        Arguments string
        
        A JSON string of the arguments to pass to the function.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Name string
        
        The name of the function to run.
        
        Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
        
        ID string
        
        The unique ID of the function tool call.
        
        Namespace string
        
        The namespace of the function to run.
        
        Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
      - type ResponseInputItemFunctionCallOutput struct{…}
        
        The output of a function tool call.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
        
        ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
      - type ResponseInputItemToolSearchCall struct{…}
        
        Arguments any
        
        The arguments supplied to the tool search call.
        
        Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
        
        ID string
        
        The unique ID of this tool search call.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
        
        Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
      - type ResponseToolSearchOutputItemParamResp struct{…}
        
        Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
        
        Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
        
        ID string
        
        The unique ID of this tool search output.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
        
        Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
      - type ResponseInputItemAdditionalTools struct{…}
        
        Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
        
        Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
        
        ID string
        
        The unique ID of this additional tools item.
      - type ResponseReasoningItem struct{…}
        
        A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
        
        ID string
        
        The unique identifier of the reasoning content.
        
        Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
        
        Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
        
        Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
        
        EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
        
        Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
      - type ResponseCompactionItemParamResp struct{…}
        
        A compaction item generated by the v1/responses/compact API.
        
        EncryptedContent string
        
        The encrypted content of the compaction summary.
        
        Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
        
        ID string
        
        The ID of the compaction item.
      - type ResponseInputItemImageGenerationCall struct{…}
        
        An image generation request made by the model.
        
        ID string
        
        The unique ID of the image generation call.
        
        Result string
        
        The generated image encoded in base64.
        
        Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
        
        Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
      - type ResponseCodeInterpreterToolCall struct{…}
        
        A tool call to run code.
        
        ID string
        
        The unique ID of the code interpreter tool call.
        
        Code string
        
        The code to run, or null if not available.
        
        ContainerID string
        
        The ID of the container used to run the code.
        
        Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
        
        Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
        
        Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
      - type ResponseInputItemLocalShellCall struct{…}
        
        A tool call to run a command on the local shell.
        
        ID string
        
        The unique ID of the local shell call.
        
        Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
        
        CallID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
        
        Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
      - type ResponseInputItemLocalShellCallOutput struct{…}
        
        The output of a local shell tool call.
        
        ID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Output string
        
        A JSON string of the output of the local shell tool call.
        
        Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
      - type ResponseInputItemShellCall struct{…}
        
        A tool representing a request to execute one or more shell commands.
        
        Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
        
        ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
        
        Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
        
        Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
      - type ResponseInputItemShellCallOutput struct{…}
        
        The streamed output items emitted by a shell tool call.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
        
        Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
        
        ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
        
        MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
        
        Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
      - type ResponseInputItemApplyPatchCall struct{…}
        
        A tool call representing a request to create, delete, or update files using diff patches.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
        
        Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
        
        Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
        
        ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
      - type ResponseInputItemApplyPatchCallOutput struct{…}
        
        The streamed output emitted by an apply patch tool call.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
        
        Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
        
        ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
        
        Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
      - type ResponseInputItemMcpListTools struct{…}
        
        A list of tools available on an MCP server.
        
        ID string
        
        The unique ID of the list.
        
        ServerLabel string
        
        The label of the MCP server.
        
        Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
        
        Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
        
        Error string
        
        Error message if the server could not list tools.
      - type ResponseInputItemMcpApprovalRequest struct{…}
        
        A request for human approval of a tool invocation.
        
        ID string
        
        The unique ID of the approval request.
        
        Arguments string
        
        A JSON string of arguments for the tool.
        
        Name string
        
        The name of the tool to run.
        
        ServerLabel string
        
        The label of the MCP server making the request.
        
        Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
      - type ResponseInputItemMcpApprovalResponse struct{…}
        
        A response to an MCP approval request.
        
        ApprovalRequestID string
        
        The ID of the approval request being answered.
        
        Approve bool
        
        Whether the request was approved.
        
        Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
        
        ID string
        
        The unique ID of the approval response
        
        Reason string
        
        Optional reason for the decision.
      - type ResponseInputItemMcpCall struct{…}
        
        An invocation of a tool on an MCP server.
        
        ID string
        
        The unique ID of the tool call.
        
        Arguments string
        
        A JSON string of the arguments passed to the tool.
        
        Name string
        
        The name of the tool that was run.
        
        ServerLabel string
        
        The label of the MCP server running the tool.
        
        Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
        
        ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
        
        Error string
        
        The error from the tool call, if any.
        
        Output string
        
        The output from the tool call.
        
        Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
      - type ResponseCustomToolCallOutput struct{…}
        
        The output of a custom tool call from your code, being sent back to the model.
        
        CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
        
        Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
        
        ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
      - type ResponseCustomToolCall struct{…}
        
        A call to a custom tool created by the model.
        
        CallID string
        
        An identifier used to map this custom tool call to a tool call output.
        
        Input string
        
        The input for the custom tool call generated by the model.
        
        Name string
        
        The name of the custom tool being called.
        
        Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
        
        ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
        
        Namespace string
        
        The namespace of the custom tool being called.
      - type ResponseInputItemCompactionTrigger struct{…}
        
        Compacts the current context. Must be the final input item.
        
        Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
      - type ResponseInputItemItemReference struct{…}
        
        An internal identifier for an item to reference.
        
        ID string
        
        The ID of the item to reference.
        
        Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
  - Metadata Metadata
    
    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
    
    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
  - Model ResponsesModel
    
    Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
    - string
    - type ChatModel string
      - const ChatModelGPT5_4 ChatModel = "gpt-5.4"
      - const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"
      - const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"
      - const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"
      - const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"
      - const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"
      - const ChatModelGPT5_2 ChatModel = "gpt-5.2"
      - const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"
      - const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"
      - const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"
      - const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"
      - const ChatModelGPT5_1 ChatModel = "gpt-5.1"
      - const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"
      - const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"
      - const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"
      - const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"
      - const ChatModelGPT5 ChatModel = "gpt-5"
      - const ChatModelGPT5Mini ChatModel = "gpt-5-mini"
      - const ChatModelGPT5Nano ChatModel = "gpt-5-nano"
      - const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"
      - const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"
      - const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"
      - const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"
      - const ChatModelGPT4_1 ChatModel = "gpt-4.1"
      - const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"
      - const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"
      - const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"
      - const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"
      - const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"
      - const ChatModelO4Mini ChatModel = "o4-mini"
      - const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"
      - const ChatModelO3 ChatModel = "o3"
      - const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"
      - const ChatModelO3Mini ChatModel = "o3-mini"
      - const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"
      - const ChatModelO1 ChatModel = "o1"
      - const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"
      - const ChatModelO1Preview ChatModel = "o1-preview"
      - const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"
      - const ChatModelO1Mini ChatModel = "o1-mini"
      - const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"
      - const ChatModelGPT4o ChatModel = "gpt-4o"
      - const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"
      - const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"
      - const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"
      - const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"
      - const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"
      - const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"
      - const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"
      - const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"
      - const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"
      - const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"
      - const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"
      - const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"
      - const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"
      - const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"
      - const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"
      - const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"
      - const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"
      - const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"
      - const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"
      - const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"
      - const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"
      - const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"
      - const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"
      - const ChatModelGPT4 ChatModel = "gpt-4"
      - const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"
      - const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"
      - const ChatModelGPT4_32k ChatModel = "gpt-4-32k"
      - const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"
      - const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"
      - const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"
      - const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"
      - const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"
      - const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"
      - const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"
      - const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"
      - const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"
    - type ResponsesModel string
      - const ResponsesModelO1Pro ResponsesModel = "o1-pro"
      - const ResponsesModelO1Pro2025_03_19 ResponsesModel = "o1-pro-2025-03-19"
      - const ResponsesModelO3Pro ResponsesModel = "o3-pro"
      - const ResponsesModelO3Pro2025_06_10 ResponsesModel = "o3-pro-2025-06-10"
      - const ResponsesModelO3DeepResearch ResponsesModel = "o3-deep-research"
      - const ResponsesModelO3DeepResearch2025_06_26 ResponsesModel = "o3-deep-research-2025-06-26"
      - const ResponsesModelO4MiniDeepResearch ResponsesModel = "o4-mini-deep-research"
      - const ResponsesModelO4MiniDeepResearch2025_06_26 ResponsesModel = "o4-mini-deep-research-2025-06-26"
      - const ResponsesModelComputerUsePreview ResponsesModel = "computer-use-preview"
      - const ResponsesModelComputerUsePreview2025_03_11 ResponsesModel = "computer-use-preview-2025-03-11"
      - const ResponsesModelGPT5Codex ResponsesModel = "gpt-5-codex"
      - const ResponsesModelGPT5Pro ResponsesModel = "gpt-5-pro"
      - const ResponsesModelGPT5Pro2025_10_06 ResponsesModel = "gpt-5-pro-2025-10-06"
      - const ResponsesModelGPT5_1CodexMax ResponsesModel = "gpt-5.1-codex-max"
  - Object Response
    
    The object type of this resource - always set to response.
    - const ResponseResponse Response = "response"
  - Output []ResponseOutputItemUnion
    
    An array of content items generated by the model.
    - The length and order of items in the output array is dependent on the model's response.
    - Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
    - type ResponseFunctionToolCallOutputItem struct{…}
      - ID string
        
        The unique ID of the function call tool output.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Output ResponseFunctionToolCallOutputItemOutputUnion
        
        The output from the function call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Status ResponseFunctionToolCallOutputItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
        
        const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
        
        const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
      - Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
    - type ResponseComputerToolCallOutputItem struct{…}
      - ID string
        
        The unique ID of the computer call tool output.
      - CallID string
        
        The ID of the computer tool call that produced the output.
      - Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
      - Status ResponseComputerToolCallOutputItemStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
        
        const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
        
        const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
        
        const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
      - Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
      - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
    - type ResponseToolSearchCall struct{…}
      - ID string
        
        The unique ID of the tool search call item.
      - Arguments any
        
        Arguments used for the tool search call.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchCallExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
        
        const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
      - Status ResponseToolSearchCallStatus
        
        The status of the tool search call item that was recorded.
        
        const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
        
        const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
        
        const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
      - Type ToolSearchCall
        
        The type of the item. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseToolSearchOutputItem struct{…}
      - ID string
        
        The unique ID of the tool search output item.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchOutputItemExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
        
        const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
      - Status ResponseToolSearchOutputItemStatus
        
        The status of the tool search output item that was recorded.
        
        const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
        
        const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
        
        const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
      - Tools []ToolUnion
        
        The loaded tool definitions returned by tool search.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type ToolSearchOutput
        
        The type of the item. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseOutputItemAdditionalTools struct{…}
      - ID string
        
        The unique ID of the additional tools item.
      - Role string
        
        The role that provided the additional tools.
        
        const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
        
        const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
        
        const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
        
        const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
        
        const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
        
        const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
        
        const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
        
        const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
      - Tools []ToolUnion
        
        The additional tool definitions made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type AdditionalTools
        
        The type of the item. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
    - type ResponseCompactionItem struct{…}
      
      A compaction item generated by the v1/responses/compact API.
      - ID string
        
        The unique ID of the compaction item.
      - EncryptedContent string
        
        The encrypted content that was produced by compaction.
      - Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseOutputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
      - ID string
        
        The unique ID of the image generation call.
      - Result string
        
        The generated image encoded in base64.
      - Status string
        
        The status of the image generation call.
        
        const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
        
        const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
        
        const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
      - Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
    - type ResponseOutputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
      - ID string
        
        The unique ID of the local shell call.
      - Action ResponseOutputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
      - CallID string
        
        The unique ID of the local shell tool call generated by the model.
      - Status string
        
        The status of the local shell call.
        
        const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
        
        const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
      - Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
    - type ResponseOutputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
      - ID string
        
        The unique ID of the local shell tool call generated by the model.
      - Output string
        
        A JSON string of the output of the local shell tool call.
      - Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
    - type ResponseFunctionShellToolCall struct{…}
      
      A tool call that executes one or more shell commands in a managed environment.
      - ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
      - Action ResponseFunctionShellToolCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Environment ResponseFunctionShellToolCallEnvironmentUnion
        
        Represents the use of a local environment to perform shell actions.
        
        type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
        
        type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
      - Status ResponseFunctionShellToolCallStatus
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
        
        const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
        
        const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
      - Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
      - CreatedBy string
        
        The ID of the entity that created this tool call.
    - type ResponseFunctionShellToolCallOutput struct{…}
      
      The output of a shell tool call that was emitted.
      - ID string
        
        The unique ID of the shell call output. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - MaxOutputLength int64
        
        The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
      - Output []ResponseFunctionShellToolCallOutputOutput
        
        An array of shell call output contents
        
        Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        The standard error output that was captured.
        
        Stdout string
        
        The standard output that was captured.
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - Status ResponseFunctionShellToolCallOutputStatus
        
        The status of the shell call output. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
        
        const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
        
        const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
      - Type ShellCallOutput
        
        The type of the shell call output. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseApplyPatchToolCall struct{…}
      
      A tool call that applies file diffs by creating, deleting, or updating files.
      - ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Operation ResponseApplyPatchToolCallOperationUnion
        
        One of the create_file, delete_file, or update_file operations applied via apply_patch.
        
        type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
      - Status ResponseApplyPatchToolCallStatus
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
        
        const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
      - Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
      - CreatedBy string
        
        The ID of the entity that created this tool call.
    - type ResponseApplyPatchToolCallOutput struct{…}
      
      The output emitted by an apply patch tool call.
      - ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Status ResponseApplyPatchToolCallOutputStatus
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
        
        const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
      - Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
      - CreatedBy string
        
        The ID of the entity that created this tool call output.
      - Output string
        
        Optional textual output returned by the apply patch tool.
    - type ResponseOutputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
      - ID string
        
        The unique ID of the tool call.
      - Arguments string
        
        A JSON string of the arguments passed to the tool.
      - Name string
        
        The name of the tool that was run.
      - ServerLabel string
        
        The label of the MCP server running the tool.
      - Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
      - ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
      - Error string
        
        The error from the tool call, if any.
      - Output string
        
        The output from the tool call.
      - Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
        
        const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
        
        const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
        
        const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
        
        const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
    - type ResponseOutputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
      - ID string
        
        The unique ID of the list.
      - ServerLabel string
        
        The label of the MCP server.
      - Tools []ResponseOutputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
      - Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
      - Error string
        
        Error message if the server could not list tools.
    - type ResponseOutputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
      - ID string
        
        The unique ID of the approval request.
      - Arguments string
        
        A JSON string of arguments for the tool.
      - Name string
        
        The name of the tool to run.
      - ServerLabel string
        
        The label of the MCP server making the request.
      - Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
    - type ResponseOutputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
      - ID string
        
        The unique ID of the approval response
      - ApprovalRequestID string
        
        The ID of the approval request being answered.
      - Approve bool
        
        Whether the request was approved.
      - Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
      - Reason string
        
        Optional reason for the decision.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
    - type ResponseCustomToolCallOutputItem struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
      - ID string
        
        The unique ID of the custom tool call output item.
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
        
        const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
        
        const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
      - CreatedBy string
        
        The identifier of the actor that created the item.
  - ParallelToolCalls bool
    
    Whether to allow the model to run tool calls in parallel.
  - Temperature float64
    
    What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
  - ToolChoice ResponseToolChoiceUnion
    
    How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.
    - type ToolChoiceOptions string
      
      Controls which (if any) tool is called by the model.
      
      none means the model will not call any tool and instead generates a message.
      
      auto means the model can pick between generating a message or calling one or more tools.
      
      required means the model must call one or more tools.
      - const ToolChoiceOptionsNone ToolChoiceOptions = "none"
      - const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
      - const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
    - type ToolChoiceAllowed struct{…}
      
      Constrains the tools available to the model to a pre-defined set.
      - Mode ToolChoiceAllowedMode
        
        Constrains the tools available to the model to a pre-defined set.
        
        auto allows the model to pick from among the allowed tools and generate a message.
        
        required requires the model to call one or more of the allowed tools.
        
        const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
        
        const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
      - Tools []map[string, any]
        
        A list of tool definitions that the model should be allowed to call.
        
        For the Responses API, the list of tool definitions might look like:
        
        [ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ]
      - Type AllowedTools
        
        Allowed tool configuration type. Always allowed_tools.
        
        const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
    - type ToolChoiceTypes struct{…}
      
      Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
      - Type ToolChoiceTypesType
        
        The type of hosted tool the model should to use. Learn more about built-in tools.
        
        Allowed values are:
        
        file_search
        
        web_search_preview
        
        computer
        
        computer_use_preview
        
        computer_use
        
        code_interpreter
        
        image_generation
        
        const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
        
        const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
        
        const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
        
        const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
        
        const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
        
        const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
        
        const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
        
        const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
    - type ToolChoiceFunction struct{…}
      
      Use this option to force the model to call a specific function.
      - Name string
        
        The name of the function to call.
      - Type Function
        
        For function calling, the type is always function.
        
        const FunctionFunction Function = "function"
    - type ToolChoiceMcp struct{…}
      
      Use this option to force the model to call a specific tool on a remote MCP server.
      - ServerLabel string
        
        The label of the MCP server to use.
      - Type Mcp
        
        For MCP tools, the type is always mcp.
        
        const McpMcp Mcp = "mcp"
      - Name string
        
        The name of the tool to call on the server.
    - type ToolChoiceCustom struct{…}
      
      Use this option to force the model to call a specific custom tool.
      - Name string
        
        The name of the custom tool to call.
      - Type Custom
        
        For custom tool calling, the type is always custom.
        
        const CustomCustom Custom = "custom"
    - type ToolChoiceApplyPatch struct{…}
      
      Forces the model to call the apply_patch tool when executing a tool call.
      - Type ApplyPatch
        
        The tool to call. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
    - type ToolChoiceShell struct{…}
      
      Forces the model to call the shell tool when a tool call is required.
      - Type Shell
        
        The tool to call. Always shell.
        
        const ShellShell Shell = "shell"
  - Tools []ToolUnion
    
    An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
    
    We support the following categories of tools:
    - Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
    - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
    - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
  - TopP float64
    
    An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
    
    We generally recommend altering this or temperature but not both.
  - Background bool
    
    Whether to run the model response in the background. Learn more.
  - CompletedAt float64
    
    Unix timestamp (in seconds) of when this Response was completed. Only present when the status is completed.
  - Conversation ResponseConversation
    
    The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
    - ID string
      
      The unique ID of the conversation that this response was associated with.
  - MaxOutputTokens int64
    
    An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
  - MaxToolCalls int64
    
    The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
  - Moderation ResponseModeration
    
    Moderation results for the response input and output, if moderated completions were requested.
    - Input ResponseModerationInputUnion
      
      Moderation for the response input.
      - type ResponseModerationInputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeText ResponseModerationInputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeImage ResponseModerationInputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
      - type ResponseModerationInputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
    - Output ResponseModerationOutputUnion
      
      Moderation for the response output.
      - type ResponseModerationOutputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeText ResponseModerationOutputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeImage ResponseModerationOutputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
      - type ResponseModerationOutputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
  - PreviousResponseID string
    
    The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
  - Prompt ResponsePrompt
    
    Reference to a prompt template and its variables. Learn more.
    - ID string
      
      The unique identifier of the prompt template to use.
    - Variables map[string, ResponsePromptVariableUnion]
      
      Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
      - string
      - type ResponseInputText struct{…}
        
        A text input to the model.
      - type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
      - type ResponseInputFile struct{…}
        
        A file input to the model.
    - Version string
      
      Optional version of the prompt template.
  - PromptCacheKey string
    
    Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
  - PromptCacheRetention ResponsePromptCacheRetention
    
    The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.
    
    For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:
    - Organizations without ZDR enabled default to 24h.
    - Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.
    - const ResponsePromptCacheRetentionInMemory ResponsePromptCacheRetention = "in_memory"
    - const ResponsePromptCacheRetention24h ResponsePromptCacheRetention = "24h"
  - Reasoning Reasoning
    
    gpt-5 and o-series models only
    
    Configuration options for reasoning models.
    - Context ReasoningContext
      
      Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
      - const ReasoningContextAuto ReasoningContext = "auto"
      - const ReasoningContextCurrentTurn ReasoningContext = "current_turn"
      - const ReasoningContextAllTurns ReasoningContext = "all_turns"
    - Effort ReasoningEffort
      
      Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
      - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
      - All models before gpt-5.1 default to medium reasoning effort, and do not support none.
      - The gpt-5-pro model defaults to (and only supports) high reasoning effort.
      - xhigh is supported for all models after gpt-5.1-codex-max.
      - const ReasoningEffortNone ReasoningEffort = "none"
      - const ReasoningEffortMinimal ReasoningEffort = "minimal"
      - const ReasoningEffortLow ReasoningEffort = "low"
      - const ReasoningEffortMedium ReasoningEffort = "medium"
      - const ReasoningEffortHigh ReasoningEffort = "high"
      - const ReasoningEffortXhigh ReasoningEffort = "xhigh"
    - GenerateSummary ReasoningGenerateSummary
      
      Deprecated: use summary instead.
      
      A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
      - const ReasoningGenerateSummaryAuto ReasoningGenerateSummary = "auto"
      - const ReasoningGenerateSummaryConcise ReasoningGenerateSummary = "concise"
      - const ReasoningGenerateSummaryDetailed ReasoningGenerateSummary = "detailed"
    - Summary ReasoningSummary
      
      A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
      
      concise is supported for computer-use-preview models and all reasoning models after gpt-5.
      - const ReasoningSummaryAuto ReasoningSummary = "auto"
      - const ReasoningSummaryConcise ReasoningSummary = "concise"
      - const ReasoningSummaryDetailed ReasoningSummary = "detailed"
  - SafetyIdentifier string
    
    A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
  - ServiceTier ResponseServiceTier
    
    Specifies the processing type used for serving the request.
    - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
    - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
    - If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
    - When not set, the default behavior is 'auto'.
    When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
    - const ResponseServiceTierAuto ResponseServiceTier = "auto"
    - const ResponseServiceTierDefault ResponseServiceTier = "default"
    - const ResponseServiceTierFlex ResponseServiceTier = "flex"
    - const ResponseServiceTierScale ResponseServiceTier = "scale"
    - const ResponseServiceTierPriority ResponseServiceTier = "priority"
  - Status ResponseStatus
    
    The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
    - const ResponseStatusCompleted ResponseStatus = "completed"
    - const ResponseStatusFailed ResponseStatus = "failed"
    - const ResponseStatusInProgress ResponseStatus = "in_progress"
    - const ResponseStatusCancelled ResponseStatus = "cancelled"
    - const ResponseStatusQueued ResponseStatus = "queued"
    - const ResponseStatusIncomplete ResponseStatus = "incomplete"
  - Text ResponseTextConfig
    
    Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
    - Text inputs and outputs
    - Structured Outputs
    - Format ResponseFormatTextConfigUnion
      
      An object specifying the format that the model must output.
      
      Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
      
      The default format is { "type": "text" } with no additional options.
      
      Not recommended for gpt-4o and newer models:
      
      Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
      - type ResponseFormatText struct{…}
        
        Default response format. Used to generate text responses.
        
        Type Text
        
        The type of response format being defined. Always text.
        
        const TextText Text = "text"
      - type ResponseFormatTextJSONSchemaConfig struct{…}
        
        JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
        
        Name string
        
        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
        
        Schema map[string, any]
        
        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
        
        Type JSONSchema
        
        The type of response format being defined. Always json_schema.
        
        const JSONSchemaJSONSchema JSONSchema = "json_schema"
        
        Description string
        
        A description of what the response format is for, used by the model to determine how to respond in the format.
        
        Strict bool
        
        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
      - type ResponseFormatJSONObject struct{…}
        
        JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
        
        Type JSONObject
        
        The type of response format being defined. Always json_object.
        
        const JSONObjectJSONObject JSONObject = "json_object"
    - Verbosity ResponseTextConfigVerbosity
      
      Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
      - const ResponseTextConfigVerbosityLow ResponseTextConfigVerbosity = "low"
      - const ResponseTextConfigVerbosityMedium ResponseTextConfigVerbosity = "medium"
      - const ResponseTextConfigVerbosityHigh ResponseTextConfigVerbosity = "high"
  - TopLogprobs int64
    
    An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
  - Truncation ResponseTruncation
    
    The truncation strategy to use for the model response.
    - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
    - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
    - const ResponseTruncationAuto ResponseTruncation = "auto"
    - const ResponseTruncationDisabled ResponseTruncation = "disabled"
  - Usage ResponseUsage
    
    Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
    - InputTokens int64
      
      The number of input tokens.
    - InputTokensDetails ResponseUsageInputTokensDetails
      
      A detailed breakdown of the input tokens.
      - CachedTokens int64
        
        The number of tokens that were retrieved from the cache. More on prompt caching.
    - OutputTokens int64
      
      The number of output tokens.
    - OutputTokensDetails ResponseUsageOutputTokensDetails
      
      A detailed breakdown of the output tokens.
      - ReasoningTokens int64
        
        The number of reasoning tokens.
    - TotalTokens int64
      
      The total number of tokens used.
  - User string
    
    This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
- SequenceNumber int64
  
  The sequence number for this event.
- Type ResponseCreated
  
  The type of the event. Always response.created.
  - const ResponseCreatedResponseCreated ResponseCreated = "response.created"

Response Custom Tool Call

type ResponseCustomToolCall struct{…}

A call to a custom tool created by the model.
- CallID string
  
  An identifier used to map this custom tool call to a tool call output.
- Input string
  
  The input for the custom tool call generated by the model.
- Name string
  
  The name of the custom tool being called.
- Type CustomToolCall
  
  The type of the custom tool call. Always custom_tool_call.
  - const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
- ID string
  
  The unique ID of the custom tool call in the OpenAI platform.
- Namespace string
  
  The namespace of the custom tool being called.

Response Custom Tool Call Input Delta Event

type ResponseCustomToolCallInputDeltaEvent struct{…}

Event representing a delta (partial update) to the input of a custom tool call.
- Delta string
  
  The incremental input data (delta) for the custom tool call.
- ItemID string
  
  Unique identifier for the API item associated with this event.
- OutputIndex int64
  
  The index of the output this delta applies to.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseCustomToolCallInputDelta
  
  The event type identifier.
  - const ResponseCustomToolCallInputDeltaResponseCustomToolCallInputDelta ResponseCustomToolCallInputDelta = "response.custom_tool_call_input.delta"

Response Custom Tool Call Input Done Event

type ResponseCustomToolCallInputDoneEvent struct{…}

Event indicating that input for a custom tool call is complete.
- Input string
  
  The complete input data for the custom tool call.
- ItemID string
  
  Unique identifier for the API item associated with this event.
- OutputIndex int64
  
  The index of the output this event applies to.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseCustomToolCallInputDone
  
  The event type identifier.
  - const ResponseCustomToolCallInputDoneResponseCustomToolCallInputDone ResponseCustomToolCallInputDone = "response.custom_tool_call_input.done"

Response Custom Tool Call Item

type ResponseCustomToolCallItem struct{…}

A call to a custom tool created by the model.
- ID string
  
  The unique ID of the custom tool call item.
- Status string
  
  The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
  - const ResponseCustomToolCallItemStatusInProgress ResponseCustomToolCallItemStatus = "in_progress"
  - const ResponseCustomToolCallItemStatusCompleted ResponseCustomToolCallItemStatus = "completed"
  - const ResponseCustomToolCallItemStatusIncomplete ResponseCustomToolCallItemStatus = "incomplete"
- CreatedBy string
  
  The identifier of the actor that created the item.

Response Custom Tool Call Output

type ResponseCustomToolCallOutput struct{…}

The output of a custom tool call from your code, being sent back to the model.
- CallID string
  
  The call ID, used to map this custom tool call output to a custom tool call.
- Output ResponseCustomToolCallOutputOutputUnion
  
  The output from the custom tool call generated by your code. Can be a string or an list of output content.
  - string
  - type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
    
    Text, image, or file output of the custom tool call.
    - type ResponseInputText struct{…}
      
      A text input to the model.
      - Text string
        
        The text input to the model.
      - Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
    - type ResponseInputImage struct{…}
      
      An image input to the model. Learn about image inputs.
      - Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
      - Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
      - FileID string
        
        The ID of the file to be sent to the model.
      - ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
    - type ResponseInputFile struct{…}
      
      A file input to the model.
      - Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
      - Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
      - FileData string
        
        The content of the file to be sent to the model.
      - FileID string
        
        The ID of the file to be sent to the model.
      - FileURL string
        
        The URL of the file to be sent to the model.
      - Filename string
        
        The name of the file to be sent to the model.
- Type CustomToolCallOutput
  
  The type of the custom tool call output. Always custom_tool_call_output.
  - const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
- ID string
  
  The unique ID of the custom tool call output in the OpenAI platform.

Response Custom Tool Call Output Item

type ResponseCustomToolCallOutputItem struct{…}

The output of a custom tool call from your code, being sent back to the model.
- ID string
  
  The unique ID of the custom tool call output item.
- Status string
  
  The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
  - const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
  - const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
  - const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
- CreatedBy string
  
  The identifier of the actor that created the item.

Response Error

type ResponseError struct{…}

An error object returned when the model fails to generate a Response.
- Code ResponseErrorCode
  
  The error code for the response.
  - const ResponseErrorCodeServerError ResponseErrorCode = "server_error"
  - const ResponseErrorCodeRateLimitExceeded ResponseErrorCode = "rate_limit_exceeded"
  - const ResponseErrorCodeInvalidPrompt ResponseErrorCode = "invalid_prompt"
  - const ResponseErrorCodeVectorStoreTimeout ResponseErrorCode = "vector_store_timeout"
  - const ResponseErrorCodeInvalidImage ResponseErrorCode = "invalid_image"
  - const ResponseErrorCodeInvalidImageFormat ResponseErrorCode = "invalid_image_format"
  - const ResponseErrorCodeInvalidBase64Image ResponseErrorCode = "invalid_base64_image"
  - const ResponseErrorCodeInvalidImageURL ResponseErrorCode = "invalid_image_url"
  - const ResponseErrorCodeImageTooLarge ResponseErrorCode = "image_too_large"
  - const ResponseErrorCodeImageTooSmall ResponseErrorCode = "image_too_small"
  - const ResponseErrorCodeImageParseError ResponseErrorCode = "image_parse_error"
  - const ResponseErrorCodeImageContentPolicyViolation ResponseErrorCode = "image_content_policy_violation"
  - const ResponseErrorCodeInvalidImageMode ResponseErrorCode = "invalid_image_mode"
  - const ResponseErrorCodeImageFileTooLarge ResponseErrorCode = "image_file_too_large"
  - const ResponseErrorCodeUnsupportedImageMediaType ResponseErrorCode = "unsupported_image_media_type"
  - const ResponseErrorCodeEmptyImageFile ResponseErrorCode = "empty_image_file"
  - const ResponseErrorCodeFailedToDownloadImage ResponseErrorCode = "failed_to_download_image"
  - const ResponseErrorCodeImageFileNotFound ResponseErrorCode = "image_file_not_found"
- Message string
  
  A human-readable description of the error.

Response Error Event

type ResponseErrorEvent struct{…}

Emitted when an error occurs.
- Code string
  
  The error code.
- Message string
  
  The error message.
- Param string
  
  The error parameter.
- SequenceNumber int64
  
  The sequence number of this event.
- Type Error
  
  The type of the event. Always error.
  - const ErrorError Error = "error"

Response Failed Event

type ResponseFailedEvent struct{…}

An event that is emitted when a response fails.
- Response Response
  
  The response that failed.
  - ID string
    
    Unique identifier for this Response.
  - CreatedAt float64
    
    Unix timestamp (in seconds) of when this Response was created.
  - Error ResponseError
    
    An error object returned when the model fails to generate a Response.
    - Code ResponseErrorCode
      
      The error code for the response.
      - const ResponseErrorCodeServerError ResponseErrorCode = "server_error"
      - const ResponseErrorCodeRateLimitExceeded ResponseErrorCode = "rate_limit_exceeded"
      - const ResponseErrorCodeInvalidPrompt ResponseErrorCode = "invalid_prompt"
      - const ResponseErrorCodeVectorStoreTimeout ResponseErrorCode = "vector_store_timeout"
      - const ResponseErrorCodeInvalidImage ResponseErrorCode = "invalid_image"
      - const ResponseErrorCodeInvalidImageFormat ResponseErrorCode = "invalid_image_format"
      - const ResponseErrorCodeInvalidBase64Image ResponseErrorCode = "invalid_base64_image"
      - const ResponseErrorCodeInvalidImageURL ResponseErrorCode = "invalid_image_url"
      - const ResponseErrorCodeImageTooLarge ResponseErrorCode = "image_too_large"
      - const ResponseErrorCodeImageTooSmall ResponseErrorCode = "image_too_small"
      - const ResponseErrorCodeImageParseError ResponseErrorCode = "image_parse_error"
      - const ResponseErrorCodeImageContentPolicyViolation ResponseErrorCode = "image_content_policy_violation"
      - const ResponseErrorCodeInvalidImageMode ResponseErrorCode = "invalid_image_mode"
      - const ResponseErrorCodeImageFileTooLarge ResponseErrorCode = "image_file_too_large"
      - const ResponseErrorCodeUnsupportedImageMediaType ResponseErrorCode = "unsupported_image_media_type"
      - const ResponseErrorCodeEmptyImageFile ResponseErrorCode = "empty_image_file"
      - const ResponseErrorCodeFailedToDownloadImage ResponseErrorCode = "failed_to_download_image"
      - const ResponseErrorCodeImageFileNotFound ResponseErrorCode = "image_file_not_found"
    - Message string
      
      A human-readable description of the error.
  - IncompleteDetails ResponseIncompleteDetails
    
    Details about why the response is incomplete.
    - Reason string
      
      The reason why the response is incomplete.
      - const ResponseIncompleteDetailsReasonMaxOutputTokens ResponseIncompleteDetailsReason = "max_output_tokens"
      - const ResponseIncompleteDetailsReasonContentFilter ResponseIncompleteDetailsReason = "content_filter"
  - Instructions ResponseInstructionsUnion
    
    A system (or developer) message inserted into the model's context.
    
    When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
    - string
    - type ResponseInstructionsInputItemList []ResponseInputItemUnion
      
      A list of one or many input items to the model, containing different content types.
      - type EasyInputMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
        
        Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
        
        Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
        
        Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
      - type ResponseInputItemMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
        
        Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
        
        Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
        
        Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
        
        Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
      - type ResponseOutputMessage struct{…}
        
        An output message from the model.
        
        ID string
        
        The unique ID of the output message.
        
        Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
        
        Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
        
        Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
        
        Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
        
        Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
      - type ResponseFileSearchToolCall struct{…}
        
        The results of a file search tool call. See the file search guide for more information.
        
        ID string
        
        The unique ID of the file search tool call.
        
        Queries []string
        
        The queries used to search for files.
        
        Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
        
        Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
        
        Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
      - type ResponseComputerToolCall struct{…}
        
        A tool call to a computer use tool. See the computer use guide for more information.
        
        ID string
        
        The unique ID of the computer call.
        
        CallID string
        
        An identifier used when responding to the tool call with output.
        
        PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
        
        Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
        
        Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
        
        Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
      - type ResponseInputItemComputerCallOutput struct{…}
        
        The output of a computer tool call.
        
        CallID string
        
        The ID of the computer tool call that produced the output.
        
        Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
        
        Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
        
        ID string
        
        The ID of the computer tool call output.
        
        AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
      - type ResponseFunctionWebSearch struct{…}
        
        The results of a web search tool call. See the web search guide for more information.
        
        ID string
        
        The unique ID of the web search tool call.
        
        Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
        
        Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
        
        Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
      - type ResponseFunctionToolCall struct{…}
        
        A tool call to run a function. See the function calling guide for more information.
        
        Arguments string
        
        A JSON string of the arguments to pass to the function.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Name string
        
        The name of the function to run.
        
        Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
        
        ID string
        
        The unique ID of the function tool call.
        
        Namespace string
        
        The namespace of the function to run.
        
        Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
      - type ResponseInputItemFunctionCallOutput struct{…}
        
        The output of a function tool call.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
        
        ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
      - type ResponseInputItemToolSearchCall struct{…}
        
        Arguments any
        
        The arguments supplied to the tool search call.
        
        Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
        
        ID string
        
        The unique ID of this tool search call.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
        
        Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
      - type ResponseToolSearchOutputItemParamResp struct{…}
        
        Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
        
        Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
        
        ID string
        
        The unique ID of this tool search output.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
        
        Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
      - type ResponseInputItemAdditionalTools struct{…}
        
        Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
        
        Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
        
        ID string
        
        The unique ID of this additional tools item.
      - type ResponseReasoningItem struct{…}
        
        A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
        
        ID string
        
        The unique identifier of the reasoning content.
        
        Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
        
        Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
        
        Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
        
        EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
        
        Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
      - type ResponseCompactionItemParamResp struct{…}
        
        A compaction item generated by the v1/responses/compact API.
        
        EncryptedContent string
        
        The encrypted content of the compaction summary.
        
        Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
        
        ID string
        
        The ID of the compaction item.
      - type ResponseInputItemImageGenerationCall struct{…}
        
        An image generation request made by the model.
        
        ID string
        
        The unique ID of the image generation call.
        
        Result string
        
        The generated image encoded in base64.
        
        Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
        
        Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
      - type ResponseCodeInterpreterToolCall struct{…}
        
        A tool call to run code.
        
        ID string
        
        The unique ID of the code interpreter tool call.
        
        Code string
        
        The code to run, or null if not available.
        
        ContainerID string
        
        The ID of the container used to run the code.
        
        Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
        
        Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
        
        Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
      - type ResponseInputItemLocalShellCall struct{…}
        
        A tool call to run a command on the local shell.
        
        ID string
        
        The unique ID of the local shell call.
        
        Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
        
        CallID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
        
        Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
      - type ResponseInputItemLocalShellCallOutput struct{…}
        
        The output of a local shell tool call.
        
        ID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Output string
        
        A JSON string of the output of the local shell tool call.
        
        Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
      - type ResponseInputItemShellCall struct{…}
        
        A tool representing a request to execute one or more shell commands.
        
        Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
        
        ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
        
        Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
        
        Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
      - type ResponseInputItemShellCallOutput struct{…}
        
        The streamed output items emitted by a shell tool call.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
        
        Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
        
        ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
        
        MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
        
        Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
      - type ResponseInputItemApplyPatchCall struct{…}
        
        A tool call representing a request to create, delete, or update files using diff patches.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
        
        Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
        
        Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
        
        ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
      - type ResponseInputItemApplyPatchCallOutput struct{…}
        
        The streamed output emitted by an apply patch tool call.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
        
        Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
        
        ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
        
        Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
      - type ResponseInputItemMcpListTools struct{…}
        
        A list of tools available on an MCP server.
        
        ID string
        
        The unique ID of the list.
        
        ServerLabel string
        
        The label of the MCP server.
        
        Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
        
        Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
        
        Error string
        
        Error message if the server could not list tools.
      - type ResponseInputItemMcpApprovalRequest struct{…}
        
        A request for human approval of a tool invocation.
        
        ID string
        
        The unique ID of the approval request.
        
        Arguments string
        
        A JSON string of arguments for the tool.
        
        Name string
        
        The name of the tool to run.
        
        ServerLabel string
        
        The label of the MCP server making the request.
        
        Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
      - type ResponseInputItemMcpApprovalResponse struct{…}
        
        A response to an MCP approval request.
        
        ApprovalRequestID string
        
        The ID of the approval request being answered.
        
        Approve bool
        
        Whether the request was approved.
        
        Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
        
        ID string
        
        The unique ID of the approval response
        
        Reason string
        
        Optional reason for the decision.
      - type ResponseInputItemMcpCall struct{…}
        
        An invocation of a tool on an MCP server.
        
        ID string
        
        The unique ID of the tool call.
        
        Arguments string
        
        A JSON string of the arguments passed to the tool.
        
        Name string
        
        The name of the tool that was run.
        
        ServerLabel string
        
        The label of the MCP server running the tool.
        
        Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
        
        ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
        
        Error string
        
        The error from the tool call, if any.
        
        Output string
        
        The output from the tool call.
        
        Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
      - type ResponseCustomToolCallOutput struct{…}
        
        The output of a custom tool call from your code, being sent back to the model.
        
        CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
        
        Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
        
        ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
      - type ResponseCustomToolCall struct{…}
        
        A call to a custom tool created by the model.
        
        CallID string
        
        An identifier used to map this custom tool call to a tool call output.
        
        Input string
        
        The input for the custom tool call generated by the model.
        
        Name string
        
        The name of the custom tool being called.
        
        Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
        
        ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
        
        Namespace string
        
        The namespace of the custom tool being called.
      - type ResponseInputItemCompactionTrigger struct{…}
        
        Compacts the current context. Must be the final input item.
        
        Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
      - type ResponseInputItemItemReference struct{…}
        
        An internal identifier for an item to reference.
        
        ID string
        
        The ID of the item to reference.
        
        Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
  - Metadata Metadata
    
    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
    
    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
  - Model ResponsesModel
    
    Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
    - string
    - type ChatModel string
      - const ChatModelGPT5_4 ChatModel = "gpt-5.4"
      - const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"
      - const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"
      - const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"
      - const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"
      - const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"
      - const ChatModelGPT5_2 ChatModel = "gpt-5.2"
      - const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"
      - const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"
      - const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"
      - const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"
      - const ChatModelGPT5_1 ChatModel = "gpt-5.1"
      - const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"
      - const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"
      - const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"
      - const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"
      - const ChatModelGPT5 ChatModel = "gpt-5"
      - const ChatModelGPT5Mini ChatModel = "gpt-5-mini"
      - const ChatModelGPT5Nano ChatModel = "gpt-5-nano"
      - const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"
      - const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"
      - const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"
      - const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"
      - const ChatModelGPT4_1 ChatModel = "gpt-4.1"
      - const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"
      - const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"
      - const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"
      - const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"
      - const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"
      - const ChatModelO4Mini ChatModel = "o4-mini"
      - const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"
      - const ChatModelO3 ChatModel = "o3"
      - const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"
      - const ChatModelO3Mini ChatModel = "o3-mini"
      - const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"
      - const ChatModelO1 ChatModel = "o1"
      - const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"
      - const ChatModelO1Preview ChatModel = "o1-preview"
      - const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"
      - const ChatModelO1Mini ChatModel = "o1-mini"
      - const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"
      - const ChatModelGPT4o ChatModel = "gpt-4o"
      - const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"
      - const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"
      - const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"
      - const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"
      - const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"
      - const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"
      - const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"
      - const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"
      - const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"
      - const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"
      - const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"
      - const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"
      - const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"
      - const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"
      - const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"
      - const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"
      - const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"
      - const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"
      - const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"
      - const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"
      - const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"
      - const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"
      - const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"
      - const ChatModelGPT4 ChatModel = "gpt-4"
      - const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"
      - const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"
      - const ChatModelGPT4_32k ChatModel = "gpt-4-32k"
      - const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"
      - const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"
      - const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"
      - const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"
      - const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"
      - const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"
      - const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"
      - const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"
      - const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"
    - type ResponsesModel string
      - const ResponsesModelO1Pro ResponsesModel = "o1-pro"
      - const ResponsesModelO1Pro2025_03_19 ResponsesModel = "o1-pro-2025-03-19"
      - const ResponsesModelO3Pro ResponsesModel = "o3-pro"
      - const ResponsesModelO3Pro2025_06_10 ResponsesModel = "o3-pro-2025-06-10"
      - const ResponsesModelO3DeepResearch ResponsesModel = "o3-deep-research"
      - const ResponsesModelO3DeepResearch2025_06_26 ResponsesModel = "o3-deep-research-2025-06-26"
      - const ResponsesModelO4MiniDeepResearch ResponsesModel = "o4-mini-deep-research"
      - const ResponsesModelO4MiniDeepResearch2025_06_26 ResponsesModel = "o4-mini-deep-research-2025-06-26"
      - const ResponsesModelComputerUsePreview ResponsesModel = "computer-use-preview"
      - const ResponsesModelComputerUsePreview2025_03_11 ResponsesModel = "computer-use-preview-2025-03-11"
      - const ResponsesModelGPT5Codex ResponsesModel = "gpt-5-codex"
      - const ResponsesModelGPT5Pro ResponsesModel = "gpt-5-pro"
      - const ResponsesModelGPT5Pro2025_10_06 ResponsesModel = "gpt-5-pro-2025-10-06"
      - const ResponsesModelGPT5_1CodexMax ResponsesModel = "gpt-5.1-codex-max"
  - Object Response
    
    The object type of this resource - always set to response.
    - const ResponseResponse Response = "response"
  - Output []ResponseOutputItemUnion
    
    An array of content items generated by the model.
    - The length and order of items in the output array is dependent on the model's response.
    - Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
    - type ResponseFunctionToolCallOutputItem struct{…}
      - ID string
        
        The unique ID of the function call tool output.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Output ResponseFunctionToolCallOutputItemOutputUnion
        
        The output from the function call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Status ResponseFunctionToolCallOutputItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
        
        const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
        
        const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
      - Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
    - type ResponseComputerToolCallOutputItem struct{…}
      - ID string
        
        The unique ID of the computer call tool output.
      - CallID string
        
        The ID of the computer tool call that produced the output.
      - Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
      - Status ResponseComputerToolCallOutputItemStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
        
        const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
        
        const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
        
        const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
      - Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
      - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
    - type ResponseToolSearchCall struct{…}
      - ID string
        
        The unique ID of the tool search call item.
      - Arguments any
        
        Arguments used for the tool search call.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchCallExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
        
        const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
      - Status ResponseToolSearchCallStatus
        
        The status of the tool search call item that was recorded.
        
        const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
        
        const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
        
        const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
      - Type ToolSearchCall
        
        The type of the item. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseToolSearchOutputItem struct{…}
      - ID string
        
        The unique ID of the tool search output item.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchOutputItemExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
        
        const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
      - Status ResponseToolSearchOutputItemStatus
        
        The status of the tool search output item that was recorded.
        
        const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
        
        const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
        
        const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
      - Tools []ToolUnion
        
        The loaded tool definitions returned by tool search.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type ToolSearchOutput
        
        The type of the item. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseOutputItemAdditionalTools struct{…}
      - ID string
        
        The unique ID of the additional tools item.
      - Role string
        
        The role that provided the additional tools.
        
        const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
        
        const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
        
        const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
        
        const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
        
        const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
        
        const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
        
        const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
        
        const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
      - Tools []ToolUnion
        
        The additional tool definitions made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type AdditionalTools
        
        The type of the item. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
    - type ResponseCompactionItem struct{…}
      
      A compaction item generated by the v1/responses/compact API.
      - ID string
        
        The unique ID of the compaction item.
      - EncryptedContent string
        
        The encrypted content that was produced by compaction.
      - Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseOutputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
      - ID string
        
        The unique ID of the image generation call.
      - Result string
        
        The generated image encoded in base64.
      - Status string
        
        The status of the image generation call.
        
        const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
        
        const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
        
        const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
      - Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
    - type ResponseOutputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
      - ID string
        
        The unique ID of the local shell call.
      - Action ResponseOutputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
      - CallID string
        
        The unique ID of the local shell tool call generated by the model.
      - Status string
        
        The status of the local shell call.
        
        const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
        
        const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
      - Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
    - type ResponseOutputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
      - ID string
        
        The unique ID of the local shell tool call generated by the model.
      - Output string
        
        A JSON string of the output of the local shell tool call.
      - Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
    - type ResponseFunctionShellToolCall struct{…}
      
      A tool call that executes one or more shell commands in a managed environment.
      - ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
      - Action ResponseFunctionShellToolCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Environment ResponseFunctionShellToolCallEnvironmentUnion
        
        Represents the use of a local environment to perform shell actions.
        
        type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
        
        type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
      - Status ResponseFunctionShellToolCallStatus
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
        
        const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
        
        const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
      - Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
      - CreatedBy string
        
        The ID of the entity that created this tool call.
    - type ResponseFunctionShellToolCallOutput struct{…}
      
      The output of a shell tool call that was emitted.
      - ID string
        
        The unique ID of the shell call output. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - MaxOutputLength int64
        
        The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
      - Output []ResponseFunctionShellToolCallOutputOutput
        
        An array of shell call output contents
        
        Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        The standard error output that was captured.
        
        Stdout string
        
        The standard output that was captured.
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - Status ResponseFunctionShellToolCallOutputStatus
        
        The status of the shell call output. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
        
        const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
        
        const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
      - Type ShellCallOutput
        
        The type of the shell call output. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseApplyPatchToolCall struct{…}
      
      A tool call that applies file diffs by creating, deleting, or updating files.
      - ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Operation ResponseApplyPatchToolCallOperationUnion
        
        One of the create_file, delete_file, or update_file operations applied via apply_patch.
        
        type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
      - Status ResponseApplyPatchToolCallStatus
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
        
        const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
      - Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
      - CreatedBy string
        
        The ID of the entity that created this tool call.
    - type ResponseApplyPatchToolCallOutput struct{…}
      
      The output emitted by an apply patch tool call.
      - ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Status ResponseApplyPatchToolCallOutputStatus
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
        
        const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
      - Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
      - CreatedBy string
        
        The ID of the entity that created this tool call output.
      - Output string
        
        Optional textual output returned by the apply patch tool.
    - type ResponseOutputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
      - ID string
        
        The unique ID of the tool call.
      - Arguments string
        
        A JSON string of the arguments passed to the tool.
      - Name string
        
        The name of the tool that was run.
      - ServerLabel string
        
        The label of the MCP server running the tool.
      - Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
      - ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
      - Error string
        
        The error from the tool call, if any.
      - Output string
        
        The output from the tool call.
      - Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
        
        const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
        
        const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
        
        const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
        
        const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
    - type ResponseOutputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
      - ID string
        
        The unique ID of the list.
      - ServerLabel string
        
        The label of the MCP server.
      - Tools []ResponseOutputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
      - Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
      - Error string
        
        Error message if the server could not list tools.
    - type ResponseOutputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
      - ID string
        
        The unique ID of the approval request.
      - Arguments string
        
        A JSON string of arguments for the tool.
      - Name string
        
        The name of the tool to run.
      - ServerLabel string
        
        The label of the MCP server making the request.
      - Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
    - type ResponseOutputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
      - ID string
        
        The unique ID of the approval response
      - ApprovalRequestID string
        
        The ID of the approval request being answered.
      - Approve bool
        
        Whether the request was approved.
      - Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
      - Reason string
        
        Optional reason for the decision.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
    - type ResponseCustomToolCallOutputItem struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
      - ID string
        
        The unique ID of the custom tool call output item.
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
        
        const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
        
        const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
      - CreatedBy string
        
        The identifier of the actor that created the item.
  - ParallelToolCalls bool
    
    Whether to allow the model to run tool calls in parallel.
  - Temperature float64
    
    What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
  - ToolChoice ResponseToolChoiceUnion
    
    How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.
    - type ToolChoiceOptions string
      
      Controls which (if any) tool is called by the model.
      
      none means the model will not call any tool and instead generates a message.
      
      auto means the model can pick between generating a message or calling one or more tools.
      
      required means the model must call one or more tools.
      - const ToolChoiceOptionsNone ToolChoiceOptions = "none"
      - const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
      - const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
    - type ToolChoiceAllowed struct{…}
      
      Constrains the tools available to the model to a pre-defined set.
      - Mode ToolChoiceAllowedMode
        
        Constrains the tools available to the model to a pre-defined set.
        
        auto allows the model to pick from among the allowed tools and generate a message.
        
        required requires the model to call one or more of the allowed tools.
        
        const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
        
        const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
      - Tools []map[string, any]
        
        A list of tool definitions that the model should be allowed to call.
        
        For the Responses API, the list of tool definitions might look like:
        
        [ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ]
      - Type AllowedTools
        
        Allowed tool configuration type. Always allowed_tools.
        
        const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
    - type ToolChoiceTypes struct{…}
      
      Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
      - Type ToolChoiceTypesType
        
        The type of hosted tool the model should to use. Learn more about built-in tools.
        
        Allowed values are:
        
        file_search
        
        web_search_preview
        
        computer
        
        computer_use_preview
        
        computer_use
        
        code_interpreter
        
        image_generation
        
        const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
        
        const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
        
        const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
        
        const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
        
        const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
        
        const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
        
        const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
        
        const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
    - type ToolChoiceFunction struct{…}
      
      Use this option to force the model to call a specific function.
      - Name string
        
        The name of the function to call.
      - Type Function
        
        For function calling, the type is always function.
        
        const FunctionFunction Function = "function"
    - type ToolChoiceMcp struct{…}
      
      Use this option to force the model to call a specific tool on a remote MCP server.
      - ServerLabel string
        
        The label of the MCP server to use.
      - Type Mcp
        
        For MCP tools, the type is always mcp.
        
        const McpMcp Mcp = "mcp"
      - Name string
        
        The name of the tool to call on the server.
    - type ToolChoiceCustom struct{…}
      
      Use this option to force the model to call a specific custom tool.
      - Name string
        
        The name of the custom tool to call.
      - Type Custom
        
        For custom tool calling, the type is always custom.
        
        const CustomCustom Custom = "custom"
    - type ToolChoiceApplyPatch struct{…}
      
      Forces the model to call the apply_patch tool when executing a tool call.
      - Type ApplyPatch
        
        The tool to call. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
    - type ToolChoiceShell struct{…}
      
      Forces the model to call the shell tool when a tool call is required.
      - Type Shell
        
        The tool to call. Always shell.
        
        const ShellShell Shell = "shell"
  - Tools []ToolUnion
    
    An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
    
    We support the following categories of tools:
    - Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
    - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
    - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
  - TopP float64
    
    An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
    
    We generally recommend altering this or temperature but not both.
  - Background bool
    
    Whether to run the model response in the background. Learn more.
  - CompletedAt float64
    
    Unix timestamp (in seconds) of when this Response was completed. Only present when the status is completed.
  - Conversation ResponseConversation
    
    The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
    - ID string
      
      The unique ID of the conversation that this response was associated with.
  - MaxOutputTokens int64
    
    An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
  - MaxToolCalls int64
    
    The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
  - Moderation ResponseModeration
    
    Moderation results for the response input and output, if moderated completions were requested.
    - Input ResponseModerationInputUnion
      
      Moderation for the response input.
      - type ResponseModerationInputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeText ResponseModerationInputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeImage ResponseModerationInputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
      - type ResponseModerationInputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
    - Output ResponseModerationOutputUnion
      
      Moderation for the response output.
      - type ResponseModerationOutputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeText ResponseModerationOutputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeImage ResponseModerationOutputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
      - type ResponseModerationOutputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
  - PreviousResponseID string
    
    The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
  - Prompt ResponsePrompt
    
    Reference to a prompt template and its variables. Learn more.
    - ID string
      
      The unique identifier of the prompt template to use.
    - Variables map[string, ResponsePromptVariableUnion]
      
      Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
      - string
      - type ResponseInputText struct{…}
        
        A text input to the model.
      - type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
      - type ResponseInputFile struct{…}
        
        A file input to the model.
    - Version string
      
      Optional version of the prompt template.
  - PromptCacheKey string
    
    Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
  - PromptCacheRetention ResponsePromptCacheRetention
    
    The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.
    
    For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:
    - Organizations without ZDR enabled default to 24h.
    - Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.
    - const ResponsePromptCacheRetentionInMemory ResponsePromptCacheRetention = "in_memory"
    - const ResponsePromptCacheRetention24h ResponsePromptCacheRetention = "24h"
  - Reasoning Reasoning
    
    gpt-5 and o-series models only
    
    Configuration options for reasoning models.
    - Context ReasoningContext
      
      Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
      - const ReasoningContextAuto ReasoningContext = "auto"
      - const ReasoningContextCurrentTurn ReasoningContext = "current_turn"
      - const ReasoningContextAllTurns ReasoningContext = "all_turns"
    - Effort ReasoningEffort
      
      Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
      - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
      - All models before gpt-5.1 default to medium reasoning effort, and do not support none.
      - The gpt-5-pro model defaults to (and only supports) high reasoning effort.
      - xhigh is supported for all models after gpt-5.1-codex-max.
      - const ReasoningEffortNone ReasoningEffort = "none"
      - const ReasoningEffortMinimal ReasoningEffort = "minimal"
      - const ReasoningEffortLow ReasoningEffort = "low"
      - const ReasoningEffortMedium ReasoningEffort = "medium"
      - const ReasoningEffortHigh ReasoningEffort = "high"
      - const ReasoningEffortXhigh ReasoningEffort = "xhigh"
    - GenerateSummary ReasoningGenerateSummary
      
      Deprecated: use summary instead.
      
      A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
      - const ReasoningGenerateSummaryAuto ReasoningGenerateSummary = "auto"
      - const ReasoningGenerateSummaryConcise ReasoningGenerateSummary = "concise"
      - const ReasoningGenerateSummaryDetailed ReasoningGenerateSummary = "detailed"
    - Summary ReasoningSummary
      
      A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
      
      concise is supported for computer-use-preview models and all reasoning models after gpt-5.
      - const ReasoningSummaryAuto ReasoningSummary = "auto"
      - const ReasoningSummaryConcise ReasoningSummary = "concise"
      - const ReasoningSummaryDetailed ReasoningSummary = "detailed"
  - SafetyIdentifier string
    
    A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
  - ServiceTier ResponseServiceTier
    
    Specifies the processing type used for serving the request.
    - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
    - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
    - If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
    - When not set, the default behavior is 'auto'.
    When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
    - const ResponseServiceTierAuto ResponseServiceTier = "auto"
    - const ResponseServiceTierDefault ResponseServiceTier = "default"
    - const ResponseServiceTierFlex ResponseServiceTier = "flex"
    - const ResponseServiceTierScale ResponseServiceTier = "scale"
    - const ResponseServiceTierPriority ResponseServiceTier = "priority"
  - Status ResponseStatus
    
    The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
    - const ResponseStatusCompleted ResponseStatus = "completed"
    - const ResponseStatusFailed ResponseStatus = "failed"
    - const ResponseStatusInProgress ResponseStatus = "in_progress"
    - const ResponseStatusCancelled ResponseStatus = "cancelled"
    - const ResponseStatusQueued ResponseStatus = "queued"
    - const ResponseStatusIncomplete ResponseStatus = "incomplete"
  - Text ResponseTextConfig
    
    Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
    - Text inputs and outputs
    - Structured Outputs
    - Format ResponseFormatTextConfigUnion
      
      An object specifying the format that the model must output.
      
      Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
      
      The default format is { "type": "text" } with no additional options.
      
      Not recommended for gpt-4o and newer models:
      
      Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
      - type ResponseFormatText struct{…}
        
        Default response format. Used to generate text responses.
        
        Type Text
        
        The type of response format being defined. Always text.
        
        const TextText Text = "text"
      - type ResponseFormatTextJSONSchemaConfig struct{…}
        
        JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
        
        Name string
        
        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
        
        Schema map[string, any]
        
        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
        
        Type JSONSchema
        
        The type of response format being defined. Always json_schema.
        
        const JSONSchemaJSONSchema JSONSchema = "json_schema"
        
        Description string
        
        A description of what the response format is for, used by the model to determine how to respond in the format.
        
        Strict bool
        
        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
      - type ResponseFormatJSONObject struct{…}
        
        JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
        
        Type JSONObject
        
        The type of response format being defined. Always json_object.
        
        const JSONObjectJSONObject JSONObject = "json_object"
    - Verbosity ResponseTextConfigVerbosity
      
      Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
      - const ResponseTextConfigVerbosityLow ResponseTextConfigVerbosity = "low"
      - const ResponseTextConfigVerbosityMedium ResponseTextConfigVerbosity = "medium"
      - const ResponseTextConfigVerbosityHigh ResponseTextConfigVerbosity = "high"
  - TopLogprobs int64
    
    An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
  - Truncation ResponseTruncation
    
    The truncation strategy to use for the model response.
    - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
    - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
    - const ResponseTruncationAuto ResponseTruncation = "auto"
    - const ResponseTruncationDisabled ResponseTruncation = "disabled"
  - Usage ResponseUsage
    
    Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
    - InputTokens int64
      
      The number of input tokens.
    - InputTokensDetails ResponseUsageInputTokensDetails
      
      A detailed breakdown of the input tokens.
      - CachedTokens int64
        
        The number of tokens that were retrieved from the cache. More on prompt caching.
    - OutputTokens int64
      
      The number of output tokens.
    - OutputTokensDetails ResponseUsageOutputTokensDetails
      
      A detailed breakdown of the output tokens.
      - ReasoningTokens int64
        
        The number of reasoning tokens.
    - TotalTokens int64
      
      The total number of tokens used.
  - User string
    
    This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseFailed
  
  The type of the event. Always response.failed.
  - const ResponseFailedResponseFailed ResponseFailed = "response.failed"

Response File Search Call Completed Event

type ResponseFileSearchCallCompletedEvent struct{…}

Emitted when a file search call is completed (results found).
- ItemID string
  
  The ID of the output item that the file search call is initiated.
- OutputIndex int64
  
  The index of the output item that the file search call is initiated.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseFileSearchCallCompleted
  
  The type of the event. Always response.file_search_call.completed.
  - const ResponseFileSearchCallCompletedResponseFileSearchCallCompleted ResponseFileSearchCallCompleted = "response.file_search_call.completed"

Response File Search Call In Progress Event

type ResponseFileSearchCallInProgressEvent struct{…}

Emitted when a file search call is initiated.
- ItemID string
  
  The ID of the output item that the file search call is initiated.
- OutputIndex int64
  
  The index of the output item that the file search call is initiated.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseFileSearchCallInProgress
  
  The type of the event. Always response.file_search_call.in_progress.
  - const ResponseFileSearchCallInProgressResponseFileSearchCallInProgress ResponseFileSearchCallInProgress = "response.file_search_call.in_progress"

Response File Search Call Searching Event

type ResponseFileSearchCallSearchingEvent struct{…}

Emitted when a file search is currently searching.
- ItemID string
  
  The ID of the output item that the file search call is initiated.
- OutputIndex int64
  
  The index of the output item that the file search call is searching.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseFileSearchCallSearching
  
  The type of the event. Always response.file_search_call.searching.
  - const ResponseFileSearchCallSearchingResponseFileSearchCallSearching ResponseFileSearchCallSearching = "response.file_search_call.searching"

Response File Search Tool Call

type ResponseFileSearchToolCall struct{…}

The results of a file search tool call. See the file search guide for more information.
- ID string
  
  The unique ID of the file search tool call.
- Queries []string
  
  The queries used to search for files.
- Status ResponseFileSearchToolCallStatus
  
  The status of the file search tool call. One of in_progress, searching, incomplete or failed,
  - const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
  - const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
  - const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
  - const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
  - const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
- Type FileSearchCall
  
  The type of the file search tool call. Always file_search_call.
  - const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
- Results []ResponseFileSearchToolCallResult
  
  The results of the file search tool call.
  - Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
    
    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
    - string
    - float64
    - bool
  - FileID string
    
    The unique ID of the file.
  - Filename string
    
    The name of the file.
  - Score float64
    
    The relevance score of the file - a value between 0 and 1.
  - Text string
    
    The text that was retrieved from the file.

Response Format Text Config

type ResponseFormatTextConfigUnion interface{…}

An object specifying the format that the model must output.

Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

The default format is { "type": "text" } with no additional options.

Not recommended for gpt-4o and newer models:

Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
- type ResponseFormatText struct{…}
  
  Default response format. Used to generate text responses.
  - Type Text
    
    The type of response format being defined. Always text.
    - const TextText Text = "text"
- type ResponseFormatTextJSONSchemaConfig struct{…}
  
  JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
  - Name string
    
    The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
  - Schema map[string, any]
    
    The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
  - Type JSONSchema
    
    The type of response format being defined. Always json_schema.
    - const JSONSchemaJSONSchema JSONSchema = "json_schema"
  - Description string
    
    A description of what the response format is for, used by the model to determine how to respond in the format.
  - Strict bool
    
    Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
- type ResponseFormatJSONObject struct{…}
  
  JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
  - Type JSONObject
    
    The type of response format being defined. Always json_object.
    - const JSONObjectJSONObject JSONObject = "json_object"

Response Format Text JSON Schema Config

type ResponseFormatTextJSONSchemaConfig struct{…}

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
- Name string
  
  The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
- Schema map[string, any]
  
  The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
- Type JSONSchema
  
  The type of response format being defined. Always json_schema.
  - const JSONSchemaJSONSchema JSONSchema = "json_schema"
- Description string
  
  A description of what the response format is for, used by the model to determine how to respond in the format.
- Strict bool
  
  Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

Response Function Call Arguments Delta Event

type ResponseFunctionCallArgumentsDeltaEvent struct{…}

Emitted when there is a partial function-call arguments delta.
- Delta string
  
  The function-call arguments delta that is added.
- ItemID string
  
  The ID of the output item that the function-call arguments delta is added to.
- OutputIndex int64
  
  The index of the output item that the function-call arguments delta is added to.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseFunctionCallArgumentsDelta
  
  The type of the event. Always response.function_call_arguments.delta.
  - const ResponseFunctionCallArgumentsDeltaResponseFunctionCallArgumentsDelta ResponseFunctionCallArgumentsDelta = "response.function_call_arguments.delta"

Response Function Call Arguments Done Event

type ResponseFunctionCallArgumentsDoneEvent struct{…}

Emitted when function-call arguments are finalized.
- Arguments string
  
  The function-call arguments.
- ItemID string
  
  The ID of the item.
- Name string
  
  The name of the function that was called.
- OutputIndex int64
  
  The index of the output item.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseFunctionCallArgumentsDone
  - const ResponseFunctionCallArgumentsDoneResponseFunctionCallArgumentsDone ResponseFunctionCallArgumentsDone = "response.function_call_arguments.done"

Response Function Call Output Item

type ResponseFunctionCallOutputItemUnion interface{…}

A piece of message content, such as text, an image, or a file.
- type ResponseInputTextContent struct{…}
  
  A text input to the model.
  - Text string
    
    The text input to the model.
  - Type InputText
    
    The type of the input item. Always input_text.
    - const InputTextInputText InputText = "input_text"
- type ResponseInputImageContent struct{…}
  
  An image input to the model. Learn about image inputs
  - Type InputImage
    
    The type of the input item. Always input_image.
    - const InputImageInputImage InputImage = "input_image"
  - Detail ResponseInputImageContentDetail
    
    The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
    - const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
    - const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
    - const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
    - const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
  - FileID string
    
    The ID of the file to be sent to the model.
  - ImageURL string
    
    The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
- type ResponseInputFileContent struct{…}
  
  A file input to the model.
  - Type InputFile
    
    The type of the input item. Always input_file.
    - const InputFileInputFile InputFile = "input_file"
  - Detail ResponseInputFileContentDetail
    
    The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
    - const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
    - const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
  - FileData string
    
    The base64-encoded data of the file to be sent to the model.
  - FileID string
    
    The ID of the file to be sent to the model.
  - FileURL string
    
    The URL of the file to be sent to the model.
  - Filename string
    
    The name of the file to be sent to the model.

Response Function Call Output Item List

type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion

An array of content outputs (text, image, file) for the function tool call.
- type ResponseInputTextContent struct{…}
  
  A text input to the model.
  - Text string
    
    The text input to the model.
  - Type InputText
    
    The type of the input item. Always input_text.
    - const InputTextInputText InputText = "input_text"
- type ResponseInputImageContent struct{…}
  
  An image input to the model. Learn about image inputs
  - Type InputImage
    
    The type of the input item. Always input_image.
    - const InputImageInputImage InputImage = "input_image"
  - Detail ResponseInputImageContentDetail
    
    The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
    - const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
    - const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
    - const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
    - const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
  - FileID string
    
    The ID of the file to be sent to the model.
  - ImageURL string
    
    The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
- type ResponseInputFileContent struct{…}
  
  A file input to the model.
  - Type InputFile
    
    The type of the input item. Always input_file.
    - const InputFileInputFile InputFile = "input_file"
  - Detail ResponseInputFileContentDetail
    
    The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
    - const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
    - const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
  - FileData string
    
    The base64-encoded data of the file to be sent to the model.
  - FileID string
    
    The ID of the file to be sent to the model.
  - FileURL string
    
    The URL of the file to be sent to the model.
  - Filename string
    
    The name of the file to be sent to the model.

Response Function Shell Call Output Content

type ResponseFunctionShellCallOutputContent struct{…}

Captured stdout and stderr for a portion of a shell tool call output.
- Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
  
  The exit or timeout outcome associated with this shell call.
  - type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
    
    Indicates that the shell call exceeded its configured time limit.
    - Type Timeout
      
      The outcome type. Always timeout.
      - const TimeoutTimeout Timeout = "timeout"
  - type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
    
    Indicates that the shell commands finished and returned an exit code.
    - ExitCode int64
      
      The exit code returned by the shell process.
    - Type Exit
      
      The outcome type. Always exit.
      - const ExitExit Exit = "exit"
- Stderr string
  
  Captured stderr output for the shell call.
- Stdout string
  
  Captured stdout output for the shell call.

Response Function Shell Tool Call

type ResponseFunctionShellToolCall struct{…}

A tool call that executes one or more shell commands in a managed environment.
- ID string
  
  The unique ID of the shell tool call. Populated when this item is returned via API.
- Action ResponseFunctionShellToolCallAction
  
  The shell commands and limits that describe how to run the tool call.
  - Commands []string
  - MaxOutputLength int64
    
    Optional maximum number of characters to return from each command.
  - TimeoutMs int64
    
    Optional timeout in milliseconds for the commands.
- CallID string
  
  The unique ID of the shell tool call generated by the model.
- Environment ResponseFunctionShellToolCallEnvironmentUnion
  
  Represents the use of a local environment to perform shell actions.
  - type ResponseLocalEnvironment struct{…}
    
    Represents the use of a local environment to perform shell actions.
    - Type Local
      
      The environment type. Always local.
      - const LocalLocal Local = "local"
  - type ResponseContainerReference struct{…}
    
    Represents a container created with /v1/containers.
    - ContainerID string
    - Type ContainerReference
      
      The environment type. Always container_reference.
      - const ContainerReferenceContainerReference ContainerReference = "container_reference"
- Status ResponseFunctionShellToolCallStatus
  
  The status of the shell call. One of in_progress, completed, or incomplete.
  - const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
  - const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
  - const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
- Type ShellCall
  
  The type of the item. Always shell_call.
  - const ShellCallShellCall ShellCall = "shell_call"
- CreatedBy string
  
  The ID of the entity that created this tool call.

Response Function Shell Tool Call Output

type ResponseFunctionShellToolCallOutput struct{…}

The output of a shell tool call that was emitted.
- ID string
  
  The unique ID of the shell call output. Populated when this item is returned via API.
- CallID string
  
  The unique ID of the shell tool call generated by the model.
- MaxOutputLength int64
  
  The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
- Output []ResponseFunctionShellToolCallOutputOutput
  
  An array of shell call output contents
  - Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
    
    Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
    - type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
      
      Indicates that the shell call exceeded its configured time limit.
      - Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
    - type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
      
      Indicates that the shell commands finished and returned an exit code.
      - ExitCode int64
        
        Exit code from the shell process.
      - Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
  - Stderr string
    
    The standard error output that was captured.
  - Stdout string
    
    The standard output that was captured.
  - CreatedBy string
    
    The identifier of the actor that created the item.
- Status ResponseFunctionShellToolCallOutputStatus
  
  The status of the shell call output. One of in_progress, completed, or incomplete.
  - const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
  - const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
  - const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
- Type ShellCallOutput
  
  The type of the shell call output. Always shell_call_output.
  - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
- CreatedBy string
  
  The identifier of the actor that created the item.

Response Function Tool Call

type ResponseFunctionToolCall struct{…}

A tool call to run a function. See the function calling guide for more information.
- Arguments string
  
  A JSON string of the arguments to pass to the function.
- CallID string
  
  The unique ID of the function tool call generated by the model.
- Name string
  
  The name of the function to run.
- Type FunctionCall
  
  The type of the function tool call. Always function_call.
  - const FunctionCallFunctionCall FunctionCall = "function_call"
- ID string
  
  The unique ID of the function tool call.
- Namespace string
  
  The namespace of the function to run.
- Status ResponseFunctionToolCallStatus
  
  The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
  - const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
  - const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
  - const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"

Response Function Tool Call Item

type ResponseFunctionToolCallItem struct{…}

A tool call to run a function. See the function calling guide for more information.
- ID string
  
  The unique ID of the function tool call.
- Status string
  
  The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
  - const ResponseFunctionToolCallItemStatusInProgress ResponseFunctionToolCallItemStatus = "in_progress"
  - const ResponseFunctionToolCallItemStatusCompleted ResponseFunctionToolCallItemStatus = "completed"
  - const ResponseFunctionToolCallItemStatusIncomplete ResponseFunctionToolCallItemStatus = "incomplete"
- CreatedBy string
  
  The identifier of the actor that created the item.

Response Function Tool Call Output Item

type ResponseFunctionToolCallOutputItem struct{…}
- ID string
  
  The unique ID of the function call tool output.
- CallID string
  
  The unique ID of the function tool call generated by the model.
- Output ResponseFunctionToolCallOutputItemOutputUnion
  
  The output from the function call generated by your code. Can be a string or an list of output content.
  - string
  - type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
    
    Text, image, or file output of the function call.
    - type ResponseInputText struct{…}
      
      A text input to the model.
      - Text string
        
        The text input to the model.
      - Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
    - type ResponseInputImage struct{…}
      
      An image input to the model. Learn about image inputs.
      - Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
      - Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
      - FileID string
        
        The ID of the file to be sent to the model.
      - ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
    - type ResponseInputFile struct{…}
      
      A file input to the model.
      - Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
      - Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
      - FileData string
        
        The content of the file to be sent to the model.
      - FileID string
        
        The ID of the file to be sent to the model.
      - FileURL string
        
        The URL of the file to be sent to the model.
      - Filename string
        
        The name of the file to be sent to the model.
- Status ResponseFunctionToolCallOutputItemStatus
  
  The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
  - const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
  - const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
  - const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
- Type FunctionCallOutput
  
  The type of the function tool call output. Always function_call_output.
  - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
- CreatedBy string
  
  The identifier of the actor that created the item.

Response Function Web Search

type ResponseFunctionWebSearch struct{…}

The results of a web search tool call. See the web search guide for more information.
- ID string
  
  The unique ID of the web search tool call.
- Action ResponseFunctionWebSearchActionUnion
  
  An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
  - type ResponseFunctionWebSearchActionSearch struct{…}
    
    Action type "search" - Performs a web search query.
    - Type Search
      
      The action type.
      - const SearchSearch Search = "search"
    - Queries []string
      
      The search queries.
    - Query string
      
      The search query.
    - Sources []ResponseFunctionWebSearchActionSearchSource
      
      The sources used in the search.
      - Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
      - URL string
        
        The URL of the source.
  - type ResponseFunctionWebSearchActionOpenPage struct{…}
    
    Action type "open_page" - Opens a specific URL from search results.
    - Type OpenPage
      
      The action type.
      - const OpenPageOpenPage OpenPage = "open_page"
    - URL string
      
      The URL opened by the model.
  - type ResponseFunctionWebSearchActionFindInPage struct{…}
    
    Action type "find_in_page": Searches for a pattern within a loaded page.
    - Pattern string
      
      The pattern or text to search for within the page.
    - Type FindInPage
      
      The action type.
      - const FindInPageFindInPage FindInPage = "find_in_page"
    - URL string
      
      The URL of the page searched for the pattern.
- Status ResponseFunctionWebSearchStatus
  
  The status of the web search tool call.
  - const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
  - const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
  - const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
  - const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
- Type WebSearchCall
  
  The type of the web search tool call. Always web_search_call.
  - const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"

Response Image Gen Call Completed Event

type ResponseImageGenCallCompletedEvent struct{…}

Emitted when an image generation tool call has completed and the final image is available.
- ItemID string
  
  The unique identifier of the image generation item being processed.
- OutputIndex int64
  
  The index of the output item in the response's output array.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseImageGenerationCallCompleted
  
  The type of the event. Always 'response.image_generation_call.completed'.
  - const ResponseImageGenerationCallCompletedResponseImageGenerationCallCompleted ResponseImageGenerationCallCompleted = "response.image_generation_call.completed"

Response Image Gen Call Generating Event

type ResponseImageGenCallGeneratingEvent struct{…}

Emitted when an image generation tool call is actively generating an image (intermediate state).
- ItemID string
  
  The unique identifier of the image generation item being processed.
- OutputIndex int64
  
  The index of the output item in the response's output array.
- SequenceNumber int64
  
  The sequence number of the image generation item being processed.
- Type ResponseImageGenerationCallGenerating
  
  The type of the event. Always 'response.image_generation_call.generating'.
  - const ResponseImageGenerationCallGeneratingResponseImageGenerationCallGenerating ResponseImageGenerationCallGenerating = "response.image_generation_call.generating"

Response Image Gen Call In Progress Event

type ResponseImageGenCallInProgressEvent struct{…}

Emitted when an image generation tool call is in progress.
- ItemID string
  
  The unique identifier of the image generation item being processed.
- OutputIndex int64
  
  The index of the output item in the response's output array.
- SequenceNumber int64
  
  The sequence number of the image generation item being processed.
- Type ResponseImageGenerationCallInProgress
  
  The type of the event. Always 'response.image_generation_call.in_progress'.
  - const ResponseImageGenerationCallInProgressResponseImageGenerationCallInProgress ResponseImageGenerationCallInProgress = "response.image_generation_call.in_progress"

Response Image Gen Call Partial Image Event

type ResponseImageGenCallPartialImageEvent struct{…}

Emitted when a partial image is available during image generation streaming.
- ItemID string
  
  The unique identifier of the image generation item being processed.
- OutputIndex int64
  
  The index of the output item in the response's output array.
- PartialImageB64 string
  
  Base64-encoded partial image data, suitable for rendering as an image.
- PartialImageIndex int64
  
  0-based index for the partial image (backend is 1-based, but this is 0-based for the user).
- SequenceNumber int64
  
  The sequence number of the image generation item being processed.
- Type ResponseImageGenerationCallPartialImage
  
  The type of the event. Always 'response.image_generation_call.partial_image'.
  - const ResponseImageGenerationCallPartialImageResponseImageGenerationCallPartialImage ResponseImageGenerationCallPartialImage = "response.image_generation_call.partial_image"

Response In Progress Event

type ResponseInProgressEvent struct{…}

Emitted when the response is in progress.
- Response Response
  
  The response that is in progress.
  - ID string
    
    Unique identifier for this Response.
  - CreatedAt float64
    
    Unix timestamp (in seconds) of when this Response was created.
  - Error ResponseError
    
    An error object returned when the model fails to generate a Response.
    - Code ResponseErrorCode
      
      The error code for the response.
      - const ResponseErrorCodeServerError ResponseErrorCode = "server_error"
      - const ResponseErrorCodeRateLimitExceeded ResponseErrorCode = "rate_limit_exceeded"
      - const ResponseErrorCodeInvalidPrompt ResponseErrorCode = "invalid_prompt"
      - const ResponseErrorCodeVectorStoreTimeout ResponseErrorCode = "vector_store_timeout"
      - const ResponseErrorCodeInvalidImage ResponseErrorCode = "invalid_image"
      - const ResponseErrorCodeInvalidImageFormat ResponseErrorCode = "invalid_image_format"
      - const ResponseErrorCodeInvalidBase64Image ResponseErrorCode = "invalid_base64_image"
      - const ResponseErrorCodeInvalidImageURL ResponseErrorCode = "invalid_image_url"
      - const ResponseErrorCodeImageTooLarge ResponseErrorCode = "image_too_large"
      - const ResponseErrorCodeImageTooSmall ResponseErrorCode = "image_too_small"
      - const ResponseErrorCodeImageParseError ResponseErrorCode = "image_parse_error"
      - const ResponseErrorCodeImageContentPolicyViolation ResponseErrorCode = "image_content_policy_violation"
      - const ResponseErrorCodeInvalidImageMode ResponseErrorCode = "invalid_image_mode"
      - const ResponseErrorCodeImageFileTooLarge ResponseErrorCode = "image_file_too_large"
      - const ResponseErrorCodeUnsupportedImageMediaType ResponseErrorCode = "unsupported_image_media_type"
      - const ResponseErrorCodeEmptyImageFile ResponseErrorCode = "empty_image_file"
      - const ResponseErrorCodeFailedToDownloadImage ResponseErrorCode = "failed_to_download_image"
      - const ResponseErrorCodeImageFileNotFound ResponseErrorCode = "image_file_not_found"
    - Message string
      
      A human-readable description of the error.
  - IncompleteDetails ResponseIncompleteDetails
    
    Details about why the response is incomplete.
    - Reason string
      
      The reason why the response is incomplete.
      - const ResponseIncompleteDetailsReasonMaxOutputTokens ResponseIncompleteDetailsReason = "max_output_tokens"
      - const ResponseIncompleteDetailsReasonContentFilter ResponseIncompleteDetailsReason = "content_filter"
  - Instructions ResponseInstructionsUnion
    
    A system (or developer) message inserted into the model's context.
    
    When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
    - string
    - type ResponseInstructionsInputItemList []ResponseInputItemUnion
      
      A list of one or many input items to the model, containing different content types.
      - type EasyInputMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
        
        Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
        
        Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
        
        Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
      - type ResponseInputItemMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
        
        Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
        
        Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
        
        Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
        
        Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
      - type ResponseOutputMessage struct{…}
        
        An output message from the model.
        
        ID string
        
        The unique ID of the output message.
        
        Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
        
        Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
        
        Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
        
        Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
        
        Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
      - type ResponseFileSearchToolCall struct{…}
        
        The results of a file search tool call. See the file search guide for more information.
        
        ID string
        
        The unique ID of the file search tool call.
        
        Queries []string
        
        The queries used to search for files.
        
        Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
        
        Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
        
        Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
      - type ResponseComputerToolCall struct{…}
        
        A tool call to a computer use tool. See the computer use guide for more information.
        
        ID string
        
        The unique ID of the computer call.
        
        CallID string
        
        An identifier used when responding to the tool call with output.
        
        PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
        
        Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
        
        Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
        
        Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
      - type ResponseInputItemComputerCallOutput struct{…}
        
        The output of a computer tool call.
        
        CallID string
        
        The ID of the computer tool call that produced the output.
        
        Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
        
        Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
        
        ID string
        
        The ID of the computer tool call output.
        
        AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
      - type ResponseFunctionWebSearch struct{…}
        
        The results of a web search tool call. See the web search guide for more information.
        
        ID string
        
        The unique ID of the web search tool call.
        
        Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
        
        Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
        
        Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
      - type ResponseFunctionToolCall struct{…}
        
        A tool call to run a function. See the function calling guide for more information.
        
        Arguments string
        
        A JSON string of the arguments to pass to the function.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Name string
        
        The name of the function to run.
        
        Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
        
        ID string
        
        The unique ID of the function tool call.
        
        Namespace string
        
        The namespace of the function to run.
        
        Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
      - type ResponseInputItemFunctionCallOutput struct{…}
        
        The output of a function tool call.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
        
        ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
      - type ResponseInputItemToolSearchCall struct{…}
        
        Arguments any
        
        The arguments supplied to the tool search call.
        
        Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
        
        ID string
        
        The unique ID of this tool search call.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
        
        Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
      - type ResponseToolSearchOutputItemParamResp struct{…}
        
        Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
        
        Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
        
        ID string
        
        The unique ID of this tool search output.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
        
        Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
      - type ResponseInputItemAdditionalTools struct{…}
        
        Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
        
        Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
        
        ID string
        
        The unique ID of this additional tools item.
      - type ResponseReasoningItem struct{…}
        
        A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
        
        ID string
        
        The unique identifier of the reasoning content.
        
        Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
        
        Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
        
        Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
        
        EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
        
        Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
      - type ResponseCompactionItemParamResp struct{…}
        
        A compaction item generated by the v1/responses/compact API.
        
        EncryptedContent string
        
        The encrypted content of the compaction summary.
        
        Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
        
        ID string
        
        The ID of the compaction item.
      - type ResponseInputItemImageGenerationCall struct{…}
        
        An image generation request made by the model.
        
        ID string
        
        The unique ID of the image generation call.
        
        Result string
        
        The generated image encoded in base64.
        
        Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
        
        Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
      - type ResponseCodeInterpreterToolCall struct{…}
        
        A tool call to run code.
        
        ID string
        
        The unique ID of the code interpreter tool call.
        
        Code string
        
        The code to run, or null if not available.
        
        ContainerID string
        
        The ID of the container used to run the code.
        
        Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
        
        Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
        
        Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
      - type ResponseInputItemLocalShellCall struct{…}
        
        A tool call to run a command on the local shell.
        
        ID string
        
        The unique ID of the local shell call.
        
        Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
        
        CallID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
        
        Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
      - type ResponseInputItemLocalShellCallOutput struct{…}
        
        The output of a local shell tool call.
        
        ID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Output string
        
        A JSON string of the output of the local shell tool call.
        
        Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
      - type ResponseInputItemShellCall struct{…}
        
        A tool representing a request to execute one or more shell commands.
        
        Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
        
        ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
        
        Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
        
        Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
      - type ResponseInputItemShellCallOutput struct{…}
        
        The streamed output items emitted by a shell tool call.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
        
        Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
        
        ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
        
        MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
        
        Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
      - type ResponseInputItemApplyPatchCall struct{…}
        
        A tool call representing a request to create, delete, or update files using diff patches.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
        
        Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
        
        Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
        
        ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
      - type ResponseInputItemApplyPatchCallOutput struct{…}
        
        The streamed output emitted by an apply patch tool call.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
        
        Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
        
        ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
        
        Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
      - type ResponseInputItemMcpListTools struct{…}
        
        A list of tools available on an MCP server.
        
        ID string
        
        The unique ID of the list.
        
        ServerLabel string
        
        The label of the MCP server.
        
        Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
        
        Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
        
        Error string
        
        Error message if the server could not list tools.
      - type ResponseInputItemMcpApprovalRequest struct{…}
        
        A request for human approval of a tool invocation.
        
        ID string
        
        The unique ID of the approval request.
        
        Arguments string
        
        A JSON string of arguments for the tool.
        
        Name string
        
        The name of the tool to run.
        
        ServerLabel string
        
        The label of the MCP server making the request.
        
        Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
      - type ResponseInputItemMcpApprovalResponse struct{…}
        
        A response to an MCP approval request.
        
        ApprovalRequestID string
        
        The ID of the approval request being answered.
        
        Approve bool
        
        Whether the request was approved.
        
        Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
        
        ID string
        
        The unique ID of the approval response
        
        Reason string
        
        Optional reason for the decision.
      - type ResponseInputItemMcpCall struct{…}
        
        An invocation of a tool on an MCP server.
        
        ID string
        
        The unique ID of the tool call.
        
        Arguments string
        
        A JSON string of the arguments passed to the tool.
        
        Name string
        
        The name of the tool that was run.
        
        ServerLabel string
        
        The label of the MCP server running the tool.
        
        Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
        
        ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
        
        Error string
        
        The error from the tool call, if any.
        
        Output string
        
        The output from the tool call.
        
        Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
      - type ResponseCustomToolCallOutput struct{…}
        
        The output of a custom tool call from your code, being sent back to the model.
        
        CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
        
        Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
        
        ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
      - type ResponseCustomToolCall struct{…}
        
        A call to a custom tool created by the model.
        
        CallID string
        
        An identifier used to map this custom tool call to a tool call output.
        
        Input string
        
        The input for the custom tool call generated by the model.
        
        Name string
        
        The name of the custom tool being called.
        
        Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
        
        ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
        
        Namespace string
        
        The namespace of the custom tool being called.
      - type ResponseInputItemCompactionTrigger struct{…}
        
        Compacts the current context. Must be the final input item.
        
        Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
      - type ResponseInputItemItemReference struct{…}
        
        An internal identifier for an item to reference.
        
        ID string
        
        The ID of the item to reference.
        
        Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
  - Metadata Metadata
    
    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
    
    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
  - Model ResponsesModel
    
    Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
    - string
    - type ChatModel string
      - const ChatModelGPT5_4 ChatModel = "gpt-5.4"
      - const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"
      - const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"
      - const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"
      - const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"
      - const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"
      - const ChatModelGPT5_2 ChatModel = "gpt-5.2"
      - const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"
      - const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"
      - const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"
      - const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"
      - const ChatModelGPT5_1 ChatModel = "gpt-5.1"
      - const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"
      - const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"
      - const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"
      - const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"
      - const ChatModelGPT5 ChatModel = "gpt-5"
      - const ChatModelGPT5Mini ChatModel = "gpt-5-mini"
      - const ChatModelGPT5Nano ChatModel = "gpt-5-nano"
      - const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"
      - const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"
      - const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"
      - const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"
      - const ChatModelGPT4_1 ChatModel = "gpt-4.1"
      - const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"
      - const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"
      - const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"
      - const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"
      - const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"
      - const ChatModelO4Mini ChatModel = "o4-mini"
      - const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"
      - const ChatModelO3 ChatModel = "o3"
      - const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"
      - const ChatModelO3Mini ChatModel = "o3-mini"
      - const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"
      - const ChatModelO1 ChatModel = "o1"
      - const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"
      - const ChatModelO1Preview ChatModel = "o1-preview"
      - const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"
      - const ChatModelO1Mini ChatModel = "o1-mini"
      - const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"
      - const ChatModelGPT4o ChatModel = "gpt-4o"
      - const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"
      - const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"
      - const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"
      - const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"
      - const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"
      - const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"
      - const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"
      - const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"
      - const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"
      - const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"
      - const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"
      - const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"
      - const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"
      - const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"
      - const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"
      - const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"
      - const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"
      - const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"
      - const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"
      - const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"
      - const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"
      - const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"
      - const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"
      - const ChatModelGPT4 ChatModel = "gpt-4"
      - const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"
      - const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"
      - const ChatModelGPT4_32k ChatModel = "gpt-4-32k"
      - const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"
      - const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"
      - const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"
      - const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"
      - const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"
      - const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"
      - const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"
      - const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"
      - const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"
    - type ResponsesModel string
      - const ResponsesModelO1Pro ResponsesModel = "o1-pro"
      - const ResponsesModelO1Pro2025_03_19 ResponsesModel = "o1-pro-2025-03-19"
      - const ResponsesModelO3Pro ResponsesModel = "o3-pro"
      - const ResponsesModelO3Pro2025_06_10 ResponsesModel = "o3-pro-2025-06-10"
      - const ResponsesModelO3DeepResearch ResponsesModel = "o3-deep-research"
      - const ResponsesModelO3DeepResearch2025_06_26 ResponsesModel = "o3-deep-research-2025-06-26"
      - const ResponsesModelO4MiniDeepResearch ResponsesModel = "o4-mini-deep-research"
      - const ResponsesModelO4MiniDeepResearch2025_06_26 ResponsesModel = "o4-mini-deep-research-2025-06-26"
      - const ResponsesModelComputerUsePreview ResponsesModel = "computer-use-preview"
      - const ResponsesModelComputerUsePreview2025_03_11 ResponsesModel = "computer-use-preview-2025-03-11"
      - const ResponsesModelGPT5Codex ResponsesModel = "gpt-5-codex"
      - const ResponsesModelGPT5Pro ResponsesModel = "gpt-5-pro"
      - const ResponsesModelGPT5Pro2025_10_06 ResponsesModel = "gpt-5-pro-2025-10-06"
      - const ResponsesModelGPT5_1CodexMax ResponsesModel = "gpt-5.1-codex-max"
  - Object Response
    
    The object type of this resource - always set to response.
    - const ResponseResponse Response = "response"
  - Output []ResponseOutputItemUnion
    
    An array of content items generated by the model.
    - The length and order of items in the output array is dependent on the model's response.
    - Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
    - type ResponseFunctionToolCallOutputItem struct{…}
      - ID string
        
        The unique ID of the function call tool output.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Output ResponseFunctionToolCallOutputItemOutputUnion
        
        The output from the function call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Status ResponseFunctionToolCallOutputItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
        
        const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
        
        const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
      - Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
    - type ResponseComputerToolCallOutputItem struct{…}
      - ID string
        
        The unique ID of the computer call tool output.
      - CallID string
        
        The ID of the computer tool call that produced the output.
      - Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
      - Status ResponseComputerToolCallOutputItemStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
        
        const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
        
        const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
        
        const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
      - Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
      - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
    - type ResponseToolSearchCall struct{…}
      - ID string
        
        The unique ID of the tool search call item.
      - Arguments any
        
        Arguments used for the tool search call.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchCallExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
        
        const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
      - Status ResponseToolSearchCallStatus
        
        The status of the tool search call item that was recorded.
        
        const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
        
        const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
        
        const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
      - Type ToolSearchCall
        
        The type of the item. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseToolSearchOutputItem struct{…}
      - ID string
        
        The unique ID of the tool search output item.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchOutputItemExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
        
        const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
      - Status ResponseToolSearchOutputItemStatus
        
        The status of the tool search output item that was recorded.
        
        const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
        
        const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
        
        const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
      - Tools []ToolUnion
        
        The loaded tool definitions returned by tool search.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type ToolSearchOutput
        
        The type of the item. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseOutputItemAdditionalTools struct{…}
      - ID string
        
        The unique ID of the additional tools item.
      - Role string
        
        The role that provided the additional tools.
        
        const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
        
        const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
        
        const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
        
        const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
        
        const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
        
        const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
        
        const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
        
        const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
      - Tools []ToolUnion
        
        The additional tool definitions made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type AdditionalTools
        
        The type of the item. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
    - type ResponseCompactionItem struct{…}
      
      A compaction item generated by the v1/responses/compact API.
      - ID string
        
        The unique ID of the compaction item.
      - EncryptedContent string
        
        The encrypted content that was produced by compaction.
      - Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseOutputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
      - ID string
        
        The unique ID of the image generation call.
      - Result string
        
        The generated image encoded in base64.
      - Status string
        
        The status of the image generation call.
        
        const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
        
        const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
        
        const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
      - Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
    - type ResponseOutputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
      - ID string
        
        The unique ID of the local shell call.
      - Action ResponseOutputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
      - CallID string
        
        The unique ID of the local shell tool call generated by the model.
      - Status string
        
        The status of the local shell call.
        
        const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
        
        const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
      - Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
    - type ResponseOutputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
      - ID string
        
        The unique ID of the local shell tool call generated by the model.
      - Output string
        
        A JSON string of the output of the local shell tool call.
      - Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
    - type ResponseFunctionShellToolCall struct{…}
      
      A tool call that executes one or more shell commands in a managed environment.
      - ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
      - Action ResponseFunctionShellToolCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Environment ResponseFunctionShellToolCallEnvironmentUnion
        
        Represents the use of a local environment to perform shell actions.
        
        type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
        
        type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
      - Status ResponseFunctionShellToolCallStatus
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
        
        const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
        
        const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
      - Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
      - CreatedBy string
        
        The ID of the entity that created this tool call.
    - type ResponseFunctionShellToolCallOutput struct{…}
      
      The output of a shell tool call that was emitted.
      - ID string
        
        The unique ID of the shell call output. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - MaxOutputLength int64
        
        The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
      - Output []ResponseFunctionShellToolCallOutputOutput
        
        An array of shell call output contents
        
        Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        The standard error output that was captured.
        
        Stdout string
        
        The standard output that was captured.
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - Status ResponseFunctionShellToolCallOutputStatus
        
        The status of the shell call output. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
        
        const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
        
        const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
      - Type ShellCallOutput
        
        The type of the shell call output. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseApplyPatchToolCall struct{…}
      
      A tool call that applies file diffs by creating, deleting, or updating files.
      - ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Operation ResponseApplyPatchToolCallOperationUnion
        
        One of the create_file, delete_file, or update_file operations applied via apply_patch.
        
        type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
      - Status ResponseApplyPatchToolCallStatus
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
        
        const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
      - Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
      - CreatedBy string
        
        The ID of the entity that created this tool call.
    - type ResponseApplyPatchToolCallOutput struct{…}
      
      The output emitted by an apply patch tool call.
      - ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Status ResponseApplyPatchToolCallOutputStatus
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
        
        const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
      - Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
      - CreatedBy string
        
        The ID of the entity that created this tool call output.
      - Output string
        
        Optional textual output returned by the apply patch tool.
    - type ResponseOutputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
      - ID string
        
        The unique ID of the tool call.
      - Arguments string
        
        A JSON string of the arguments passed to the tool.
      - Name string
        
        The name of the tool that was run.
      - ServerLabel string
        
        The label of the MCP server running the tool.
      - Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
      - ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
      - Error string
        
        The error from the tool call, if any.
      - Output string
        
        The output from the tool call.
      - Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
        
        const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
        
        const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
        
        const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
        
        const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
    - type ResponseOutputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
      - ID string
        
        The unique ID of the list.
      - ServerLabel string
        
        The label of the MCP server.
      - Tools []ResponseOutputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
      - Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
      - Error string
        
        Error message if the server could not list tools.
    - type ResponseOutputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
      - ID string
        
        The unique ID of the approval request.
      - Arguments string
        
        A JSON string of arguments for the tool.
      - Name string
        
        The name of the tool to run.
      - ServerLabel string
        
        The label of the MCP server making the request.
      - Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
    - type ResponseOutputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
      - ID string
        
        The unique ID of the approval response
      - ApprovalRequestID string
        
        The ID of the approval request being answered.
      - Approve bool
        
        Whether the request was approved.
      - Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
      - Reason string
        
        Optional reason for the decision.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
    - type ResponseCustomToolCallOutputItem struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
      - ID string
        
        The unique ID of the custom tool call output item.
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
        
        const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
        
        const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
      - CreatedBy string
        
        The identifier of the actor that created the item.
  - ParallelToolCalls bool
    
    Whether to allow the model to run tool calls in parallel.
  - Temperature float64
    
    What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
  - ToolChoice ResponseToolChoiceUnion
    
    How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.
    - type ToolChoiceOptions string
      
      Controls which (if any) tool is called by the model.
      
      none means the model will not call any tool and instead generates a message.
      
      auto means the model can pick between generating a message or calling one or more tools.
      
      required means the model must call one or more tools.
      - const ToolChoiceOptionsNone ToolChoiceOptions = "none"
      - const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
      - const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
    - type ToolChoiceAllowed struct{…}
      
      Constrains the tools available to the model to a pre-defined set.
      - Mode ToolChoiceAllowedMode
        
        Constrains the tools available to the model to a pre-defined set.
        
        auto allows the model to pick from among the allowed tools and generate a message.
        
        required requires the model to call one or more of the allowed tools.
        
        const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
        
        const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
      - Tools []map[string, any]
        
        A list of tool definitions that the model should be allowed to call.
        
        For the Responses API, the list of tool definitions might look like:
        
        [ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ]
      - Type AllowedTools
        
        Allowed tool configuration type. Always allowed_tools.
        
        const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
    - type ToolChoiceTypes struct{…}
      
      Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
      - Type ToolChoiceTypesType
        
        The type of hosted tool the model should to use. Learn more about built-in tools.
        
        Allowed values are:
        
        file_search
        
        web_search_preview
        
        computer
        
        computer_use_preview
        
        computer_use
        
        code_interpreter
        
        image_generation
        
        const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
        
        const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
        
        const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
        
        const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
        
        const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
        
        const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
        
        const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
        
        const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
    - type ToolChoiceFunction struct{…}
      
      Use this option to force the model to call a specific function.
      - Name string
        
        The name of the function to call.
      - Type Function
        
        For function calling, the type is always function.
        
        const FunctionFunction Function = "function"
    - type ToolChoiceMcp struct{…}
      
      Use this option to force the model to call a specific tool on a remote MCP server.
      - ServerLabel string
        
        The label of the MCP server to use.
      - Type Mcp
        
        For MCP tools, the type is always mcp.
        
        const McpMcp Mcp = "mcp"
      - Name string
        
        The name of the tool to call on the server.
    - type ToolChoiceCustom struct{…}
      
      Use this option to force the model to call a specific custom tool.
      - Name string
        
        The name of the custom tool to call.
      - Type Custom
        
        For custom tool calling, the type is always custom.
        
        const CustomCustom Custom = "custom"
    - type ToolChoiceApplyPatch struct{…}
      
      Forces the model to call the apply_patch tool when executing a tool call.
      - Type ApplyPatch
        
        The tool to call. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
    - type ToolChoiceShell struct{…}
      
      Forces the model to call the shell tool when a tool call is required.
      - Type Shell
        
        The tool to call. Always shell.
        
        const ShellShell Shell = "shell"
  - Tools []ToolUnion
    
    An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
    
    We support the following categories of tools:
    - Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
    - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
    - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
  - TopP float64
    
    An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
    
    We generally recommend altering this or temperature but not both.
  - Background bool
    
    Whether to run the model response in the background. Learn more.
  - CompletedAt float64
    
    Unix timestamp (in seconds) of when this Response was completed. Only present when the status is completed.
  - Conversation ResponseConversation
    
    The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
    - ID string
      
      The unique ID of the conversation that this response was associated with.
  - MaxOutputTokens int64
    
    An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
  - MaxToolCalls int64
    
    The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
  - Moderation ResponseModeration
    
    Moderation results for the response input and output, if moderated completions were requested.
    - Input ResponseModerationInputUnion
      
      Moderation for the response input.
      - type ResponseModerationInputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeText ResponseModerationInputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeImage ResponseModerationInputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
      - type ResponseModerationInputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
    - Output ResponseModerationOutputUnion
      
      Moderation for the response output.
      - type ResponseModerationOutputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeText ResponseModerationOutputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeImage ResponseModerationOutputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
      - type ResponseModerationOutputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
  - PreviousResponseID string
    
    The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
  - Prompt ResponsePrompt
    
    Reference to a prompt template and its variables. Learn more.
    - ID string
      
      The unique identifier of the prompt template to use.
    - Variables map[string, ResponsePromptVariableUnion]
      
      Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
      - string
      - type ResponseInputText struct{…}
        
        A text input to the model.
      - type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
      - type ResponseInputFile struct{…}
        
        A file input to the model.
    - Version string
      
      Optional version of the prompt template.
  - PromptCacheKey string
    
    Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
  - PromptCacheRetention ResponsePromptCacheRetention
    
    The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.
    
    For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:
    - Organizations without ZDR enabled default to 24h.
    - Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.
    - const ResponsePromptCacheRetentionInMemory ResponsePromptCacheRetention = "in_memory"
    - const ResponsePromptCacheRetention24h ResponsePromptCacheRetention = "24h"
  - Reasoning Reasoning
    
    gpt-5 and o-series models only
    
    Configuration options for reasoning models.
    - Context ReasoningContext
      
      Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
      - const ReasoningContextAuto ReasoningContext = "auto"
      - const ReasoningContextCurrentTurn ReasoningContext = "current_turn"
      - const ReasoningContextAllTurns ReasoningContext = "all_turns"
    - Effort ReasoningEffort
      
      Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
      - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
      - All models before gpt-5.1 default to medium reasoning effort, and do not support none.
      - The gpt-5-pro model defaults to (and only supports) high reasoning effort.
      - xhigh is supported for all models after gpt-5.1-codex-max.
      - const ReasoningEffortNone ReasoningEffort = "none"
      - const ReasoningEffortMinimal ReasoningEffort = "minimal"
      - const ReasoningEffortLow ReasoningEffort = "low"
      - const ReasoningEffortMedium ReasoningEffort = "medium"
      - const ReasoningEffortHigh ReasoningEffort = "high"
      - const ReasoningEffortXhigh ReasoningEffort = "xhigh"
    - GenerateSummary ReasoningGenerateSummary
      
      Deprecated: use summary instead.
      
      A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
      - const ReasoningGenerateSummaryAuto ReasoningGenerateSummary = "auto"
      - const ReasoningGenerateSummaryConcise ReasoningGenerateSummary = "concise"
      - const ReasoningGenerateSummaryDetailed ReasoningGenerateSummary = "detailed"
    - Summary ReasoningSummary
      
      A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
      
      concise is supported for computer-use-preview models and all reasoning models after gpt-5.
      - const ReasoningSummaryAuto ReasoningSummary = "auto"
      - const ReasoningSummaryConcise ReasoningSummary = "concise"
      - const ReasoningSummaryDetailed ReasoningSummary = "detailed"
  - SafetyIdentifier string
    
    A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
  - ServiceTier ResponseServiceTier
    
    Specifies the processing type used for serving the request.
    - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
    - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
    - If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
    - When not set, the default behavior is 'auto'.
    When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
    - const ResponseServiceTierAuto ResponseServiceTier = "auto"
    - const ResponseServiceTierDefault ResponseServiceTier = "default"
    - const ResponseServiceTierFlex ResponseServiceTier = "flex"
    - const ResponseServiceTierScale ResponseServiceTier = "scale"
    - const ResponseServiceTierPriority ResponseServiceTier = "priority"
  - Status ResponseStatus
    
    The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
    - const ResponseStatusCompleted ResponseStatus = "completed"
    - const ResponseStatusFailed ResponseStatus = "failed"
    - const ResponseStatusInProgress ResponseStatus = "in_progress"
    - const ResponseStatusCancelled ResponseStatus = "cancelled"
    - const ResponseStatusQueued ResponseStatus = "queued"
    - const ResponseStatusIncomplete ResponseStatus = "incomplete"
  - Text ResponseTextConfig
    
    Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
    - Text inputs and outputs
    - Structured Outputs
    - Format ResponseFormatTextConfigUnion
      
      An object specifying the format that the model must output.
      
      Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
      
      The default format is { "type": "text" } with no additional options.
      
      Not recommended for gpt-4o and newer models:
      
      Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
      - type ResponseFormatText struct{…}
        
        Default response format. Used to generate text responses.
        
        Type Text
        
        The type of response format being defined. Always text.
        
        const TextText Text = "text"
      - type ResponseFormatTextJSONSchemaConfig struct{…}
        
        JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
        
        Name string
        
        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
        
        Schema map[string, any]
        
        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
        
        Type JSONSchema
        
        The type of response format being defined. Always json_schema.
        
        const JSONSchemaJSONSchema JSONSchema = "json_schema"
        
        Description string
        
        A description of what the response format is for, used by the model to determine how to respond in the format.
        
        Strict bool
        
        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
      - type ResponseFormatJSONObject struct{…}
        
        JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
        
        Type JSONObject
        
        The type of response format being defined. Always json_object.
        
        const JSONObjectJSONObject JSONObject = "json_object"
    - Verbosity ResponseTextConfigVerbosity
      
      Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
      - const ResponseTextConfigVerbosityLow ResponseTextConfigVerbosity = "low"
      - const ResponseTextConfigVerbosityMedium ResponseTextConfigVerbosity = "medium"
      - const ResponseTextConfigVerbosityHigh ResponseTextConfigVerbosity = "high"
  - TopLogprobs int64
    
    An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
  - Truncation ResponseTruncation
    
    The truncation strategy to use for the model response.
    - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
    - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
    - const ResponseTruncationAuto ResponseTruncation = "auto"
    - const ResponseTruncationDisabled ResponseTruncation = "disabled"
  - Usage ResponseUsage
    
    Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
    - InputTokens int64
      
      The number of input tokens.
    - InputTokensDetails ResponseUsageInputTokensDetails
      
      A detailed breakdown of the input tokens.
      - CachedTokens int64
        
        The number of tokens that were retrieved from the cache. More on prompt caching.
    - OutputTokens int64
      
      The number of output tokens.
    - OutputTokensDetails ResponseUsageOutputTokensDetails
      
      A detailed breakdown of the output tokens.
      - ReasoningTokens int64
        
        The number of reasoning tokens.
    - TotalTokens int64
      
      The total number of tokens used.
  - User string
    
    This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseInProgress
  
  The type of the event. Always response.in_progress.
  - const ResponseInProgressResponseInProgress ResponseInProgress = "response.in_progress"

Response Includable

type ResponseIncludable string

Specify additional output data to include in the model response. Currently supported values are:
- web_search_call.results: Include the search results of the web search tool call.
- web_search_call.action.sources: Include the sources of the web search tool call.
- code_interpreter_call.outputs: Includes the outputs of python code execution in code interpreter tool call items.
- computer_call_output.output.image_url: Include image urls from the computer call output.
- file_search_call.results: Include the search results of the file search tool call.
- message.input_image.image_url: Include image urls from the input message.
- message.output_text.logprobs: Include logprobs with assistant messages.
- reasoning.encrypted_content: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the store parameter is set to false, or when an organization is enrolled in the zero data retention program).
- const ResponseIncludableFileSearchCallResults ResponseIncludable = "file_search_call.results"
- const ResponseIncludableWebSearchCallResults ResponseIncludable = "web_search_call.results"
- const ResponseIncludableWebSearchCallActionSources ResponseIncludable = "web_search_call.action.sources"
- const ResponseIncludableMessageInputImageImageURL ResponseIncludable = "message.input_image.image_url"
- const ResponseIncludableComputerCallOutputOutputImageURL ResponseIncludable = "computer_call_output.output.image_url"
- const ResponseIncludableCodeInterpreterCallOutputs ResponseIncludable = "code_interpreter_call.outputs"
- const ResponseIncludableReasoningEncryptedContent ResponseIncludable = "reasoning.encrypted_content"
- const ResponseIncludableMessageOutputTextLogprobs ResponseIncludable = "message.output_text.logprobs"

Response Incomplete Event

type ResponseIncompleteEvent struct{…}

An event that is emitted when a response finishes as incomplete.
- Response Response
  
  The response that was incomplete.
  - ID string
    
    Unique identifier for this Response.
  - CreatedAt float64
    
    Unix timestamp (in seconds) of when this Response was created.
  - Error ResponseError
    
    An error object returned when the model fails to generate a Response.
    - Code ResponseErrorCode
      
      The error code for the response.
      - const ResponseErrorCodeServerError ResponseErrorCode = "server_error"
      - const ResponseErrorCodeRateLimitExceeded ResponseErrorCode = "rate_limit_exceeded"
      - const ResponseErrorCodeInvalidPrompt ResponseErrorCode = "invalid_prompt"
      - const ResponseErrorCodeVectorStoreTimeout ResponseErrorCode = "vector_store_timeout"
      - const ResponseErrorCodeInvalidImage ResponseErrorCode = "invalid_image"
      - const ResponseErrorCodeInvalidImageFormat ResponseErrorCode = "invalid_image_format"
      - const ResponseErrorCodeInvalidBase64Image ResponseErrorCode = "invalid_base64_image"
      - const ResponseErrorCodeInvalidImageURL ResponseErrorCode = "invalid_image_url"
      - const ResponseErrorCodeImageTooLarge ResponseErrorCode = "image_too_large"
      - const ResponseErrorCodeImageTooSmall ResponseErrorCode = "image_too_small"
      - const ResponseErrorCodeImageParseError ResponseErrorCode = "image_parse_error"
      - const ResponseErrorCodeImageContentPolicyViolation ResponseErrorCode = "image_content_policy_violation"
      - const ResponseErrorCodeInvalidImageMode ResponseErrorCode = "invalid_image_mode"
      - const ResponseErrorCodeImageFileTooLarge ResponseErrorCode = "image_file_too_large"
      - const ResponseErrorCodeUnsupportedImageMediaType ResponseErrorCode = "unsupported_image_media_type"
      - const ResponseErrorCodeEmptyImageFile ResponseErrorCode = "empty_image_file"
      - const ResponseErrorCodeFailedToDownloadImage ResponseErrorCode = "failed_to_download_image"
      - const ResponseErrorCodeImageFileNotFound ResponseErrorCode = "image_file_not_found"
    - Message string
      
      A human-readable description of the error.
  - IncompleteDetails ResponseIncompleteDetails
    
    Details about why the response is incomplete.
    - Reason string
      
      The reason why the response is incomplete.
      - const ResponseIncompleteDetailsReasonMaxOutputTokens ResponseIncompleteDetailsReason = "max_output_tokens"
      - const ResponseIncompleteDetailsReasonContentFilter ResponseIncompleteDetailsReason = "content_filter"
  - Instructions ResponseInstructionsUnion
    
    A system (or developer) message inserted into the model's context.
    
    When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
    - string
    - type ResponseInstructionsInputItemList []ResponseInputItemUnion
      
      A list of one or many input items to the model, containing different content types.
      - type EasyInputMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
        
        Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
        
        Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
        
        Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
      - type ResponseInputItemMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
        
        Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
        
        Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
        
        Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
        
        Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
      - type ResponseOutputMessage struct{…}
        
        An output message from the model.
        
        ID string
        
        The unique ID of the output message.
        
        Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
        
        Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
        
        Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
        
        Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
        
        Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
      - type ResponseFileSearchToolCall struct{…}
        
        The results of a file search tool call. See the file search guide for more information.
        
        ID string
        
        The unique ID of the file search tool call.
        
        Queries []string
        
        The queries used to search for files.
        
        Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
        
        Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
        
        Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
      - type ResponseComputerToolCall struct{…}
        
        A tool call to a computer use tool. See the computer use guide for more information.
        
        ID string
        
        The unique ID of the computer call.
        
        CallID string
        
        An identifier used when responding to the tool call with output.
        
        PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
        
        Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
        
        Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
        
        Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
      - type ResponseInputItemComputerCallOutput struct{…}
        
        The output of a computer tool call.
        
        CallID string
        
        The ID of the computer tool call that produced the output.
        
        Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
        
        Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
        
        ID string
        
        The ID of the computer tool call output.
        
        AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
      - type ResponseFunctionWebSearch struct{…}
        
        The results of a web search tool call. See the web search guide for more information.
        
        ID string
        
        The unique ID of the web search tool call.
        
        Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
        
        Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
        
        Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
      - type ResponseFunctionToolCall struct{…}
        
        A tool call to run a function. See the function calling guide for more information.
        
        Arguments string
        
        A JSON string of the arguments to pass to the function.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Name string
        
        The name of the function to run.
        
        Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
        
        ID string
        
        The unique ID of the function tool call.
        
        Namespace string
        
        The namespace of the function to run.
        
        Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
      - type ResponseInputItemFunctionCallOutput struct{…}
        
        The output of a function tool call.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
        
        ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
      - type ResponseInputItemToolSearchCall struct{…}
        
        Arguments any
        
        The arguments supplied to the tool search call.
        
        Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
        
        ID string
        
        The unique ID of this tool search call.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
        
        Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
      - type ResponseToolSearchOutputItemParamResp struct{…}
        
        Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
        
        Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
        
        ID string
        
        The unique ID of this tool search output.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
        
        Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
      - type ResponseInputItemAdditionalTools struct{…}
        
        Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
        
        Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
        
        ID string
        
        The unique ID of this additional tools item.
      - type ResponseReasoningItem struct{…}
        
        A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
        
        ID string
        
        The unique identifier of the reasoning content.
        
        Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
        
        Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
        
        Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
        
        EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
        
        Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
      - type ResponseCompactionItemParamResp struct{…}
        
        A compaction item generated by the v1/responses/compact API.
        
        EncryptedContent string
        
        The encrypted content of the compaction summary.
        
        Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
        
        ID string
        
        The ID of the compaction item.
      - type ResponseInputItemImageGenerationCall struct{…}
        
        An image generation request made by the model.
        
        ID string
        
        The unique ID of the image generation call.
        
        Result string
        
        The generated image encoded in base64.
        
        Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
        
        Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
      - type ResponseCodeInterpreterToolCall struct{…}
        
        A tool call to run code.
        
        ID string
        
        The unique ID of the code interpreter tool call.
        
        Code string
        
        The code to run, or null if not available.
        
        ContainerID string
        
        The ID of the container used to run the code.
        
        Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
        
        Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
        
        Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
      - type ResponseInputItemLocalShellCall struct{…}
        
        A tool call to run a command on the local shell.
        
        ID string
        
        The unique ID of the local shell call.
        
        Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
        
        CallID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
        
        Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
      - type ResponseInputItemLocalShellCallOutput struct{…}
        
        The output of a local shell tool call.
        
        ID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Output string
        
        A JSON string of the output of the local shell tool call.
        
        Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
      - type ResponseInputItemShellCall struct{…}
        
        A tool representing a request to execute one or more shell commands.
        
        Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
        
        ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
        
        Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
        
        Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
      - type ResponseInputItemShellCallOutput struct{…}
        
        The streamed output items emitted by a shell tool call.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
        
        Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
        
        ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
        
        MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
        
        Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
      - type ResponseInputItemApplyPatchCall struct{…}
        
        A tool call representing a request to create, delete, or update files using diff patches.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
        
        Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
        
        Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
        
        ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
      - type ResponseInputItemApplyPatchCallOutput struct{…}
        
        The streamed output emitted by an apply patch tool call.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
        
        Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
        
        ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
        
        Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
      - type ResponseInputItemMcpListTools struct{…}
        
        A list of tools available on an MCP server.
        
        ID string
        
        The unique ID of the list.
        
        ServerLabel string
        
        The label of the MCP server.
        
        Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
        
        Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
        
        Error string
        
        Error message if the server could not list tools.
      - type ResponseInputItemMcpApprovalRequest struct{…}
        
        A request for human approval of a tool invocation.
        
        ID string
        
        The unique ID of the approval request.
        
        Arguments string
        
        A JSON string of arguments for the tool.
        
        Name string
        
        The name of the tool to run.
        
        ServerLabel string
        
        The label of the MCP server making the request.
        
        Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
      - type ResponseInputItemMcpApprovalResponse struct{…}
        
        A response to an MCP approval request.
        
        ApprovalRequestID string
        
        The ID of the approval request being answered.
        
        Approve bool
        
        Whether the request was approved.
        
        Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
        
        ID string
        
        The unique ID of the approval response
        
        Reason string
        
        Optional reason for the decision.
      - type ResponseInputItemMcpCall struct{…}
        
        An invocation of a tool on an MCP server.
        
        ID string
        
        The unique ID of the tool call.
        
        Arguments string
        
        A JSON string of the arguments passed to the tool.
        
        Name string
        
        The name of the tool that was run.
        
        ServerLabel string
        
        The label of the MCP server running the tool.
        
        Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
        
        ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
        
        Error string
        
        The error from the tool call, if any.
        
        Output string
        
        The output from the tool call.
        
        Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
      - type ResponseCustomToolCallOutput struct{…}
        
        The output of a custom tool call from your code, being sent back to the model.
        
        CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
        
        Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
        
        ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
      - type ResponseCustomToolCall struct{…}
        
        A call to a custom tool created by the model.
        
        CallID string
        
        An identifier used to map this custom tool call to a tool call output.
        
        Input string
        
        The input for the custom tool call generated by the model.
        
        Name string
        
        The name of the custom tool being called.
        
        Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
        
        ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
        
        Namespace string
        
        The namespace of the custom tool being called.
      - type ResponseInputItemCompactionTrigger struct{…}
        
        Compacts the current context. Must be the final input item.
        
        Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
      - type ResponseInputItemItemReference struct{…}
        
        An internal identifier for an item to reference.
        
        ID string
        
        The ID of the item to reference.
        
        Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
  - Metadata Metadata
    
    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
    
    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
  - Model ResponsesModel
    
    Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
    - string
    - type ChatModel string
      - const ChatModelGPT5_4 ChatModel = "gpt-5.4"
      - const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"
      - const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"
      - const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"
      - const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"
      - const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"
      - const ChatModelGPT5_2 ChatModel = "gpt-5.2"
      - const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"
      - const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"
      - const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"
      - const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"
      - const ChatModelGPT5_1 ChatModel = "gpt-5.1"
      - const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"
      - const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"
      - const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"
      - const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"
      - const ChatModelGPT5 ChatModel = "gpt-5"
      - const ChatModelGPT5Mini ChatModel = "gpt-5-mini"
      - const ChatModelGPT5Nano ChatModel = "gpt-5-nano"
      - const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"
      - const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"
      - const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"
      - const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"
      - const ChatModelGPT4_1 ChatModel = "gpt-4.1"
      - const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"
      - const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"
      - const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"
      - const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"
      - const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"
      - const ChatModelO4Mini ChatModel = "o4-mini"
      - const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"
      - const ChatModelO3 ChatModel = "o3"
      - const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"
      - const ChatModelO3Mini ChatModel = "o3-mini"
      - const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"
      - const ChatModelO1 ChatModel = "o1"
      - const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"
      - const ChatModelO1Preview ChatModel = "o1-preview"
      - const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"
      - const ChatModelO1Mini ChatModel = "o1-mini"
      - const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"
      - const ChatModelGPT4o ChatModel = "gpt-4o"
      - const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"
      - const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"
      - const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"
      - const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"
      - const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"
      - const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"
      - const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"
      - const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"
      - const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"
      - const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"
      - const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"
      - const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"
      - const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"
      - const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"
      - const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"
      - const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"
      - const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"
      - const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"
      - const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"
      - const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"
      - const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"
      - const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"
      - const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"
      - const ChatModelGPT4 ChatModel = "gpt-4"
      - const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"
      - const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"
      - const ChatModelGPT4_32k ChatModel = "gpt-4-32k"
      - const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"
      - const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"
      - const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"
      - const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"
      - const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"
      - const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"
      - const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"
      - const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"
      - const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"
    - type ResponsesModel string
      - const ResponsesModelO1Pro ResponsesModel = "o1-pro"
      - const ResponsesModelO1Pro2025_03_19 ResponsesModel = "o1-pro-2025-03-19"
      - const ResponsesModelO3Pro ResponsesModel = "o3-pro"
      - const ResponsesModelO3Pro2025_06_10 ResponsesModel = "o3-pro-2025-06-10"
      - const ResponsesModelO3DeepResearch ResponsesModel = "o3-deep-research"
      - const ResponsesModelO3DeepResearch2025_06_26 ResponsesModel = "o3-deep-research-2025-06-26"
      - const ResponsesModelO4MiniDeepResearch ResponsesModel = "o4-mini-deep-research"
      - const ResponsesModelO4MiniDeepResearch2025_06_26 ResponsesModel = "o4-mini-deep-research-2025-06-26"
      - const ResponsesModelComputerUsePreview ResponsesModel = "computer-use-preview"
      - const ResponsesModelComputerUsePreview2025_03_11 ResponsesModel = "computer-use-preview-2025-03-11"
      - const ResponsesModelGPT5Codex ResponsesModel = "gpt-5-codex"
      - const ResponsesModelGPT5Pro ResponsesModel = "gpt-5-pro"
      - const ResponsesModelGPT5Pro2025_10_06 ResponsesModel = "gpt-5-pro-2025-10-06"
      - const ResponsesModelGPT5_1CodexMax ResponsesModel = "gpt-5.1-codex-max"
  - Object Response
    
    The object type of this resource - always set to response.
    - const ResponseResponse Response = "response"
  - Output []ResponseOutputItemUnion
    
    An array of content items generated by the model.
    - The length and order of items in the output array is dependent on the model's response.
    - Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
    - type ResponseFunctionToolCallOutputItem struct{…}
      - ID string
        
        The unique ID of the function call tool output.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Output ResponseFunctionToolCallOutputItemOutputUnion
        
        The output from the function call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Status ResponseFunctionToolCallOutputItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
        
        const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
        
        const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
      - Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
    - type ResponseComputerToolCallOutputItem struct{…}
      - ID string
        
        The unique ID of the computer call tool output.
      - CallID string
        
        The ID of the computer tool call that produced the output.
      - Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
      - Status ResponseComputerToolCallOutputItemStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
        
        const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
        
        const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
        
        const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
      - Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
      - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
    - type ResponseToolSearchCall struct{…}
      - ID string
        
        The unique ID of the tool search call item.
      - Arguments any
        
        Arguments used for the tool search call.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchCallExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
        
        const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
      - Status ResponseToolSearchCallStatus
        
        The status of the tool search call item that was recorded.
        
        const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
        
        const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
        
        const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
      - Type ToolSearchCall
        
        The type of the item. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseToolSearchOutputItem struct{…}
      - ID string
        
        The unique ID of the tool search output item.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchOutputItemExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
        
        const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
      - Status ResponseToolSearchOutputItemStatus
        
        The status of the tool search output item that was recorded.
        
        const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
        
        const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
        
        const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
      - Tools []ToolUnion
        
        The loaded tool definitions returned by tool search.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type ToolSearchOutput
        
        The type of the item. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseOutputItemAdditionalTools struct{…}
      - ID string
        
        The unique ID of the additional tools item.
      - Role string
        
        The role that provided the additional tools.
        
        const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
        
        const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
        
        const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
        
        const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
        
        const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
        
        const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
        
        const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
        
        const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
      - Tools []ToolUnion
        
        The additional tool definitions made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type AdditionalTools
        
        The type of the item. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
    - type ResponseCompactionItem struct{…}
      
      A compaction item generated by the v1/responses/compact API.
      - ID string
        
        The unique ID of the compaction item.
      - EncryptedContent string
        
        The encrypted content that was produced by compaction.
      - Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseOutputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
      - ID string
        
        The unique ID of the image generation call.
      - Result string
        
        The generated image encoded in base64.
      - Status string
        
        The status of the image generation call.
        
        const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
        
        const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
        
        const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
      - Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
    - type ResponseOutputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
      - ID string
        
        The unique ID of the local shell call.
      - Action ResponseOutputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
      - CallID string
        
        The unique ID of the local shell tool call generated by the model.
      - Status string
        
        The status of the local shell call.
        
        const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
        
        const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
      - Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
    - type ResponseOutputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
      - ID string
        
        The unique ID of the local shell tool call generated by the model.
      - Output string
        
        A JSON string of the output of the local shell tool call.
      - Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
    - type ResponseFunctionShellToolCall struct{…}
      
      A tool call that executes one or more shell commands in a managed environment.
      - ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
      - Action ResponseFunctionShellToolCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Environment ResponseFunctionShellToolCallEnvironmentUnion
        
        Represents the use of a local environment to perform shell actions.
        
        type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
        
        type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
      - Status ResponseFunctionShellToolCallStatus
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
        
        const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
        
        const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
      - Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
      - CreatedBy string
        
        The ID of the entity that created this tool call.
    - type ResponseFunctionShellToolCallOutput struct{…}
      
      The output of a shell tool call that was emitted.
      - ID string
        
        The unique ID of the shell call output. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - MaxOutputLength int64
        
        The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
      - Output []ResponseFunctionShellToolCallOutputOutput
        
        An array of shell call output contents
        
        Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        The standard error output that was captured.
        
        Stdout string
        
        The standard output that was captured.
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - Status ResponseFunctionShellToolCallOutputStatus
        
        The status of the shell call output. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
        
        const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
        
        const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
      - Type ShellCallOutput
        
        The type of the shell call output. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseApplyPatchToolCall struct{…}
      
      A tool call that applies file diffs by creating, deleting, or updating files.
      - ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Operation ResponseApplyPatchToolCallOperationUnion
        
        One of the create_file, delete_file, or update_file operations applied via apply_patch.
        
        type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
      - Status ResponseApplyPatchToolCallStatus
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
        
        const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
      - Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
      - CreatedBy string
        
        The ID of the entity that created this tool call.
    - type ResponseApplyPatchToolCallOutput struct{…}
      
      The output emitted by an apply patch tool call.
      - ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Status ResponseApplyPatchToolCallOutputStatus
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
        
        const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
      - Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
      - CreatedBy string
        
        The ID of the entity that created this tool call output.
      - Output string
        
        Optional textual output returned by the apply patch tool.
    - type ResponseOutputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
      - ID string
        
        The unique ID of the tool call.
      - Arguments string
        
        A JSON string of the arguments passed to the tool.
      - Name string
        
        The name of the tool that was run.
      - ServerLabel string
        
        The label of the MCP server running the tool.
      - Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
      - ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
      - Error string
        
        The error from the tool call, if any.
      - Output string
        
        The output from the tool call.
      - Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
        
        const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
        
        const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
        
        const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
        
        const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
    - type ResponseOutputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
      - ID string
        
        The unique ID of the list.
      - ServerLabel string
        
        The label of the MCP server.
      - Tools []ResponseOutputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
      - Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
      - Error string
        
        Error message if the server could not list tools.
    - type ResponseOutputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
      - ID string
        
        The unique ID of the approval request.
      - Arguments string
        
        A JSON string of arguments for the tool.
      - Name string
        
        The name of the tool to run.
      - ServerLabel string
        
        The label of the MCP server making the request.
      - Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
    - type ResponseOutputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
      - ID string
        
        The unique ID of the approval response
      - ApprovalRequestID string
        
        The ID of the approval request being answered.
      - Approve bool
        
        Whether the request was approved.
      - Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
      - Reason string
        
        Optional reason for the decision.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
    - type ResponseCustomToolCallOutputItem struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
      - ID string
        
        The unique ID of the custom tool call output item.
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
        
        const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
        
        const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
      - CreatedBy string
        
        The identifier of the actor that created the item.
  - ParallelToolCalls bool
    
    Whether to allow the model to run tool calls in parallel.
  - Temperature float64
    
    What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
  - ToolChoice ResponseToolChoiceUnion
    
    How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.
    - type ToolChoiceOptions string
      
      Controls which (if any) tool is called by the model.
      
      none means the model will not call any tool and instead generates a message.
      
      auto means the model can pick between generating a message or calling one or more tools.
      
      required means the model must call one or more tools.
      - const ToolChoiceOptionsNone ToolChoiceOptions = "none"
      - const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
      - const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
    - type ToolChoiceAllowed struct{…}
      
      Constrains the tools available to the model to a pre-defined set.
      - Mode ToolChoiceAllowedMode
        
        Constrains the tools available to the model to a pre-defined set.
        
        auto allows the model to pick from among the allowed tools and generate a message.
        
        required requires the model to call one or more of the allowed tools.
        
        const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
        
        const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
      - Tools []map[string, any]
        
        A list of tool definitions that the model should be allowed to call.
        
        For the Responses API, the list of tool definitions might look like:
        
        [ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ]
      - Type AllowedTools
        
        Allowed tool configuration type. Always allowed_tools.
        
        const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
    - type ToolChoiceTypes struct{…}
      
      Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
      - Type ToolChoiceTypesType
        
        The type of hosted tool the model should to use. Learn more about built-in tools.
        
        Allowed values are:
        
        file_search
        
        web_search_preview
        
        computer
        
        computer_use_preview
        
        computer_use
        
        code_interpreter
        
        image_generation
        
        const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
        
        const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
        
        const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
        
        const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
        
        const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
        
        const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
        
        const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
        
        const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
    - type ToolChoiceFunction struct{…}
      
      Use this option to force the model to call a specific function.
      - Name string
        
        The name of the function to call.
      - Type Function
        
        For function calling, the type is always function.
        
        const FunctionFunction Function = "function"
    - type ToolChoiceMcp struct{…}
      
      Use this option to force the model to call a specific tool on a remote MCP server.
      - ServerLabel string
        
        The label of the MCP server to use.
      - Type Mcp
        
        For MCP tools, the type is always mcp.
        
        const McpMcp Mcp = "mcp"
      - Name string
        
        The name of the tool to call on the server.
    - type ToolChoiceCustom struct{…}
      
      Use this option to force the model to call a specific custom tool.
      - Name string
        
        The name of the custom tool to call.
      - Type Custom
        
        For custom tool calling, the type is always custom.
        
        const CustomCustom Custom = "custom"
    - type ToolChoiceApplyPatch struct{…}
      
      Forces the model to call the apply_patch tool when executing a tool call.
      - Type ApplyPatch
        
        The tool to call. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
    - type ToolChoiceShell struct{…}
      
      Forces the model to call the shell tool when a tool call is required.
      - Type Shell
        
        The tool to call. Always shell.
        
        const ShellShell Shell = "shell"
  - Tools []ToolUnion
    
    An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
    
    We support the following categories of tools:
    - Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
    - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
    - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
  - TopP float64
    
    An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
    
    We generally recommend altering this or temperature but not both.
  - Background bool
    
    Whether to run the model response in the background. Learn more.
  - CompletedAt float64
    
    Unix timestamp (in seconds) of when this Response was completed. Only present when the status is completed.
  - Conversation ResponseConversation
    
    The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
    - ID string
      
      The unique ID of the conversation that this response was associated with.
  - MaxOutputTokens int64
    
    An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
  - MaxToolCalls int64
    
    The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
  - Moderation ResponseModeration
    
    Moderation results for the response input and output, if moderated completions were requested.
    - Input ResponseModerationInputUnion
      
      Moderation for the response input.
      - type ResponseModerationInputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeText ResponseModerationInputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeImage ResponseModerationInputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
      - type ResponseModerationInputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
    - Output ResponseModerationOutputUnion
      
      Moderation for the response output.
      - type ResponseModerationOutputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeText ResponseModerationOutputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeImage ResponseModerationOutputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
      - type ResponseModerationOutputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
  - PreviousResponseID string
    
    The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
  - Prompt ResponsePrompt
    
    Reference to a prompt template and its variables. Learn more.
    - ID string
      
      The unique identifier of the prompt template to use.
    - Variables map[string, ResponsePromptVariableUnion]
      
      Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
      - string
      - type ResponseInputText struct{…}
        
        A text input to the model.
      - type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
      - type ResponseInputFile struct{…}
        
        A file input to the model.
    - Version string
      
      Optional version of the prompt template.
  - PromptCacheKey string
    
    Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
  - PromptCacheRetention ResponsePromptCacheRetention
    
    The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.
    
    For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:
    - Organizations without ZDR enabled default to 24h.
    - Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.
    - const ResponsePromptCacheRetentionInMemory ResponsePromptCacheRetention = "in_memory"
    - const ResponsePromptCacheRetention24h ResponsePromptCacheRetention = "24h"
  - Reasoning Reasoning
    
    gpt-5 and o-series models only
    
    Configuration options for reasoning models.
    - Context ReasoningContext
      
      Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
      - const ReasoningContextAuto ReasoningContext = "auto"
      - const ReasoningContextCurrentTurn ReasoningContext = "current_turn"
      - const ReasoningContextAllTurns ReasoningContext = "all_turns"
    - Effort ReasoningEffort
      
      Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
      - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
      - All models before gpt-5.1 default to medium reasoning effort, and do not support none.
      - The gpt-5-pro model defaults to (and only supports) high reasoning effort.
      - xhigh is supported for all models after gpt-5.1-codex-max.
      - const ReasoningEffortNone ReasoningEffort = "none"
      - const ReasoningEffortMinimal ReasoningEffort = "minimal"
      - const ReasoningEffortLow ReasoningEffort = "low"
      - const ReasoningEffortMedium ReasoningEffort = "medium"
      - const ReasoningEffortHigh ReasoningEffort = "high"
      - const ReasoningEffortXhigh ReasoningEffort = "xhigh"
    - GenerateSummary ReasoningGenerateSummary
      
      Deprecated: use summary instead.
      
      A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
      - const ReasoningGenerateSummaryAuto ReasoningGenerateSummary = "auto"
      - const ReasoningGenerateSummaryConcise ReasoningGenerateSummary = "concise"
      - const ReasoningGenerateSummaryDetailed ReasoningGenerateSummary = "detailed"
    - Summary ReasoningSummary
      
      A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
      
      concise is supported for computer-use-preview models and all reasoning models after gpt-5.
      - const ReasoningSummaryAuto ReasoningSummary = "auto"
      - const ReasoningSummaryConcise ReasoningSummary = "concise"
      - const ReasoningSummaryDetailed ReasoningSummary = "detailed"
  - SafetyIdentifier string
    
    A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
  - ServiceTier ResponseServiceTier
    
    Specifies the processing type used for serving the request.
    - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
    - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
    - If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
    - When not set, the default behavior is 'auto'.
    When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
    - const ResponseServiceTierAuto ResponseServiceTier = "auto"
    - const ResponseServiceTierDefault ResponseServiceTier = "default"
    - const ResponseServiceTierFlex ResponseServiceTier = "flex"
    - const ResponseServiceTierScale ResponseServiceTier = "scale"
    - const ResponseServiceTierPriority ResponseServiceTier = "priority"
  - Status ResponseStatus
    
    The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
    - const ResponseStatusCompleted ResponseStatus = "completed"
    - const ResponseStatusFailed ResponseStatus = "failed"
    - const ResponseStatusInProgress ResponseStatus = "in_progress"
    - const ResponseStatusCancelled ResponseStatus = "cancelled"
    - const ResponseStatusQueued ResponseStatus = "queued"
    - const ResponseStatusIncomplete ResponseStatus = "incomplete"
  - Text ResponseTextConfig
    
    Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
    - Text inputs and outputs
    - Structured Outputs
    - Format ResponseFormatTextConfigUnion
      
      An object specifying the format that the model must output.
      
      Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
      
      The default format is { "type": "text" } with no additional options.
      
      Not recommended for gpt-4o and newer models:
      
      Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
      - type ResponseFormatText struct{…}
        
        Default response format. Used to generate text responses.
        
        Type Text
        
        The type of response format being defined. Always text.
        
        const TextText Text = "text"
      - type ResponseFormatTextJSONSchemaConfig struct{…}
        
        JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
        
        Name string
        
        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
        
        Schema map[string, any]
        
        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
        
        Type JSONSchema
        
        The type of response format being defined. Always json_schema.
        
        const JSONSchemaJSONSchema JSONSchema = "json_schema"
        
        Description string
        
        A description of what the response format is for, used by the model to determine how to respond in the format.
        
        Strict bool
        
        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
      - type ResponseFormatJSONObject struct{…}
        
        JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
        
        Type JSONObject
        
        The type of response format being defined. Always json_object.
        
        const JSONObjectJSONObject JSONObject = "json_object"
    - Verbosity ResponseTextConfigVerbosity
      
      Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
      - const ResponseTextConfigVerbosityLow ResponseTextConfigVerbosity = "low"
      - const ResponseTextConfigVerbosityMedium ResponseTextConfigVerbosity = "medium"
      - const ResponseTextConfigVerbosityHigh ResponseTextConfigVerbosity = "high"
  - TopLogprobs int64
    
    An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
  - Truncation ResponseTruncation
    
    The truncation strategy to use for the model response.
    - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
    - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
    - const ResponseTruncationAuto ResponseTruncation = "auto"
    - const ResponseTruncationDisabled ResponseTruncation = "disabled"
  - Usage ResponseUsage
    
    Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
    - InputTokens int64
      
      The number of input tokens.
    - InputTokensDetails ResponseUsageInputTokensDetails
      
      A detailed breakdown of the input tokens.
      - CachedTokens int64
        
        The number of tokens that were retrieved from the cache. More on prompt caching.
    - OutputTokens int64
      
      The number of output tokens.
    - OutputTokensDetails ResponseUsageOutputTokensDetails
      
      A detailed breakdown of the output tokens.
      - ReasoningTokens int64
        
        The number of reasoning tokens.
    - TotalTokens int64
      
      The total number of tokens used.
  - User string
    
    This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseIncomplete
  
  The type of the event. Always response.incomplete.
  - const ResponseIncompleteResponseIncomplete ResponseIncomplete = "response.incomplete"

Response Input

type ResponseInput []ResponseInputItemUnion

A list of one or many input items to the model, containing different content types.
- type EasyInputMessage struct{…}
  
  A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
  - Content EasyInputMessageContentUnion
    
    Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
    - string
    - type ResponseInputMessageContentList []ResponseInputContentUnion
      
      A list of one or many input items to the model, containing different content types.
      - type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
      - type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
      - type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
  - Role EasyInputMessageRole
    
    The role of the message input. One of user, assistant, system, or developer.
    - const EasyInputMessageRoleUser EasyInputMessageRole = "user"
    - const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
    - const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
    - const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
  - Phase EasyInputMessagePhase
    
    Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
    - const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
    - const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
  - Type EasyInputMessageType
    
    The type of the message input. Always message.
    - const EasyInputMessageTypeMessage EasyInputMessageType = "message"
- type ResponseInputItemMessage struct{…}
  
  A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
  - Content ResponseInputMessageContentList
    
    A list of one or many input items to the model, containing different content types.
  - Role string
    
    The role of the message input. One of user, system, or developer.
    - const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
    - const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
    - const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
  - Status string
    
    The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
    - const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
    - const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
  - Type string
    
    The type of the message input. Always set to message.
    - const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
- type ResponseOutputMessage struct{…}
  
  An output message from the model.
  - ID string
    
    The unique ID of the output message.
  - Content []ResponseOutputMessageContentUnion
    
    The content of the output message.
    - type ResponseOutputText struct{…}
      
      A text output from the model.
      - Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
      - Text string
        
        The text output from the model.
      - Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
      - Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
    - type ResponseOutputRefusal struct{…}
      
      A refusal from the model.
      - Refusal string
        
        The refusal explanation from the model.
      - Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
  - Role Assistant
    
    The role of the output message. Always assistant.
    - const AssistantAssistant Assistant = "assistant"
  - Status ResponseOutputMessageStatus
    
    The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
    - const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
    - const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
    - const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
  - Type Message
    
    The type of the output message. Always message.
    - const MessageMessage Message = "message"
  - Phase ResponseOutputMessagePhase
    
    Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
    - const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
    - const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
- type ResponseFileSearchToolCall struct{…}
  
  The results of a file search tool call. See the file search guide for more information.
  - ID string
    
    The unique ID of the file search tool call.
  - Queries []string
    
    The queries used to search for files.
  - Status ResponseFileSearchToolCallStatus
    
    The status of the file search tool call. One of in_progress, searching, incomplete or failed,
    - const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
    - const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
    - const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
    - const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
    - const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
  - Type FileSearchCall
    
    The type of the file search tool call. Always file_search_call.
    - const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
  - Results []ResponseFileSearchToolCallResult
    
    The results of the file search tool call.
    - Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
      
      Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
      - string
      - float64
      - bool
    - FileID string
      
      The unique ID of the file.
    - Filename string
      
      The name of the file.
    - Score float64
      
      The relevance score of the file - a value between 0 and 1.
    - Text string
      
      The text that was retrieved from the file.
- type ResponseComputerToolCall struct{…}
  
  A tool call to a computer use tool. See the computer use guide for more information.
  - ID string
    
    The unique ID of the computer call.
  - CallID string
    
    An identifier used when responding to the tool call with output.
  - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
    
    The pending safety checks for the computer call.
    - ID string
      
      The ID of the pending safety check.
    - Code string
      
      The type of the pending safety check.
    - Message string
      
      Details about the pending safety check.
  - Status ResponseComputerToolCallStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
    - const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
    - const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
  - Type ResponseComputerToolCallType
    
    The type of the computer call. Always computer_call.
    - const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
  - Action ResponseComputerToolCallActionUnion
    
    A click action.
    - type ResponseComputerToolCallActionClick struct{…}
      
      A click action.
      - Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
      - Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
      - X int64
        
        The x-coordinate where the click occurred.
      - Y int64
        
        The y-coordinate where the click occurred.
      - Keys []string
        
        The keys being held while clicking.
    - type ResponseComputerToolCallActionDoubleClick struct{…}
      
      A double click action.
      - Keys []string
        
        The keys being held while double-clicking.
      - Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
      - X int64
        
        The x-coordinate where the double click occurred.
      - Y int64
        
        The y-coordinate where the double click occurred.
    - type ResponseComputerToolCallActionDrag struct{…}
      
      A drag action.
      - Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
      - Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
      - Keys []string
        
        The keys being held while dragging the mouse.
    - type ResponseComputerToolCallActionKeypress struct{…}
      
      A collection of keypresses the model would like to perform.
      - Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
      - Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
    - type ResponseComputerToolCallActionMove struct{…}
      
      A mouse move action.
      - Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
      - X int64
        
        The x-coordinate to move to.
      - Y int64
        
        The y-coordinate to move to.
      - Keys []string
        
        The keys being held while moving the mouse.
    - type ResponseComputerToolCallActionScreenshot struct{…}
      
      A screenshot action.
      - Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
    - type ResponseComputerToolCallActionScroll struct{…}
      
      A scroll action.
      - ScrollX int64
        
        The horizontal scroll distance.
      - ScrollY int64
        
        The vertical scroll distance.
      - Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
      - X int64
        
        The x-coordinate where the scroll occurred.
      - Y int64
        
        The y-coordinate where the scroll occurred.
      - Keys []string
        
        The keys being held while scrolling.
    - type ResponseComputerToolCallActionType struct{…}
      
      An action to type in text.
      - Text string
        
        The text to type.
      - Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
    - type ResponseComputerToolCallActionWait struct{…}
      
      A wait action.
      - Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
  - Actions ComputerActionList
    
    Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
    - type ComputerActionClick struct{…}
      
      A click action.
      - Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
      - Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
      - X int64
        
        The x-coordinate where the click occurred.
      - Y int64
        
        The y-coordinate where the click occurred.
      - Keys []string
        
        The keys being held while clicking.
    - type ComputerActionDoubleClick struct{…}
      
      A double click action.
      - Keys []string
        
        The keys being held while double-clicking.
      - Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
      - X int64
        
        The x-coordinate where the double click occurred.
      - Y int64
        
        The y-coordinate where the double click occurred.
    - type ComputerActionDrag struct{…}
      
      A drag action.
      - Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
      - Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
      - Keys []string
        
        The keys being held while dragging the mouse.
    - type ComputerActionKeypress struct{…}
      
      A collection of keypresses the model would like to perform.
      - Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
      - Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
    - type ComputerActionMove struct{…}
      
      A mouse move action.
      - Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
      - X int64
        
        The x-coordinate to move to.
      - Y int64
        
        The y-coordinate to move to.
      - Keys []string
        
        The keys being held while moving the mouse.
    - type ComputerActionScreenshot struct{…}
      
      A screenshot action.
      - Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
    - type ComputerActionScroll struct{…}
      
      A scroll action.
      - ScrollX int64
        
        The horizontal scroll distance.
      - ScrollY int64
        
        The vertical scroll distance.
      - Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
      - X int64
        
        The x-coordinate where the scroll occurred.
      - Y int64
        
        The y-coordinate where the scroll occurred.
      - Keys []string
        
        The keys being held while scrolling.
    - type ComputerActionType struct{…}
      
      An action to type in text.
      - Text string
        
        The text to type.
      - Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
    - type ComputerActionWait struct{…}
      
      A wait action.
      - Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
- type ResponseInputItemComputerCallOutput struct{…}
  
  The output of a computer tool call.
  - CallID string
    
    The ID of the computer tool call that produced the output.
  - Output ResponseComputerToolCallOutputScreenshot
    
    A computer screenshot image used with the computer use tool.
    - Type ComputerScreenshot
      
      Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
      - const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
    - FileID string
      
      The identifier of an uploaded file that contains the screenshot.
    - ImageURL string
      
      The URL of the screenshot image.
  - Type ComputerCallOutput
    
    The type of the computer tool call output. Always computer_call_output.
    - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
  - ID string
    
    The ID of the computer tool call output.
  - AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
    
    The safety checks reported by the API that have been acknowledged by the developer.
    - ID string
      
      The ID of the pending safety check.
    - Code string
      
      The type of the pending safety check.
    - Message string
      
      Details about the pending safety check.
  - Status string
    
    The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
    - const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
    - const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
    - const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
- type ResponseFunctionWebSearch struct{…}
  
  The results of a web search tool call. See the web search guide for more information.
  - ID string
    
    The unique ID of the web search tool call.
  - Action ResponseFunctionWebSearchActionUnion
    
    An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
    - type ResponseFunctionWebSearchActionSearch struct{…}
      
      Action type "search" - Performs a web search query.
      - Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
      - Queries []string
        
        The search queries.
      - Query string
        
        The search query.
      - Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
    - type ResponseFunctionWebSearchActionOpenPage struct{…}
      
      Action type "open_page" - Opens a specific URL from search results.
      - Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
      - URL string
        
        The URL opened by the model.
    - type ResponseFunctionWebSearchActionFindInPage struct{…}
      
      Action type "find_in_page": Searches for a pattern within a loaded page.
      - Pattern string
        
        The pattern or text to search for within the page.
      - Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
      - URL string
        
        The URL of the page searched for the pattern.
  - Status ResponseFunctionWebSearchStatus
    
    The status of the web search tool call.
    - const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
    - const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
    - const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
    - const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
  - Type WebSearchCall
    
    The type of the web search tool call. Always web_search_call.
    - const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
- type ResponseFunctionToolCall struct{…}
  
  A tool call to run a function. See the function calling guide for more information.
  - Arguments string
    
    A JSON string of the arguments to pass to the function.
  - CallID string
    
    The unique ID of the function tool call generated by the model.
  - Name string
    
    The name of the function to run.
  - Type FunctionCall
    
    The type of the function tool call. Always function_call.
    - const FunctionCallFunctionCall FunctionCall = "function_call"
  - ID string
    
    The unique ID of the function tool call.
  - Namespace string
    
    The namespace of the function to run.
  - Status ResponseFunctionToolCallStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
    - const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
    - const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
- type ResponseInputItemFunctionCallOutput struct{…}
  
  The output of a function tool call.
  - CallID string
    
    The unique ID of the function tool call generated by the model.
  - Output ResponseInputItemFunctionCallOutputOutputUnion
    
    Text, image, or file output of the function tool call.
    - string
    - type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
      
      An array of content outputs (text, image, file) for the function tool call.
      - type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
      - type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
      - type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
  - Type FunctionCallOutput
    
    The type of the function tool call output. Always function_call_output.
    - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
  - ID string
    
    The unique ID of the function tool call output. Populated when this item is returned via API.
  - Status string
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
    - const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
    - const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
- type ResponseInputItemToolSearchCall struct{…}
  - Arguments any
    
    The arguments supplied to the tool search call.
  - Type ToolSearchCall
    
    The item type. Always tool_search_call.
    - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
  - ID string
    
    The unique ID of this tool search call.
  - CallID string
    
    The unique ID of the tool search call generated by the model.
  - Execution string
    
    Whether tool search was executed by the server or by the client.
    - const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
    - const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
  - Status string
    
    The status of the tool search call.
    - const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
    - const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
    - const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
- type ResponseToolSearchOutputItemParamResp struct{…}
  - Tools []ToolUnion
    
    The loaded tool definitions returned by the tool search output.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
      - Name string
        
        The name of the function to call.
      - Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
      - Strict bool
        
        Whether to enforce strict parameter validation. Default true.
      - Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
      - DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
      - Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
      - VectorStoreIDs []string
        
        The IDs of the vector stores to search.
      - Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
      - MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
      - RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
      - Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
      - DisplayHeight int64
        
        The height of the computer display.
      - DisplayWidth int64
        
        The width of the computer display.
      - Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
      - Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
      - Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
      - SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
      - UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
      - Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
      - AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
      - Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
      - ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
      - DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
      - Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
      - RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
      - ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
      - ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
      - TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
      - Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
      - Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
      - Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
      - Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
      - Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
      - InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
      - InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
      - Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
      - Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
      - OutputCompression int64
        
        Compression level for the output image. Default: 100.
      - OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
      - PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
      - Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
      - Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
      - Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
      - Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
      - Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
      - Name string
        
        The name of the custom tool, used to identify it in tool calls.
      - Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
      - DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
      - Description string
        
        Optional description of the custom tool, used to provide more context.
      - Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
      - Description string
        
        A description of the namespace shown to the model.
      - Name string
        
        The namespace name used in tool calls (for example, crm).
      - Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
      - Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
      - Description string
        
        Description shown to the model for a client-executed tool search tool.
      - Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
      - Parameters any
        
        Parameter schema for a client-executed tool search tool.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
      - SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
      - SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
      - UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
      - Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
  - Type ToolSearchOutput
    
    The item type. Always tool_search_output.
    - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
  - ID string
    
    The unique ID of this tool search output.
  - CallID string
    
    The unique ID of the tool search call generated by the model.
  - Execution ResponseToolSearchOutputItemParamExecution
    
    Whether tool search was executed by the server or by the client.
    - const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
    - const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
  - Status ResponseToolSearchOutputItemParamStatus
    
    The status of the tool search output.
    - const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
    - const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
    - const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
- type ResponseInputItemAdditionalTools struct{…}
  - Role Developer
    
    The role that provided the additional tools. Only developer is supported.
    - const DeveloperDeveloper Developer = "developer"
  - Tools []ToolUnion
    
    A list of additional tools made available at this item.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
  - Type AdditionalTools
    
    The item type. Always additional_tools.
    - const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
  - ID string
    
    The unique ID of this additional tools item.
- type ResponseReasoningItem struct{…}
  
  A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
  - ID string
    
    The unique identifier of the reasoning content.
  - Summary []ResponseReasoningItemSummary
    
    Reasoning summary content.
    - Text string
      
      A summary of the reasoning output from the model so far.
    - Type SummaryText
      
      The type of the object. Always summary_text.
      - const SummaryTextSummaryText SummaryText = "summary_text"
  - Type Reasoning
    
    The type of the object. Always reasoning.
    - const ReasoningReasoning Reasoning = "reasoning"
  - Content []ResponseReasoningItemContent
    
    Reasoning text content.
    - Text string
      
      The reasoning text from the model.
    - Type ReasoningText
      
      The type of the reasoning text. Always reasoning_text.
      - const ReasoningTextReasoningText ReasoningText = "reasoning_text"
  - EncryptedContent string
    
    The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
  - Status ResponseReasoningItemStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
    - const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
    - const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
- type ResponseCompactionItemParamResp struct{…}
  
  A compaction item generated by the v1/responses/compact API.
  - EncryptedContent string
    
    The encrypted content of the compaction summary.
  - Type Compaction
    
    The type of the item. Always compaction.
    - const CompactionCompaction Compaction = "compaction"
  - ID string
    
    The ID of the compaction item.
- type ResponseInputItemImageGenerationCall struct{…}
  
  An image generation request made by the model.
  - ID string
    
    The unique ID of the image generation call.
  - Result string
    
    The generated image encoded in base64.
  - Status string
    
    The status of the image generation call.
    - const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
    - const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
    - const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
    - const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
  - Type ImageGenerationCall
    
    The type of the image generation call. Always image_generation_call.
    - const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
- type ResponseCodeInterpreterToolCall struct{…}
  
  A tool call to run code.
  - ID string
    
    The unique ID of the code interpreter tool call.
  - Code string
    
    The code to run, or null if not available.
  - ContainerID string
    
    The ID of the container used to run the code.
  - Outputs []ResponseCodeInterpreterToolCallOutputUnion
    
    The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
    - type ResponseCodeInterpreterToolCallOutputLogs struct{…}
      
      The logs output from the code interpreter.
      - Logs string
        
        The logs output from the code interpreter.
      - Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
    - type ResponseCodeInterpreterToolCallOutputImage struct{…}
      
      The image output from the code interpreter.
      - Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
      - URL string
        
        The URL of the image output from the code interpreter.
  - Status ResponseCodeInterpreterToolCallStatus
    
    The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
    - const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
    - const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
    - const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
    - const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
    - const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
  - Type CodeInterpreterCall
    
    The type of the code interpreter tool call. Always code_interpreter_call.
    - const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
- type ResponseInputItemLocalShellCall struct{…}
  
  A tool call to run a command on the local shell.
  - ID string
    
    The unique ID of the local shell call.
  - Action ResponseInputItemLocalShellCallAction
    
    Execute a shell command on the server.
    - Command []string
      
      The command to run.
    - Env map[string, string]
      
      Environment variables to set for the command.
    - Type Exec
      
      The type of the local shell action. Always exec.
      - const ExecExec Exec = "exec"
    - TimeoutMs int64
      
      Optional timeout in milliseconds for the command.
    - User string
      
      Optional user to run the command as.
    - WorkingDirectory string
      
      Optional working directory to run the command in.
  - CallID string
    
    The unique ID of the local shell tool call generated by the model.
  - Status string
    
    The status of the local shell call.
    - const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
    - const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
    - const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
  - Type LocalShellCall
    
    The type of the local shell call. Always local_shell_call.
    - const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
- type ResponseInputItemLocalShellCallOutput struct{…}
  
  The output of a local shell tool call.
  - ID string
    
    The unique ID of the local shell tool call generated by the model.
  - Output string
    
    A JSON string of the output of the local shell tool call.
  - Type LocalShellCallOutput
    
    The type of the local shell tool call output. Always local_shell_call_output.
    - const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
  - Status string
    
    The status of the item. One of in_progress, completed, or incomplete.
    - const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
    - const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
    - const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
- type ResponseInputItemShellCall struct{…}
  
  A tool representing a request to execute one or more shell commands.
  - Action ResponseInputItemShellCallAction
    
    The shell commands and limits that describe how to run the tool call.
    - Commands []string
      
      Ordered shell commands for the execution environment to run.
    - MaxOutputLength int64
      
      Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
    - TimeoutMs int64
      
      Maximum wall-clock time in milliseconds to allow the shell commands to run.
  - CallID string
    
    The unique ID of the shell tool call generated by the model.
  - Type ShellCall
    
    The type of the item. Always shell_call.
    - const ShellCallShellCall ShellCall = "shell_call"
  - ID string
    
    The unique ID of the shell tool call. Populated when this item is returned via API.
  - Environment ResponseInputItemShellCallEnvironmentUnion
    
    The environment to execute the shell commands in.
    - type LocalEnvironment struct{…}
    - type ContainerReference struct{…}
  - Status string
    
    The status of the shell call. One of in_progress, completed, or incomplete.
    - const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
    - const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
    - const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
- type ResponseInputItemShellCallOutput struct{…}
  
  The streamed output items emitted by a shell tool call.
  - CallID string
    
    The unique ID of the shell tool call generated by the model.
  - Output []ResponseFunctionShellCallOutputContent
    
    Captured chunks of stdout and stderr output, along with their associated outcomes.
    - Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
      
      The exit or timeout outcome associated with this shell call.
      - type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
      - type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
    - Stderr string
      
      Captured stderr output for the shell call.
    - Stdout string
      
      Captured stdout output for the shell call.
  - Type ShellCallOutput
    
    The type of the item. Always shell_call_output.
    - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
  - ID string
    
    The unique ID of the shell tool call output. Populated when this item is returned via API.
  - MaxOutputLength int64
    
    The maximum number of UTF-8 characters captured for this shell call's combined output.
  - Status string
    
    The status of the shell call output.
    - const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
    - const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
    - const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
- type ResponseInputItemApplyPatchCall struct{…}
  
  A tool call representing a request to create, delete, or update files using diff patches.
  - CallID string
    
    The unique ID of the apply patch tool call generated by the model.
  - Operation ResponseInputItemApplyPatchCallOperationUnion
    
    The specific create, delete, or update instruction for the apply_patch tool call.
    - type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
      
      Instruction for creating a new file via the apply_patch tool.
      - Diff string
        
        Unified diff content to apply when creating the file.
      - Path string
        
        Path of the file to create relative to the workspace root.
      - Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
    - type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
      
      Instruction for deleting an existing file via the apply_patch tool.
      - Path string
        
        Path of the file to delete relative to the workspace root.
      - Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
    - type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
      
      Instruction for updating an existing file via the apply_patch tool.
      - Diff string
        
        Unified diff content to apply to the existing file.
      - Path string
        
        Path of the file to update relative to the workspace root.
      - Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
  - Status string
    
    The status of the apply patch tool call. One of in_progress or completed.
    - const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
    - const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
  - Type ApplyPatchCall
    
    The type of the item. Always apply_patch_call.
    - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
  - ID string
    
    The unique ID of the apply patch tool call. Populated when this item is returned via API.
- type ResponseInputItemApplyPatchCallOutput struct{…}
  
  The streamed output emitted by an apply patch tool call.
  - CallID string
    
    The unique ID of the apply patch tool call generated by the model.
  - Status string
    
    The status of the apply patch tool call output. One of completed or failed.
    - const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
    - const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
  - Type ApplyPatchCallOutput
    
    The type of the item. Always apply_patch_call_output.
    - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
  - ID string
    
    The unique ID of the apply patch tool call output. Populated when this item is returned via API.
  - Output string
    
    Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
- type ResponseInputItemMcpListTools struct{…}
  
  A list of tools available on an MCP server.
  - ID string
    
    The unique ID of the list.
  - ServerLabel string
    
    The label of the MCP server.
  - Tools []ResponseInputItemMcpListToolsTool
    
    The tools available on the server.
    - InputSchema any
      
      The JSON schema describing the tool's input.
    - Name string
      
      The name of the tool.
    - Annotations any
      
      Additional annotations about the tool.
    - Description string
      
      The description of the tool.
  - Type McpListTools
    
    The type of the item. Always mcp_list_tools.
    - const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
  - Error string
    
    Error message if the server could not list tools.
- type ResponseInputItemMcpApprovalRequest struct{…}
  
  A request for human approval of a tool invocation.
  - ID string
    
    The unique ID of the approval request.
  - Arguments string
    
    A JSON string of arguments for the tool.
  - Name string
    
    The name of the tool to run.
  - ServerLabel string
    
    The label of the MCP server making the request.
  - Type McpApprovalRequest
    
    The type of the item. Always mcp_approval_request.
    - const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
- type ResponseInputItemMcpApprovalResponse struct{…}
  
  A response to an MCP approval request.
  - ApprovalRequestID string
    
    The ID of the approval request being answered.
  - Approve bool
    
    Whether the request was approved.
  - Type McpApprovalResponse
    
    The type of the item. Always mcp_approval_response.
    - const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
  - ID string
    
    The unique ID of the approval response
  - Reason string
    
    Optional reason for the decision.
- type ResponseInputItemMcpCall struct{…}
  
  An invocation of a tool on an MCP server.
  - ID string
    
    The unique ID of the tool call.
  - Arguments string
    
    A JSON string of the arguments passed to the tool.
  - Name string
    
    The name of the tool that was run.
  - ServerLabel string
    
    The label of the MCP server running the tool.
  - Type McpCall
    
    The type of the item. Always mcp_call.
    - const McpCallMcpCall McpCall = "mcp_call"
  - ApprovalRequestID string
    
    Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
  - Error string
    
    The error from the tool call, if any.
  - Output string
    
    The output from the tool call.
  - Status string
    
    The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
    - const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
    - const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
    - const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
    - const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
    - const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
- type ResponseCustomToolCallOutput struct{…}
  
  The output of a custom tool call from your code, being sent back to the model.
  - CallID string
    
    The call ID, used to map this custom tool call output to a custom tool call.
  - Output ResponseCustomToolCallOutputOutputUnion
    
    The output from the custom tool call generated by your code. Can be a string or an list of output content.
    - string
    - type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
      
      Text, image, or file output of the custom tool call.
      - type ResponseInputText struct{…}
        
        A text input to the model.
      - type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
      - type ResponseInputFile struct{…}
        
        A file input to the model.
  - Type CustomToolCallOutput
    
    The type of the custom tool call output. Always custom_tool_call_output.
    - const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
  - ID string
    
    The unique ID of the custom tool call output in the OpenAI platform.
- type ResponseCustomToolCall struct{…}
  
  A call to a custom tool created by the model.
  - CallID string
    
    An identifier used to map this custom tool call to a tool call output.
  - Input string
    
    The input for the custom tool call generated by the model.
  - Name string
    
    The name of the custom tool being called.
  - Type CustomToolCall
    
    The type of the custom tool call. Always custom_tool_call.
    - const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
  - ID string
    
    The unique ID of the custom tool call in the OpenAI platform.
  - Namespace string
    
    The namespace of the custom tool being called.
- type ResponseInputItemCompactionTrigger struct{…}
  
  Compacts the current context. Must be the final input item.
  - Type CompactionTrigger
    
    The type of the item. Always compaction_trigger.
    - const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
- type ResponseInputItemItemReference struct{…}
  
  An internal identifier for an item to reference.
  - ID string
    
    The ID of the item to reference.
  - Type string
    
    The type of item to reference. Always item_reference.
    - const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"

Response Input Audio

type ResponseInputAudio struct{…}

An audio input to the model.
- InputAudio ResponseInputAudioInputAudio
  - Data string
    
    Base64-encoded audio data.
  - Format string
    
    The format of the audio data. Currently supported formats are mp3 and wav.
    - const ResponseInputAudioInputAudioFormatMP3 ResponseInputAudioInputAudioFormat = "mp3"
    - const ResponseInputAudioInputAudioFormatWAV ResponseInputAudioInputAudioFormat = "wav"
- Type InputAudio
  
  The type of the input item. Always input_audio.
  - const InputAudioInputAudio InputAudio = "input_audio"

Response Input Content

type ResponseInputContentUnion interface{…}

A text input to the model.
- type ResponseInputText struct{…}
  
  A text input to the model.
  - Text string
    
    The text input to the model.
  - Type InputText
    
    The type of the input item. Always input_text.
    - const InputTextInputText InputText = "input_text"
- type ResponseInputImage struct{…}
  
  An image input to the model. Learn about image inputs.
  - Detail ResponseInputImageDetail
    
    The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
    - const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
    - const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
    - const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
    - const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
  - Type InputImage
    
    The type of the input item. Always input_image.
    - const InputImageInputImage InputImage = "input_image"
  - FileID string
    
    The ID of the file to be sent to the model.
  - ImageURL string
    
    The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
- type ResponseInputFile struct{…}
  
  A file input to the model.
  - Type InputFile
    
    The type of the input item. Always input_file.
    - const InputFileInputFile InputFile = "input_file"
  - Detail ResponseInputFileDetail
    
    The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
    - const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
    - const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
  - FileData string
    
    The content of the file to be sent to the model.
  - FileID string
    
    The ID of the file to be sent to the model.
  - FileURL string
    
    The URL of the file to be sent to the model.
  - Filename string
    
    The name of the file to be sent to the model.

Response Input File

type ResponseInputFile struct{…}

A file input to the model.
- Type InputFile
  
  The type of the input item. Always input_file.
  - const InputFileInputFile InputFile = "input_file"
- Detail ResponseInputFileDetail
  
  The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
  - const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
  - const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
- FileData string
  
  The content of the file to be sent to the model.
- FileID string
  
  The ID of the file to be sent to the model.
- FileURL string
  
  The URL of the file to be sent to the model.
- Filename string
  
  The name of the file to be sent to the model.

Response Input File Content

type ResponseInputFileContent struct{…}

A file input to the model.
- Type InputFile
  
  The type of the input item. Always input_file.
  - const InputFileInputFile InputFile = "input_file"
- Detail ResponseInputFileContentDetail
  
  The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
  - const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
  - const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
- FileData string
  
  The base64-encoded data of the file to be sent to the model.
- FileID string
  
  The ID of the file to be sent to the model.
- FileURL string
  
  The URL of the file to be sent to the model.
- Filename string
  
  The name of the file to be sent to the model.

Response Input Image

type ResponseInputImage struct{…}

An image input to the model. Learn about image inputs.
- Detail ResponseInputImageDetail
  
  The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
  - const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
  - const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
  - const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
  - const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
- Type InputImage
  
  The type of the input item. Always input_image.
  - const InputImageInputImage InputImage = "input_image"
- FileID string
  
  The ID of the file to be sent to the model.
- ImageURL string
  
  The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.

Response Input Image Content

type ResponseInputImageContent struct{…}

An image input to the model. Learn about image inputs
- Type InputImage
  
  The type of the input item. Always input_image.
  - const InputImageInputImage InputImage = "input_image"
- Detail ResponseInputImageContentDetail
  
  The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
  - const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
  - const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
  - const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
  - const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
- FileID string
  
  The ID of the file to be sent to the model.
- ImageURL string
  
  The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.

Response Input Item

type ResponseInputItemUnion interface{…}

A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
- type EasyInputMessage struct{…}
  
  A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
  - Content EasyInputMessageContentUnion
    
    Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
    - string
    - type ResponseInputMessageContentList []ResponseInputContentUnion
      
      A list of one or many input items to the model, containing different content types.
      - type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
      - type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
      - type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
  - Role EasyInputMessageRole
    
    The role of the message input. One of user, assistant, system, or developer.
    - const EasyInputMessageRoleUser EasyInputMessageRole = "user"
    - const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
    - const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
    - const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
  - Phase EasyInputMessagePhase
    
    Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
    - const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
    - const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
  - Type EasyInputMessageType
    
    The type of the message input. Always message.
    - const EasyInputMessageTypeMessage EasyInputMessageType = "message"
- type ResponseInputItemMessage struct{…}
  
  A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
  - Content ResponseInputMessageContentList
    
    A list of one or many input items to the model, containing different content types.
  - Role string
    
    The role of the message input. One of user, system, or developer.
    - const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
    - const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
    - const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
  - Status string
    
    The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
    - const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
    - const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
  - Type string
    
    The type of the message input. Always set to message.
    - const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
- type ResponseOutputMessage struct{…}
  
  An output message from the model.
  - ID string
    
    The unique ID of the output message.
  - Content []ResponseOutputMessageContentUnion
    
    The content of the output message.
    - type ResponseOutputText struct{…}
      
      A text output from the model.
      - Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
      - Text string
        
        The text output from the model.
      - Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
      - Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
    - type ResponseOutputRefusal struct{…}
      
      A refusal from the model.
      - Refusal string
        
        The refusal explanation from the model.
      - Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
  - Role Assistant
    
    The role of the output message. Always assistant.
    - const AssistantAssistant Assistant = "assistant"
  - Status ResponseOutputMessageStatus
    
    The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
    - const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
    - const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
    - const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
  - Type Message
    
    The type of the output message. Always message.
    - const MessageMessage Message = "message"
  - Phase ResponseOutputMessagePhase
    
    Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
    - const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
    - const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
- type ResponseFileSearchToolCall struct{…}
  
  The results of a file search tool call. See the file search guide for more information.
  - ID string
    
    The unique ID of the file search tool call.
  - Queries []string
    
    The queries used to search for files.
  - Status ResponseFileSearchToolCallStatus
    
    The status of the file search tool call. One of in_progress, searching, incomplete or failed,
    - const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
    - const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
    - const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
    - const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
    - const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
  - Type FileSearchCall
    
    The type of the file search tool call. Always file_search_call.
    - const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
  - Results []ResponseFileSearchToolCallResult
    
    The results of the file search tool call.
    - Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
      
      Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
      - string
      - float64
      - bool
    - FileID string
      
      The unique ID of the file.
    - Filename string
      
      The name of the file.
    - Score float64
      
      The relevance score of the file - a value between 0 and 1.
    - Text string
      
      The text that was retrieved from the file.
- type ResponseComputerToolCall struct{…}
  
  A tool call to a computer use tool. See the computer use guide for more information.
  - ID string
    
    The unique ID of the computer call.
  - CallID string
    
    An identifier used when responding to the tool call with output.
  - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
    
    The pending safety checks for the computer call.
    - ID string
      
      The ID of the pending safety check.
    - Code string
      
      The type of the pending safety check.
    - Message string
      
      Details about the pending safety check.
  - Status ResponseComputerToolCallStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
    - const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
    - const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
  - Type ResponseComputerToolCallType
    
    The type of the computer call. Always computer_call.
    - const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
  - Action ResponseComputerToolCallActionUnion
    
    A click action.
    - type ResponseComputerToolCallActionClick struct{…}
      
      A click action.
      - Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
      - Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
      - X int64
        
        The x-coordinate where the click occurred.
      - Y int64
        
        The y-coordinate where the click occurred.
      - Keys []string
        
        The keys being held while clicking.
    - type ResponseComputerToolCallActionDoubleClick struct{…}
      
      A double click action.
      - Keys []string
        
        The keys being held while double-clicking.
      - Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
      - X int64
        
        The x-coordinate where the double click occurred.
      - Y int64
        
        The y-coordinate where the double click occurred.
    - type ResponseComputerToolCallActionDrag struct{…}
      
      A drag action.
      - Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
      - Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
      - Keys []string
        
        The keys being held while dragging the mouse.
    - type ResponseComputerToolCallActionKeypress struct{…}
      
      A collection of keypresses the model would like to perform.
      - Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
      - Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
    - type ResponseComputerToolCallActionMove struct{…}
      
      A mouse move action.
      - Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
      - X int64
        
        The x-coordinate to move to.
      - Y int64
        
        The y-coordinate to move to.
      - Keys []string
        
        The keys being held while moving the mouse.
    - type ResponseComputerToolCallActionScreenshot struct{…}
      
      A screenshot action.
      - Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
    - type ResponseComputerToolCallActionScroll struct{…}
      
      A scroll action.
      - ScrollX int64
        
        The horizontal scroll distance.
      - ScrollY int64
        
        The vertical scroll distance.
      - Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
      - X int64
        
        The x-coordinate where the scroll occurred.
      - Y int64
        
        The y-coordinate where the scroll occurred.
      - Keys []string
        
        The keys being held while scrolling.
    - type ResponseComputerToolCallActionType struct{…}
      
      An action to type in text.
      - Text string
        
        The text to type.
      - Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
    - type ResponseComputerToolCallActionWait struct{…}
      
      A wait action.
      - Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
  - Actions ComputerActionList
    
    Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
    - type ComputerActionClick struct{…}
      
      A click action.
      - Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
      - Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
      - X int64
        
        The x-coordinate where the click occurred.
      - Y int64
        
        The y-coordinate where the click occurred.
      - Keys []string
        
        The keys being held while clicking.
    - type ComputerActionDoubleClick struct{…}
      
      A double click action.
      - Keys []string
        
        The keys being held while double-clicking.
      - Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
      - X int64
        
        The x-coordinate where the double click occurred.
      - Y int64
        
        The y-coordinate where the double click occurred.
    - type ComputerActionDrag struct{…}
      
      A drag action.
      - Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
      - Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
      - Keys []string
        
        The keys being held while dragging the mouse.
    - type ComputerActionKeypress struct{…}
      
      A collection of keypresses the model would like to perform.
      - Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
      - Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
    - type ComputerActionMove struct{…}
      
      A mouse move action.
      - Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
      - X int64
        
        The x-coordinate to move to.
      - Y int64
        
        The y-coordinate to move to.
      - Keys []string
        
        The keys being held while moving the mouse.
    - type ComputerActionScreenshot struct{…}
      
      A screenshot action.
      - Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
    - type ComputerActionScroll struct{…}
      
      A scroll action.
      - ScrollX int64
        
        The horizontal scroll distance.
      - ScrollY int64
        
        The vertical scroll distance.
      - Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
      - X int64
        
        The x-coordinate where the scroll occurred.
      - Y int64
        
        The y-coordinate where the scroll occurred.
      - Keys []string
        
        The keys being held while scrolling.
    - type ComputerActionType struct{…}
      
      An action to type in text.
      - Text string
        
        The text to type.
      - Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
    - type ComputerActionWait struct{…}
      
      A wait action.
      - Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
- type ResponseInputItemComputerCallOutput struct{…}
  
  The output of a computer tool call.
  - CallID string
    
    The ID of the computer tool call that produced the output.
  - Output ResponseComputerToolCallOutputScreenshot
    
    A computer screenshot image used with the computer use tool.
    - Type ComputerScreenshot
      
      Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
      - const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
    - FileID string
      
      The identifier of an uploaded file that contains the screenshot.
    - ImageURL string
      
      The URL of the screenshot image.
  - Type ComputerCallOutput
    
    The type of the computer tool call output. Always computer_call_output.
    - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
  - ID string
    
    The ID of the computer tool call output.
  - AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
    
    The safety checks reported by the API that have been acknowledged by the developer.
    - ID string
      
      The ID of the pending safety check.
    - Code string
      
      The type of the pending safety check.
    - Message string
      
      Details about the pending safety check.
  - Status string
    
    The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
    - const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
    - const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
    - const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
- type ResponseFunctionWebSearch struct{…}
  
  The results of a web search tool call. See the web search guide for more information.
  - ID string
    
    The unique ID of the web search tool call.
  - Action ResponseFunctionWebSearchActionUnion
    
    An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
    - type ResponseFunctionWebSearchActionSearch struct{…}
      
      Action type "search" - Performs a web search query.
      - Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
      - Queries []string
        
        The search queries.
      - Query string
        
        The search query.
      - Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
    - type ResponseFunctionWebSearchActionOpenPage struct{…}
      
      Action type "open_page" - Opens a specific URL from search results.
      - Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
      - URL string
        
        The URL opened by the model.
    - type ResponseFunctionWebSearchActionFindInPage struct{…}
      
      Action type "find_in_page": Searches for a pattern within a loaded page.
      - Pattern string
        
        The pattern or text to search for within the page.
      - Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
      - URL string
        
        The URL of the page searched for the pattern.
  - Status ResponseFunctionWebSearchStatus
    
    The status of the web search tool call.
    - const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
    - const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
    - const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
    - const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
  - Type WebSearchCall
    
    The type of the web search tool call. Always web_search_call.
    - const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
- type ResponseFunctionToolCall struct{…}
  
  A tool call to run a function. See the function calling guide for more information.
  - Arguments string
    
    A JSON string of the arguments to pass to the function.
  - CallID string
    
    The unique ID of the function tool call generated by the model.
  - Name string
    
    The name of the function to run.
  - Type FunctionCall
    
    The type of the function tool call. Always function_call.
    - const FunctionCallFunctionCall FunctionCall = "function_call"
  - ID string
    
    The unique ID of the function tool call.
  - Namespace string
    
    The namespace of the function to run.
  - Status ResponseFunctionToolCallStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
    - const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
    - const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
- type ResponseInputItemFunctionCallOutput struct{…}
  
  The output of a function tool call.
  - CallID string
    
    The unique ID of the function tool call generated by the model.
  - Output ResponseInputItemFunctionCallOutputOutputUnion
    
    Text, image, or file output of the function tool call.
    - string
    - type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
      
      An array of content outputs (text, image, file) for the function tool call.
      - type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
      - type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
      - type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
  - Type FunctionCallOutput
    
    The type of the function tool call output. Always function_call_output.
    - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
  - ID string
    
    The unique ID of the function tool call output. Populated when this item is returned via API.
  - Status string
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
    - const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
    - const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
- type ResponseInputItemToolSearchCall struct{…}
  - Arguments any
    
    The arguments supplied to the tool search call.
  - Type ToolSearchCall
    
    The item type. Always tool_search_call.
    - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
  - ID string
    
    The unique ID of this tool search call.
  - CallID string
    
    The unique ID of the tool search call generated by the model.
  - Execution string
    
    Whether tool search was executed by the server or by the client.
    - const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
    - const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
  - Status string
    
    The status of the tool search call.
    - const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
    - const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
    - const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
- type ResponseToolSearchOutputItemParamResp struct{…}
  - Tools []ToolUnion
    
    The loaded tool definitions returned by the tool search output.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
      - Name string
        
        The name of the function to call.
      - Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
      - Strict bool
        
        Whether to enforce strict parameter validation. Default true.
      - Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
      - DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
      - Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
      - VectorStoreIDs []string
        
        The IDs of the vector stores to search.
      - Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
      - MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
      - RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
      - Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
      - DisplayHeight int64
        
        The height of the computer display.
      - DisplayWidth int64
        
        The width of the computer display.
      - Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
      - Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
      - Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
      - SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
      - UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
      - Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
      - AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
      - Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
      - ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
      - DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
      - Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
      - RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
      - ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
      - ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
      - TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
      - Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
      - Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
      - Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
      - Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
      - Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
      - InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
      - InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
      - Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
      - Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
      - OutputCompression int64
        
        Compression level for the output image. Default: 100.
      - OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
      - PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
      - Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
      - Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
      - Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
      - Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
      - Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
      - Name string
        
        The name of the custom tool, used to identify it in tool calls.
      - Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
      - DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
      - Description string
        
        Optional description of the custom tool, used to provide more context.
      - Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
      - Description string
        
        A description of the namespace shown to the model.
      - Name string
        
        The namespace name used in tool calls (for example, crm).
      - Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
      - Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
      - Description string
        
        Description shown to the model for a client-executed tool search tool.
      - Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
      - Parameters any
        
        Parameter schema for a client-executed tool search tool.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
      - SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
      - SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
      - UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
      - Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
  - Type ToolSearchOutput
    
    The item type. Always tool_search_output.
    - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
  - ID string
    
    The unique ID of this tool search output.
  - CallID string
    
    The unique ID of the tool search call generated by the model.
  - Execution ResponseToolSearchOutputItemParamExecution
    
    Whether tool search was executed by the server or by the client.
    - const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
    - const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
  - Status ResponseToolSearchOutputItemParamStatus
    
    The status of the tool search output.
    - const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
    - const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
    - const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
- type ResponseInputItemAdditionalTools struct{…}
  - Role Developer
    
    The role that provided the additional tools. Only developer is supported.
    - const DeveloperDeveloper Developer = "developer"
  - Tools []ToolUnion
    
    A list of additional tools made available at this item.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
  - Type AdditionalTools
    
    The item type. Always additional_tools.
    - const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
  - ID string
    
    The unique ID of this additional tools item.
- type ResponseReasoningItem struct{…}
  
  A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
  - ID string
    
    The unique identifier of the reasoning content.
  - Summary []ResponseReasoningItemSummary
    
    Reasoning summary content.
    - Text string
      
      A summary of the reasoning output from the model so far.
    - Type SummaryText
      
      The type of the object. Always summary_text.
      - const SummaryTextSummaryText SummaryText = "summary_text"
  - Type Reasoning
    
    The type of the object. Always reasoning.
    - const ReasoningReasoning Reasoning = "reasoning"
  - Content []ResponseReasoningItemContent
    
    Reasoning text content.
    - Text string
      
      The reasoning text from the model.
    - Type ReasoningText
      
      The type of the reasoning text. Always reasoning_text.
      - const ReasoningTextReasoningText ReasoningText = "reasoning_text"
  - EncryptedContent string
    
    The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
  - Status ResponseReasoningItemStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
    - const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
    - const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
- type ResponseCompactionItemParamResp struct{…}
  
  A compaction item generated by the v1/responses/compact API.
  - EncryptedContent string
    
    The encrypted content of the compaction summary.
  - Type Compaction
    
    The type of the item. Always compaction.
    - const CompactionCompaction Compaction = "compaction"
  - ID string
    
    The ID of the compaction item.
- type ResponseInputItemImageGenerationCall struct{…}
  
  An image generation request made by the model.
  - ID string
    
    The unique ID of the image generation call.
  - Result string
    
    The generated image encoded in base64.
  - Status string
    
    The status of the image generation call.
    - const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
    - const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
    - const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
    - const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
  - Type ImageGenerationCall
    
    The type of the image generation call. Always image_generation_call.
    - const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
- type ResponseCodeInterpreterToolCall struct{…}
  
  A tool call to run code.
  - ID string
    
    The unique ID of the code interpreter tool call.
  - Code string
    
    The code to run, or null if not available.
  - ContainerID string
    
    The ID of the container used to run the code.
  - Outputs []ResponseCodeInterpreterToolCallOutputUnion
    
    The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
    - type ResponseCodeInterpreterToolCallOutputLogs struct{…}
      
      The logs output from the code interpreter.
      - Logs string
        
        The logs output from the code interpreter.
      - Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
    - type ResponseCodeInterpreterToolCallOutputImage struct{…}
      
      The image output from the code interpreter.
      - Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
      - URL string
        
        The URL of the image output from the code interpreter.
  - Status ResponseCodeInterpreterToolCallStatus
    
    The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
    - const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
    - const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
    - const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
    - const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
    - const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
  - Type CodeInterpreterCall
    
    The type of the code interpreter tool call. Always code_interpreter_call.
    - const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
- type ResponseInputItemLocalShellCall struct{…}
  
  A tool call to run a command on the local shell.
  - ID string
    
    The unique ID of the local shell call.
  - Action ResponseInputItemLocalShellCallAction
    
    Execute a shell command on the server.
    - Command []string
      
      The command to run.
    - Env map[string, string]
      
      Environment variables to set for the command.
    - Type Exec
      
      The type of the local shell action. Always exec.
      - const ExecExec Exec = "exec"
    - TimeoutMs int64
      
      Optional timeout in milliseconds for the command.
    - User string
      
      Optional user to run the command as.
    - WorkingDirectory string
      
      Optional working directory to run the command in.
  - CallID string
    
    The unique ID of the local shell tool call generated by the model.
  - Status string
    
    The status of the local shell call.
    - const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
    - const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
    - const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
  - Type LocalShellCall
    
    The type of the local shell call. Always local_shell_call.
    - const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
- type ResponseInputItemLocalShellCallOutput struct{…}
  
  The output of a local shell tool call.
  - ID string
    
    The unique ID of the local shell tool call generated by the model.
  - Output string
    
    A JSON string of the output of the local shell tool call.
  - Type LocalShellCallOutput
    
    The type of the local shell tool call output. Always local_shell_call_output.
    - const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
  - Status string
    
    The status of the item. One of in_progress, completed, or incomplete.
    - const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
    - const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
    - const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
- type ResponseInputItemShellCall struct{…}
  
  A tool representing a request to execute one or more shell commands.
  - Action ResponseInputItemShellCallAction
    
    The shell commands and limits that describe how to run the tool call.
    - Commands []string
      
      Ordered shell commands for the execution environment to run.
    - MaxOutputLength int64
      
      Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
    - TimeoutMs int64
      
      Maximum wall-clock time in milliseconds to allow the shell commands to run.
  - CallID string
    
    The unique ID of the shell tool call generated by the model.
  - Type ShellCall
    
    The type of the item. Always shell_call.
    - const ShellCallShellCall ShellCall = "shell_call"
  - ID string
    
    The unique ID of the shell tool call. Populated when this item is returned via API.
  - Environment ResponseInputItemShellCallEnvironmentUnion
    
    The environment to execute the shell commands in.
    - type LocalEnvironment struct{…}
    - type ContainerReference struct{…}
  - Status string
    
    The status of the shell call. One of in_progress, completed, or incomplete.
    - const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
    - const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
    - const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
- type ResponseInputItemShellCallOutput struct{…}
  
  The streamed output items emitted by a shell tool call.
  - CallID string
    
    The unique ID of the shell tool call generated by the model.
  - Output []ResponseFunctionShellCallOutputContent
    
    Captured chunks of stdout and stderr output, along with their associated outcomes.
    - Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
      
      The exit or timeout outcome associated with this shell call.
      - type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
      - type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
    - Stderr string
      
      Captured stderr output for the shell call.
    - Stdout string
      
      Captured stdout output for the shell call.
  - Type ShellCallOutput
    
    The type of the item. Always shell_call_output.
    - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
  - ID string
    
    The unique ID of the shell tool call output. Populated when this item is returned via API.
  - MaxOutputLength int64
    
    The maximum number of UTF-8 characters captured for this shell call's combined output.
  - Status string
    
    The status of the shell call output.
    - const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
    - const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
    - const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
- type ResponseInputItemApplyPatchCall struct{…}
  
  A tool call representing a request to create, delete, or update files using diff patches.
  - CallID string
    
    The unique ID of the apply patch tool call generated by the model.
  - Operation ResponseInputItemApplyPatchCallOperationUnion
    
    The specific create, delete, or update instruction for the apply_patch tool call.
    - type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
      
      Instruction for creating a new file via the apply_patch tool.
      - Diff string
        
        Unified diff content to apply when creating the file.
      - Path string
        
        Path of the file to create relative to the workspace root.
      - Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
    - type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
      
      Instruction for deleting an existing file via the apply_patch tool.
      - Path string
        
        Path of the file to delete relative to the workspace root.
      - Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
    - type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
      
      Instruction for updating an existing file via the apply_patch tool.
      - Diff string
        
        Unified diff content to apply to the existing file.
      - Path string
        
        Path of the file to update relative to the workspace root.
      - Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
  - Status string
    
    The status of the apply patch tool call. One of in_progress or completed.
    - const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
    - const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
  - Type ApplyPatchCall
    
    The type of the item. Always apply_patch_call.
    - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
  - ID string
    
    The unique ID of the apply patch tool call. Populated when this item is returned via API.
- type ResponseInputItemApplyPatchCallOutput struct{…}
  
  The streamed output emitted by an apply patch tool call.
  - CallID string
    
    The unique ID of the apply patch tool call generated by the model.
  - Status string
    
    The status of the apply patch tool call output. One of completed or failed.
    - const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
    - const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
  - Type ApplyPatchCallOutput
    
    The type of the item. Always apply_patch_call_output.
    - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
  - ID string
    
    The unique ID of the apply patch tool call output. Populated when this item is returned via API.
  - Output string
    
    Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
- type ResponseInputItemMcpListTools struct{…}
  
  A list of tools available on an MCP server.
  - ID string
    
    The unique ID of the list.
  - ServerLabel string
    
    The label of the MCP server.
  - Tools []ResponseInputItemMcpListToolsTool
    
    The tools available on the server.
    - InputSchema any
      
      The JSON schema describing the tool's input.
    - Name string
      
      The name of the tool.
    - Annotations any
      
      Additional annotations about the tool.
    - Description string
      
      The description of the tool.
  - Type McpListTools
    
    The type of the item. Always mcp_list_tools.
    - const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
  - Error string
    
    Error message if the server could not list tools.
- type ResponseInputItemMcpApprovalRequest struct{…}
  
  A request for human approval of a tool invocation.
  - ID string
    
    The unique ID of the approval request.
  - Arguments string
    
    A JSON string of arguments for the tool.
  - Name string
    
    The name of the tool to run.
  - ServerLabel string
    
    The label of the MCP server making the request.
  - Type McpApprovalRequest
    
    The type of the item. Always mcp_approval_request.
    - const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
- type ResponseInputItemMcpApprovalResponse struct{…}
  
  A response to an MCP approval request.
  - ApprovalRequestID string
    
    The ID of the approval request being answered.
  - Approve bool
    
    Whether the request was approved.
  - Type McpApprovalResponse
    
    The type of the item. Always mcp_approval_response.
    - const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
  - ID string
    
    The unique ID of the approval response
  - Reason string
    
    Optional reason for the decision.
- type ResponseInputItemMcpCall struct{…}
  
  An invocation of a tool on an MCP server.
  - ID string
    
    The unique ID of the tool call.
  - Arguments string
    
    A JSON string of the arguments passed to the tool.
  - Name string
    
    The name of the tool that was run.
  - ServerLabel string
    
    The label of the MCP server running the tool.
  - Type McpCall
    
    The type of the item. Always mcp_call.
    - const McpCallMcpCall McpCall = "mcp_call"
  - ApprovalRequestID string
    
    Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
  - Error string
    
    The error from the tool call, if any.
  - Output string
    
    The output from the tool call.
  - Status string
    
    The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
    - const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
    - const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
    - const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
    - const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
    - const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
- type ResponseCustomToolCallOutput struct{…}
  
  The output of a custom tool call from your code, being sent back to the model.
  - CallID string
    
    The call ID, used to map this custom tool call output to a custom tool call.
  - Output ResponseCustomToolCallOutputOutputUnion
    
    The output from the custom tool call generated by your code. Can be a string or an list of output content.
    - string
    - type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
      
      Text, image, or file output of the custom tool call.
      - type ResponseInputText struct{…}
        
        A text input to the model.
      - type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
      - type ResponseInputFile struct{…}
        
        A file input to the model.
  - Type CustomToolCallOutput
    
    The type of the custom tool call output. Always custom_tool_call_output.
    - const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
  - ID string
    
    The unique ID of the custom tool call output in the OpenAI platform.
- type ResponseCustomToolCall struct{…}
  
  A call to a custom tool created by the model.
  - CallID string
    
    An identifier used to map this custom tool call to a tool call output.
  - Input string
    
    The input for the custom tool call generated by the model.
  - Name string
    
    The name of the custom tool being called.
  - Type CustomToolCall
    
    The type of the custom tool call. Always custom_tool_call.
    - const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
  - ID string
    
    The unique ID of the custom tool call in the OpenAI platform.
  - Namespace string
    
    The namespace of the custom tool being called.
- type ResponseInputItemCompactionTrigger struct{…}
  
  Compacts the current context. Must be the final input item.
  - Type CompactionTrigger
    
    The type of the item. Always compaction_trigger.
    - const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
- type ResponseInputItemItemReference struct{…}
  
  An internal identifier for an item to reference.
  - ID string
    
    The ID of the item to reference.
  - Type string
    
    The type of item to reference. Always item_reference.
    - const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"

Response Input Message Content List

type ResponseInputMessageContentList []ResponseInputContentUnion

A list of one or many input items to the model, containing different content types.
- type ResponseInputText struct{…}
  
  A text input to the model.
  - Text string
    
    The text input to the model.
  - Type InputText
    
    The type of the input item. Always input_text.
    - const InputTextInputText InputText = "input_text"
- type ResponseInputImage struct{…}
  
  An image input to the model. Learn about image inputs.
  - Detail ResponseInputImageDetail
    
    The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
    - const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
    - const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
    - const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
    - const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
  - Type InputImage
    
    The type of the input item. Always input_image.
    - const InputImageInputImage InputImage = "input_image"
  - FileID string
    
    The ID of the file to be sent to the model.
  - ImageURL string
    
    The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
- type ResponseInputFile struct{…}
  
  A file input to the model.
  - Type InputFile
    
    The type of the input item. Always input_file.
    - const InputFileInputFile InputFile = "input_file"
  - Detail ResponseInputFileDetail
    
    The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
    - const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
    - const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
  - FileData string
    
    The content of the file to be sent to the model.
  - FileID string
    
    The ID of the file to be sent to the model.
  - FileURL string
    
    The URL of the file to be sent to the model.
  - Filename string
    
    The name of the file to be sent to the model.

Response Input Message Item

type ResponseInputMessageItem struct{…}
- ID string
  
  The unique ID of the message input.
- Content ResponseInputMessageContentList
  
  A list of one or many input items to the model, containing different content types.
  - type ResponseInputText struct{…}
    
    A text input to the model.
    - Text string
      
      The text input to the model.
    - Type InputText
      
      The type of the input item. Always input_text.
      - const InputTextInputText InputText = "input_text"
  - type ResponseInputImage struct{…}
    
    An image input to the model. Learn about image inputs.
    - Detail ResponseInputImageDetail
      
      The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
      - const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
      - const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
      - const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
      - const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
    - Type InputImage
      
      The type of the input item. Always input_image.
      - const InputImageInputImage InputImage = "input_image"
    - FileID string
      
      The ID of the file to be sent to the model.
    - ImageURL string
      
      The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
  - type ResponseInputFile struct{…}
    
    A file input to the model.
    - Type InputFile
      
      The type of the input item. Always input_file.
      - const InputFileInputFile InputFile = "input_file"
    - Detail ResponseInputFileDetail
      
      The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
      - const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
      - const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
    - FileData string
      
      The content of the file to be sent to the model.
    - FileID string
      
      The ID of the file to be sent to the model.
    - FileURL string
      
      The URL of the file to be sent to the model.
    - Filename string
      
      The name of the file to be sent to the model.
- Role ResponseInputMessageItemRole
  
  The role of the message input. One of user, system, or developer.
  - const ResponseInputMessageItemRoleUser ResponseInputMessageItemRole = "user"
  - const ResponseInputMessageItemRoleSystem ResponseInputMessageItemRole = "system"
  - const ResponseInputMessageItemRoleDeveloper ResponseInputMessageItemRole = "developer"
- Type Message
  
  The type of the message input. Always set to message.
  - const MessageMessage Message = "message"
- Status ResponseInputMessageItemStatus
  
  The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
  - const ResponseInputMessageItemStatusInProgress ResponseInputMessageItemStatus = "in_progress"
  - const ResponseInputMessageItemStatusCompleted ResponseInputMessageItemStatus = "completed"
  - const ResponseInputMessageItemStatusIncomplete ResponseInputMessageItemStatus = "incomplete"

Response Input Text

type ResponseInputText struct{…}

A text input to the model.
- Text string
  
  The text input to the model.
- Type InputText
  
  The type of the input item. Always input_text.
  - const InputTextInputText InputText = "input_text"

Response Input Text Content

type ResponseInputTextContent struct{…}

A text input to the model.
- Text string
  
  The text input to the model.
- Type InputText
  
  The type of the input item. Always input_text.
  - const InputTextInputText InputText = "input_text"

Response Item

type ResponseItemUnion interface{…}

Content item used to generate a response.
- type ResponseInputMessageItem struct{…}
  - ID string
    
    The unique ID of the message input.
  - Content ResponseInputMessageContentList
    
    A list of one or many input items to the model, containing different content types.
    - type ResponseInputText struct{…}
      
      A text input to the model.
      - Text string
        
        The text input to the model.
      - Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
    - type ResponseInputImage struct{…}
      
      An image input to the model. Learn about image inputs.
      - Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
      - Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
      - FileID string
        
        The ID of the file to be sent to the model.
      - ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
    - type ResponseInputFile struct{…}
      
      A file input to the model.
      - Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
      - Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
      - FileData string
        
        The content of the file to be sent to the model.
      - FileID string
        
        The ID of the file to be sent to the model.
      - FileURL string
        
        The URL of the file to be sent to the model.
      - Filename string
        
        The name of the file to be sent to the model.
  - Role ResponseInputMessageItemRole
    
    The role of the message input. One of user, system, or developer.
    - const ResponseInputMessageItemRoleUser ResponseInputMessageItemRole = "user"
    - const ResponseInputMessageItemRoleSystem ResponseInputMessageItemRole = "system"
    - const ResponseInputMessageItemRoleDeveloper ResponseInputMessageItemRole = "developer"
  - Type Message
    
    The type of the message input. Always set to message.
    - const MessageMessage Message = "message"
  - Status ResponseInputMessageItemStatus
    
    The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseInputMessageItemStatusInProgress ResponseInputMessageItemStatus = "in_progress"
    - const ResponseInputMessageItemStatusCompleted ResponseInputMessageItemStatus = "completed"
    - const ResponseInputMessageItemStatusIncomplete ResponseInputMessageItemStatus = "incomplete"
- type ResponseOutputMessage struct{…}
  
  An output message from the model.
  - ID string
    
    The unique ID of the output message.
  - Content []ResponseOutputMessageContentUnion
    
    The content of the output message.
    - type ResponseOutputText struct{…}
      
      A text output from the model.
      - Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
      - Text string
        
        The text output from the model.
      - Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
      - Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
    - type ResponseOutputRefusal struct{…}
      
      A refusal from the model.
      - Refusal string
        
        The refusal explanation from the model.
      - Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
  - Role Assistant
    
    The role of the output message. Always assistant.
    - const AssistantAssistant Assistant = "assistant"
  - Status ResponseOutputMessageStatus
    
    The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
    - const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
    - const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
    - const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
  - Type Message
    
    The type of the output message. Always message.
    - const MessageMessage Message = "message"
  - Phase ResponseOutputMessagePhase
    
    Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
    - const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
    - const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
- type ResponseFileSearchToolCall struct{…}
  
  The results of a file search tool call. See the file search guide for more information.
  - ID string
    
    The unique ID of the file search tool call.
  - Queries []string
    
    The queries used to search for files.
  - Status ResponseFileSearchToolCallStatus
    
    The status of the file search tool call. One of in_progress, searching, incomplete or failed,
    - const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
    - const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
    - const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
    - const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
    - const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
  - Type FileSearchCall
    
    The type of the file search tool call. Always file_search_call.
    - const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
  - Results []ResponseFileSearchToolCallResult
    
    The results of the file search tool call.
    - Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
      
      Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
      - string
      - float64
      - bool
    - FileID string
      
      The unique ID of the file.
    - Filename string
      
      The name of the file.
    - Score float64
      
      The relevance score of the file - a value between 0 and 1.
    - Text string
      
      The text that was retrieved from the file.
- type ResponseComputerToolCall struct{…}
  
  A tool call to a computer use tool. See the computer use guide for more information.
  - ID string
    
    The unique ID of the computer call.
  - CallID string
    
    An identifier used when responding to the tool call with output.
  - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
    
    The pending safety checks for the computer call.
    - ID string
      
      The ID of the pending safety check.
    - Code string
      
      The type of the pending safety check.
    - Message string
      
      Details about the pending safety check.
  - Status ResponseComputerToolCallStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
    - const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
    - const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
  - Type ResponseComputerToolCallType
    
    The type of the computer call. Always computer_call.
    - const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
  - Action ResponseComputerToolCallActionUnion
    
    A click action.
    - type ResponseComputerToolCallActionClick struct{…}
      
      A click action.
      - Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
      - Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
      - X int64
        
        The x-coordinate where the click occurred.
      - Y int64
        
        The y-coordinate where the click occurred.
      - Keys []string
        
        The keys being held while clicking.
    - type ResponseComputerToolCallActionDoubleClick struct{…}
      
      A double click action.
      - Keys []string
        
        The keys being held while double-clicking.
      - Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
      - X int64
        
        The x-coordinate where the double click occurred.
      - Y int64
        
        The y-coordinate where the double click occurred.
    - type ResponseComputerToolCallActionDrag struct{…}
      
      A drag action.
      - Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
      - Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
      - Keys []string
        
        The keys being held while dragging the mouse.
    - type ResponseComputerToolCallActionKeypress struct{…}
      
      A collection of keypresses the model would like to perform.
      - Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
      - Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
    - type ResponseComputerToolCallActionMove struct{…}
      
      A mouse move action.
      - Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
      - X int64
        
        The x-coordinate to move to.
      - Y int64
        
        The y-coordinate to move to.
      - Keys []string
        
        The keys being held while moving the mouse.
    - type ResponseComputerToolCallActionScreenshot struct{…}
      
      A screenshot action.
      - Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
    - type ResponseComputerToolCallActionScroll struct{…}
      
      A scroll action.
      - ScrollX int64
        
        The horizontal scroll distance.
      - ScrollY int64
        
        The vertical scroll distance.
      - Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
      - X int64
        
        The x-coordinate where the scroll occurred.
      - Y int64
        
        The y-coordinate where the scroll occurred.
      - Keys []string
        
        The keys being held while scrolling.
    - type ResponseComputerToolCallActionType struct{…}
      
      An action to type in text.
      - Text string
        
        The text to type.
      - Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
    - type ResponseComputerToolCallActionWait struct{…}
      
      A wait action.
      - Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
  - Actions ComputerActionList
    
    Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
    - type ComputerActionClick struct{…}
      
      A click action.
      - Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
      - Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
      - X int64
        
        The x-coordinate where the click occurred.
      - Y int64
        
        The y-coordinate where the click occurred.
      - Keys []string
        
        The keys being held while clicking.
    - type ComputerActionDoubleClick struct{…}
      
      A double click action.
      - Keys []string
        
        The keys being held while double-clicking.
      - Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
      - X int64
        
        The x-coordinate where the double click occurred.
      - Y int64
        
        The y-coordinate where the double click occurred.
    - type ComputerActionDrag struct{…}
      
      A drag action.
      - Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
      - Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
      - Keys []string
        
        The keys being held while dragging the mouse.
    - type ComputerActionKeypress struct{…}
      
      A collection of keypresses the model would like to perform.
      - Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
      - Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
    - type ComputerActionMove struct{…}
      
      A mouse move action.
      - Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
      - X int64
        
        The x-coordinate to move to.
      - Y int64
        
        The y-coordinate to move to.
      - Keys []string
        
        The keys being held while moving the mouse.
    - type ComputerActionScreenshot struct{…}
      
      A screenshot action.
      - Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
    - type ComputerActionScroll struct{…}
      
      A scroll action.
      - ScrollX int64
        
        The horizontal scroll distance.
      - ScrollY int64
        
        The vertical scroll distance.
      - Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
      - X int64
        
        The x-coordinate where the scroll occurred.
      - Y int64
        
        The y-coordinate where the scroll occurred.
      - Keys []string
        
        The keys being held while scrolling.
    - type ComputerActionType struct{…}
      
      An action to type in text.
      - Text string
        
        The text to type.
      - Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
    - type ComputerActionWait struct{…}
      
      A wait action.
      - Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
- type ResponseComputerToolCallOutputItem struct{…}
  - ID string
    
    The unique ID of the computer call tool output.
  - CallID string
    
    The ID of the computer tool call that produced the output.
  - Output ResponseComputerToolCallOutputScreenshot
    
    A computer screenshot image used with the computer use tool.
    - Type ComputerScreenshot
      
      Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
      - const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
    - FileID string
      
      The identifier of an uploaded file that contains the screenshot.
    - ImageURL string
      
      The URL of the screenshot image.
  - Status ResponseComputerToolCallOutputItemStatus
    
    The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
    - const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
    - const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
    - const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
    - const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
  - Type ComputerCallOutput
    
    The type of the computer tool call output. Always computer_call_output.
    - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
  - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
    
    The safety checks reported by the API that have been acknowledged by the developer.
    - ID string
      
      The ID of the pending safety check.
    - Code string
      
      The type of the pending safety check.
    - Message string
      
      Details about the pending safety check.
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseFunctionWebSearch struct{…}
  
  The results of a web search tool call. See the web search guide for more information.
  - ID string
    
    The unique ID of the web search tool call.
  - Action ResponseFunctionWebSearchActionUnion
    
    An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
    - type ResponseFunctionWebSearchActionSearch struct{…}
      
      Action type "search" - Performs a web search query.
      - Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
      - Queries []string
        
        The search queries.
      - Query string
        
        The search query.
      - Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
    - type ResponseFunctionWebSearchActionOpenPage struct{…}
      
      Action type "open_page" - Opens a specific URL from search results.
      - Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
      - URL string
        
        The URL opened by the model.
    - type ResponseFunctionWebSearchActionFindInPage struct{…}
      
      Action type "find_in_page": Searches for a pattern within a loaded page.
      - Pattern string
        
        The pattern or text to search for within the page.
      - Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
      - URL string
        
        The URL of the page searched for the pattern.
  - Status ResponseFunctionWebSearchStatus
    
    The status of the web search tool call.
    - const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
    - const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
    - const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
    - const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
  - Type WebSearchCall
    
    The type of the web search tool call. Always web_search_call.
    - const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
- type ResponseFunctionToolCallItem struct{…}
  
  A tool call to run a function. See the function calling guide for more information.
  - ID string
    
    The unique ID of the function tool call.
  - Status string
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseFunctionToolCallItemStatusInProgress ResponseFunctionToolCallItemStatus = "in_progress"
    - const ResponseFunctionToolCallItemStatusCompleted ResponseFunctionToolCallItemStatus = "completed"
    - const ResponseFunctionToolCallItemStatusIncomplete ResponseFunctionToolCallItemStatus = "incomplete"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseFunctionToolCallOutputItem struct{…}
  - ID string
    
    The unique ID of the function call tool output.
  - CallID string
    
    The unique ID of the function tool call generated by the model.
  - Output ResponseFunctionToolCallOutputItemOutputUnion
    
    The output from the function call generated by your code. Can be a string or an list of output content.
    - string
    - type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
      
      Text, image, or file output of the function call.
      - type ResponseInputText struct{…}
        
        A text input to the model.
      - type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
      - type ResponseInputFile struct{…}
        
        A file input to the model.
  - Status ResponseFunctionToolCallOutputItemStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
    - const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
    - const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
  - Type FunctionCallOutput
    
    The type of the function tool call output. Always function_call_output.
    - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseToolSearchCall struct{…}
  - ID string
    
    The unique ID of the tool search call item.
  - Arguments any
    
    Arguments used for the tool search call.
  - CallID string
    
    The unique ID of the tool search call generated by the model.
  - Execution ResponseToolSearchCallExecution
    
    Whether tool search was executed by the server or by the client.
    - const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
    - const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
  - Status ResponseToolSearchCallStatus
    
    The status of the tool search call item that was recorded.
    - const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
    - const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
    - const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
  - Type ToolSearchCall
    
    The type of the item. Always tool_search_call.
    - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseToolSearchOutputItem struct{…}
  - ID string
    
    The unique ID of the tool search output item.
  - CallID string
    
    The unique ID of the tool search call generated by the model.
  - Execution ResponseToolSearchOutputItemExecution
    
    Whether tool search was executed by the server or by the client.
    - const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
    - const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
  - Status ResponseToolSearchOutputItemStatus
    
    The status of the tool search output item that was recorded.
    - const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
    - const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
    - const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
  - Tools []ToolUnion
    
    The loaded tool definitions returned by tool search.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
      - Name string
        
        The name of the function to call.
      - Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
      - Strict bool
        
        Whether to enforce strict parameter validation. Default true.
      - Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
      - DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
      - Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
      - VectorStoreIDs []string
        
        The IDs of the vector stores to search.
      - Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
      - MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
      - RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
      - Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
      - DisplayHeight int64
        
        The height of the computer display.
      - DisplayWidth int64
        
        The width of the computer display.
      - Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
      - Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
      - Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
      - SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
      - UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
      - Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
      - AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
      - Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
      - ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
      - DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
      - Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
      - RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
      - ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
      - ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
      - TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
      - Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
      - Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
      - Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
      - Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
      - Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
      - InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
      - InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
      - Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
      - Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
      - OutputCompression int64
        
        Compression level for the output image. Default: 100.
      - OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
      - PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
      - Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
      - Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
      - Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
      - Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
      - Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
      - Name string
        
        The name of the custom tool, used to identify it in tool calls.
      - Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
      - DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
      - Description string
        
        Optional description of the custom tool, used to provide more context.
      - Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
      - Description string
        
        A description of the namespace shown to the model.
      - Name string
        
        The namespace name used in tool calls (for example, crm).
      - Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
      - Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
      - Description string
        
        Description shown to the model for a client-executed tool search tool.
      - Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
      - Parameters any
        
        Parameter schema for a client-executed tool search tool.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
      - SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
      - SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
      - UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
      - Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
  - Type ToolSearchOutput
    
    The type of the item. Always tool_search_output.
    - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseItemAdditionalTools struct{…}
  - ID string
    
    The unique ID of the additional tools item.
  - Role string
    
    The role that provided the additional tools.
    - const ResponseItemAdditionalToolsRoleUnknown ResponseItemAdditionalToolsRole = "unknown"
    - const ResponseItemAdditionalToolsRoleUser ResponseItemAdditionalToolsRole = "user"
    - const ResponseItemAdditionalToolsRoleAssistant ResponseItemAdditionalToolsRole = "assistant"
    - const ResponseItemAdditionalToolsRoleSystem ResponseItemAdditionalToolsRole = "system"
    - const ResponseItemAdditionalToolsRoleCritic ResponseItemAdditionalToolsRole = "critic"
    - const ResponseItemAdditionalToolsRoleDiscriminator ResponseItemAdditionalToolsRole = "discriminator"
    - const ResponseItemAdditionalToolsRoleDeveloper ResponseItemAdditionalToolsRole = "developer"
    - const ResponseItemAdditionalToolsRoleTool ResponseItemAdditionalToolsRole = "tool"
  - Tools []ToolUnion
    
    The additional tool definitions made available at this item.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
  - Type AdditionalTools
    
    The type of the item. Always additional_tools.
    - const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
- type ResponseReasoningItem struct{…}
  
  A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
  - ID string
    
    The unique identifier of the reasoning content.
  - Summary []ResponseReasoningItemSummary
    
    Reasoning summary content.
    - Text string
      
      A summary of the reasoning output from the model so far.
    - Type SummaryText
      
      The type of the object. Always summary_text.
      - const SummaryTextSummaryText SummaryText = "summary_text"
  - Type Reasoning
    
    The type of the object. Always reasoning.
    - const ReasoningReasoning Reasoning = "reasoning"
  - Content []ResponseReasoningItemContent
    
    Reasoning text content.
    - Text string
      
      The reasoning text from the model.
    - Type ReasoningText
      
      The type of the reasoning text. Always reasoning_text.
      - const ReasoningTextReasoningText ReasoningText = "reasoning_text"
  - EncryptedContent string
    
    The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
  - Status ResponseReasoningItemStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
    - const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
    - const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
- type ResponseCompactionItem struct{…}
  
  A compaction item generated by the v1/responses/compact API.
  - ID string
    
    The unique ID of the compaction item.
  - EncryptedContent string
    
    The encrypted content that was produced by compaction.
  - Type Compaction
    
    The type of the item. Always compaction.
    - const CompactionCompaction Compaction = "compaction"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseItemImageGenerationCall struct{…}
  
  An image generation request made by the model.
  - ID string
    
    The unique ID of the image generation call.
  - Result string
    
    The generated image encoded in base64.
  - Status string
    
    The status of the image generation call.
    - const ResponseItemImageGenerationCallStatusInProgress ResponseItemImageGenerationCallStatus = "in_progress"
    - const ResponseItemImageGenerationCallStatusCompleted ResponseItemImageGenerationCallStatus = "completed"
    - const ResponseItemImageGenerationCallStatusGenerating ResponseItemImageGenerationCallStatus = "generating"
    - const ResponseItemImageGenerationCallStatusFailed ResponseItemImageGenerationCallStatus = "failed"
  - Type ImageGenerationCall
    
    The type of the image generation call. Always image_generation_call.
    - const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
- type ResponseCodeInterpreterToolCall struct{…}
  
  A tool call to run code.
  - ID string
    
    The unique ID of the code interpreter tool call.
  - Code string
    
    The code to run, or null if not available.
  - ContainerID string
    
    The ID of the container used to run the code.
  - Outputs []ResponseCodeInterpreterToolCallOutputUnion
    
    The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
    - type ResponseCodeInterpreterToolCallOutputLogs struct{…}
      
      The logs output from the code interpreter.
      - Logs string
        
        The logs output from the code interpreter.
      - Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
    - type ResponseCodeInterpreterToolCallOutputImage struct{…}
      
      The image output from the code interpreter.
      - Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
      - URL string
        
        The URL of the image output from the code interpreter.
  - Status ResponseCodeInterpreterToolCallStatus
    
    The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
    - const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
    - const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
    - const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
    - const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
    - const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
  - Type CodeInterpreterCall
    
    The type of the code interpreter tool call. Always code_interpreter_call.
    - const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
- type ResponseItemLocalShellCall struct{…}
  
  A tool call to run a command on the local shell.
  - ID string
    
    The unique ID of the local shell call.
  - Action ResponseItemLocalShellCallAction
    
    Execute a shell command on the server.
    - Command []string
      
      The command to run.
    - Env map[string, string]
      
      Environment variables to set for the command.
    - Type Exec
      
      The type of the local shell action. Always exec.
      - const ExecExec Exec = "exec"
    - TimeoutMs int64
      
      Optional timeout in milliseconds for the command.
    - User string
      
      Optional user to run the command as.
    - WorkingDirectory string
      
      Optional working directory to run the command in.
  - CallID string
    
    The unique ID of the local shell tool call generated by the model.
  - Status string
    
    The status of the local shell call.
    - const ResponseItemLocalShellCallStatusInProgress ResponseItemLocalShellCallStatus = "in_progress"
    - const ResponseItemLocalShellCallStatusCompleted ResponseItemLocalShellCallStatus = "completed"
    - const ResponseItemLocalShellCallStatusIncomplete ResponseItemLocalShellCallStatus = "incomplete"
  - Type LocalShellCall
    
    The type of the local shell call. Always local_shell_call.
    - const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
- type ResponseItemLocalShellCallOutput struct{…}
  
  The output of a local shell tool call.
  - ID string
    
    The unique ID of the local shell tool call generated by the model.
  - Output string
    
    A JSON string of the output of the local shell tool call.
  - Type LocalShellCallOutput
    
    The type of the local shell tool call output. Always local_shell_call_output.
    - const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
  - Status string
    
    The status of the item. One of in_progress, completed, or incomplete.
    - const ResponseItemLocalShellCallOutputStatusInProgress ResponseItemLocalShellCallOutputStatus = "in_progress"
    - const ResponseItemLocalShellCallOutputStatusCompleted ResponseItemLocalShellCallOutputStatus = "completed"
    - const ResponseItemLocalShellCallOutputStatusIncomplete ResponseItemLocalShellCallOutputStatus = "incomplete"
- type ResponseFunctionShellToolCall struct{…}
  
  A tool call that executes one or more shell commands in a managed environment.
  - ID string
    
    The unique ID of the shell tool call. Populated when this item is returned via API.
  - Action ResponseFunctionShellToolCallAction
    
    The shell commands and limits that describe how to run the tool call.
    - Commands []string
    - MaxOutputLength int64
      
      Optional maximum number of characters to return from each command.
    - TimeoutMs int64
      
      Optional timeout in milliseconds for the commands.
  - CallID string
    
    The unique ID of the shell tool call generated by the model.
  - Environment ResponseFunctionShellToolCallEnvironmentUnion
    
    Represents the use of a local environment to perform shell actions.
    - type ResponseLocalEnvironment struct{…}
      
      Represents the use of a local environment to perform shell actions.
      - Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
    - type ResponseContainerReference struct{…}
      
      Represents a container created with /v1/containers.
      - ContainerID string
      - Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
  - Status ResponseFunctionShellToolCallStatus
    
    The status of the shell call. One of in_progress, completed, or incomplete.
    - const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
    - const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
    - const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
  - Type ShellCall
    
    The type of the item. Always shell_call.
    - const ShellCallShellCall ShellCall = "shell_call"
  - CreatedBy string
    
    The ID of the entity that created this tool call.
- type ResponseFunctionShellToolCallOutput struct{…}
  
  The output of a shell tool call that was emitted.
  - ID string
    
    The unique ID of the shell call output. Populated when this item is returned via API.
  - CallID string
    
    The unique ID of the shell tool call generated by the model.
  - MaxOutputLength int64
    
    The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
  - Output []ResponseFunctionShellToolCallOutputOutput
    
    An array of shell call output contents
    - Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
      
      Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
      - type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
      - type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
    - Stderr string
      
      The standard error output that was captured.
    - Stdout string
      
      The standard output that was captured.
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - Status ResponseFunctionShellToolCallOutputStatus
    
    The status of the shell call output. One of in_progress, completed, or incomplete.
    - const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
    - const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
    - const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
  - Type ShellCallOutput
    
    The type of the shell call output. Always shell_call_output.
    - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseApplyPatchToolCall struct{…}
  
  A tool call that applies file diffs by creating, deleting, or updating files.
  - ID string
    
    The unique ID of the apply patch tool call. Populated when this item is returned via API.
  - CallID string
    
    The unique ID of the apply patch tool call generated by the model.
  - Operation ResponseApplyPatchToolCallOperationUnion
    
    One of the create_file, delete_file, or update_file operations applied via apply_patch.
    - type ResponseApplyPatchToolCallOperationCreateFile struct{…}
      
      Instruction describing how to create a file via the apply_patch tool.
      - Diff string
        
        Diff to apply.
      - Path string
        
        Path of the file to create.
      - Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
    - type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
      
      Instruction describing how to delete a file via the apply_patch tool.
      - Path string
        
        Path of the file to delete.
      - Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
    - type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
      
      Instruction describing how to update a file via the apply_patch tool.
      - Diff string
        
        Diff to apply.
      - Path string
        
        Path of the file to update.
      - Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
  - Status ResponseApplyPatchToolCallStatus
    
    The status of the apply patch tool call. One of in_progress or completed.
    - const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
    - const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
  - Type ApplyPatchCall
    
    The type of the item. Always apply_patch_call.
    - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
  - CreatedBy string
    
    The ID of the entity that created this tool call.
- type ResponseApplyPatchToolCallOutput struct{…}
  
  The output emitted by an apply patch tool call.
  - ID string
    
    The unique ID of the apply patch tool call output. Populated when this item is returned via API.
  - CallID string
    
    The unique ID of the apply patch tool call generated by the model.
  - Status ResponseApplyPatchToolCallOutputStatus
    
    The status of the apply patch tool call output. One of completed or failed.
    - const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
    - const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
  - Type ApplyPatchCallOutput
    
    The type of the item. Always apply_patch_call_output.
    - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
  - CreatedBy string
    
    The ID of the entity that created this tool call output.
  - Output string
    
    Optional textual output returned by the apply patch tool.
- type ResponseItemMcpListTools struct{…}
  
  A list of tools available on an MCP server.
  - ID string
    
    The unique ID of the list.
  - ServerLabel string
    
    The label of the MCP server.
  - Tools []ResponseItemMcpListToolsTool
    
    The tools available on the server.
    - InputSchema any
      
      The JSON schema describing the tool's input.
    - Name string
      
      The name of the tool.
    - Annotations any
      
      Additional annotations about the tool.
    - Description string
      
      The description of the tool.
  - Type McpListTools
    
    The type of the item. Always mcp_list_tools.
    - const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
  - Error string
    
    Error message if the server could not list tools.
- type ResponseItemMcpApprovalRequest struct{…}
  
  A request for human approval of a tool invocation.
  - ID string
    
    The unique ID of the approval request.
  - Arguments string
    
    A JSON string of arguments for the tool.
  - Name string
    
    The name of the tool to run.
  - ServerLabel string
    
    The label of the MCP server making the request.
  - Type McpApprovalRequest
    
    The type of the item. Always mcp_approval_request.
    - const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
- type ResponseItemMcpApprovalResponse struct{…}
  
  A response to an MCP approval request.
  - ID string
    
    The unique ID of the approval response
  - ApprovalRequestID string
    
    The ID of the approval request being answered.
  - Approve bool
    
    Whether the request was approved.
  - Type McpApprovalResponse
    
    The type of the item. Always mcp_approval_response.
    - const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
  - Reason string
    
    Optional reason for the decision.
- type ResponseItemMcpCall struct{…}
  
  An invocation of a tool on an MCP server.
  - ID string
    
    The unique ID of the tool call.
  - Arguments string
    
    A JSON string of the arguments passed to the tool.
  - Name string
    
    The name of the tool that was run.
  - ServerLabel string
    
    The label of the MCP server running the tool.
  - Type McpCall
    
    The type of the item. Always mcp_call.
    - const McpCallMcpCall McpCall = "mcp_call"
  - ApprovalRequestID string
    
    Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
  - Error string
    
    The error from the tool call, if any.
  - Output string
    
    The output from the tool call.
  - Status string
    
    The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
    - const ResponseItemMcpCallStatusInProgress ResponseItemMcpCallStatus = "in_progress"
    - const ResponseItemMcpCallStatusCompleted ResponseItemMcpCallStatus = "completed"
    - const ResponseItemMcpCallStatusIncomplete ResponseItemMcpCallStatus = "incomplete"
    - const ResponseItemMcpCallStatusCalling ResponseItemMcpCallStatus = "calling"
    - const ResponseItemMcpCallStatusFailed ResponseItemMcpCallStatus = "failed"
- type ResponseCustomToolCallItem struct{…}
  
  A call to a custom tool created by the model.
  - ID string
    
    The unique ID of the custom tool call item.
  - Status string
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseCustomToolCallItemStatusInProgress ResponseCustomToolCallItemStatus = "in_progress"
    - const ResponseCustomToolCallItemStatusCompleted ResponseCustomToolCallItemStatus = "completed"
    - const ResponseCustomToolCallItemStatusIncomplete ResponseCustomToolCallItemStatus = "incomplete"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseCustomToolCallOutputItem struct{…}
  
  The output of a custom tool call from your code, being sent back to the model.
  - ID string
    
    The unique ID of the custom tool call output item.
  - Status string
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
    - const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
    - const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
  - CreatedBy string
    
    The identifier of the actor that created the item.

Response Local Environment

type ResponseLocalEnvironment struct{…}

Represents the use of a local environment to perform shell actions.
- Type Local
  
  The environment type. Always local.
  - const LocalLocal Local = "local"

Response Mcp Call Arguments Delta Event

type ResponseMcpCallArgumentsDeltaEvent struct{…}

Emitted when there is a delta (partial update) to the arguments of an MCP tool call.
- Delta string
  
  A JSON string containing the partial update to the arguments for the MCP tool call.
- ItemID string
  
  The unique identifier of the MCP tool call item being processed.
- OutputIndex int64
  
  The index of the output item in the response's output array.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseMcpCallArgumentsDelta
  
  The type of the event. Always 'response.mcp_call_arguments.delta'.
  - const ResponseMcpCallArgumentsDeltaResponseMcpCallArgumentsDelta ResponseMcpCallArgumentsDelta = "response.mcp_call_arguments.delta"

Response Mcp Call Arguments Done Event

type ResponseMcpCallArgumentsDoneEvent struct{…}

Emitted when the arguments for an MCP tool call are finalized.
- Arguments string
  
  A JSON string containing the finalized arguments for the MCP tool call.
- ItemID string
  
  The unique identifier of the MCP tool call item being processed.
- OutputIndex int64
  
  The index of the output item in the response's output array.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseMcpCallArgumentsDone
  
  The type of the event. Always 'response.mcp_call_arguments.done'.
  - const ResponseMcpCallArgumentsDoneResponseMcpCallArgumentsDone ResponseMcpCallArgumentsDone = "response.mcp_call_arguments.done"

Response Mcp Call Completed Event

type ResponseMcpCallCompletedEvent struct{…}

Emitted when an MCP tool call has completed successfully.
- ItemID string
  
  The ID of the MCP tool call item that completed.
- OutputIndex int64
  
  The index of the output item that completed.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseMcpCallCompleted
  
  The type of the event. Always 'response.mcp_call.completed'.
  - const ResponseMcpCallCompletedResponseMcpCallCompleted ResponseMcpCallCompleted = "response.mcp_call.completed"

Response Mcp Call Failed Event

type ResponseMcpCallFailedEvent struct{…}

Emitted when an MCP tool call has failed.
- ItemID string
  
  The ID of the MCP tool call item that failed.
- OutputIndex int64
  
  The index of the output item that failed.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseMcpCallFailed
  
  The type of the event. Always 'response.mcp_call.failed'.
  - const ResponseMcpCallFailedResponseMcpCallFailed ResponseMcpCallFailed = "response.mcp_call.failed"

Response Mcp Call In Progress Event

type ResponseMcpCallInProgressEvent struct{…}

Emitted when an MCP tool call is in progress.
- ItemID string
  
  The unique identifier of the MCP tool call item being processed.
- OutputIndex int64
  
  The index of the output item in the response's output array.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseMcpCallInProgress
  
  The type of the event. Always 'response.mcp_call.in_progress'.
  - const ResponseMcpCallInProgressResponseMcpCallInProgress ResponseMcpCallInProgress = "response.mcp_call.in_progress"

Response Mcp List Tools Completed Event

type ResponseMcpListToolsCompletedEvent struct{…}

Emitted when the list of available MCP tools has been successfully retrieved.
- ItemID string
  
  The ID of the MCP tool call item that produced this output.
- OutputIndex int64
  
  The index of the output item that was processed.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseMcpListToolsCompleted
  
  The type of the event. Always 'response.mcp_list_tools.completed'.
  - const ResponseMcpListToolsCompletedResponseMcpListToolsCompleted ResponseMcpListToolsCompleted = "response.mcp_list_tools.completed"

Response Mcp List Tools Failed Event

type ResponseMcpListToolsFailedEvent struct{…}

Emitted when the attempt to list available MCP tools has failed.
- ItemID string
  
  The ID of the MCP tool call item that failed.
- OutputIndex int64
  
  The index of the output item that failed.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseMcpListToolsFailed
  
  The type of the event. Always 'response.mcp_list_tools.failed'.
  - const ResponseMcpListToolsFailedResponseMcpListToolsFailed ResponseMcpListToolsFailed = "response.mcp_list_tools.failed"

Response Mcp List Tools In Progress Event

type ResponseMcpListToolsInProgressEvent struct{…}

Emitted when the system is in the process of retrieving the list of available MCP tools.
- ItemID string
  
  The ID of the MCP tool call item that is being processed.
- OutputIndex int64
  
  The index of the output item that is being processed.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseMcpListToolsInProgress
  
  The type of the event. Always 'response.mcp_list_tools.in_progress'.
  - const ResponseMcpListToolsInProgressResponseMcpListToolsInProgress ResponseMcpListToolsInProgress = "response.mcp_list_tools.in_progress"

Response Output Audio

type ResponseOutputAudio struct{…}

An audio output from the model.
- Data string
  
  Base64-encoded audio data from the model.
- Transcript string
  
  The transcript of the audio data from the model.
- Type OutputAudio
  
  The type of the output audio. Always output_audio.
  - const OutputAudioOutputAudio OutputAudio = "output_audio"

Response Output Item

type ResponseOutputItemUnion interface{…}

An output message from the model.
- type ResponseOutputMessage struct{…}
  
  An output message from the model.
  - ID string
    
    The unique ID of the output message.
  - Content []ResponseOutputMessageContentUnion
    
    The content of the output message.
    - type ResponseOutputText struct{…}
      
      A text output from the model.
      - Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
      - Text string
        
        The text output from the model.
      - Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
      - Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
    - type ResponseOutputRefusal struct{…}
      
      A refusal from the model.
      - Refusal string
        
        The refusal explanation from the model.
      - Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
  - Role Assistant
    
    The role of the output message. Always assistant.
    - const AssistantAssistant Assistant = "assistant"
  - Status ResponseOutputMessageStatus
    
    The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
    - const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
    - const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
    - const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
  - Type Message
    
    The type of the output message. Always message.
    - const MessageMessage Message = "message"
  - Phase ResponseOutputMessagePhase
    
    Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
    - const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
    - const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
- type ResponseFileSearchToolCall struct{…}
  
  The results of a file search tool call. See the file search guide for more information.
  - ID string
    
    The unique ID of the file search tool call.
  - Queries []string
    
    The queries used to search for files.
  - Status ResponseFileSearchToolCallStatus
    
    The status of the file search tool call. One of in_progress, searching, incomplete or failed,
    - const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
    - const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
    - const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
    - const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
    - const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
  - Type FileSearchCall
    
    The type of the file search tool call. Always file_search_call.
    - const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
  - Results []ResponseFileSearchToolCallResult
    
    The results of the file search tool call.
    - Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
      
      Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
      - string
      - float64
      - bool
    - FileID string
      
      The unique ID of the file.
    - Filename string
      
      The name of the file.
    - Score float64
      
      The relevance score of the file - a value between 0 and 1.
    - Text string
      
      The text that was retrieved from the file.
- type ResponseFunctionToolCall struct{…}
  
  A tool call to run a function. See the function calling guide for more information.
  - Arguments string
    
    A JSON string of the arguments to pass to the function.
  - CallID string
    
    The unique ID of the function tool call generated by the model.
  - Name string
    
    The name of the function to run.
  - Type FunctionCall
    
    The type of the function tool call. Always function_call.
    - const FunctionCallFunctionCall FunctionCall = "function_call"
  - ID string
    
    The unique ID of the function tool call.
  - Namespace string
    
    The namespace of the function to run.
  - Status ResponseFunctionToolCallStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
    - const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
    - const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
- type ResponseFunctionToolCallOutputItem struct{…}
  - ID string
    
    The unique ID of the function call tool output.
  - CallID string
    
    The unique ID of the function tool call generated by the model.
  - Output ResponseFunctionToolCallOutputItemOutputUnion
    
    The output from the function call generated by your code. Can be a string or an list of output content.
    - string
    - type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
      
      Text, image, or file output of the function call.
      - type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
      - type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
      - type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
  - Status ResponseFunctionToolCallOutputItemStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
    - const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
    - const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
  - Type FunctionCallOutput
    
    The type of the function tool call output. Always function_call_output.
    - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseFunctionWebSearch struct{…}
  
  The results of a web search tool call. See the web search guide for more information.
  - ID string
    
    The unique ID of the web search tool call.
  - Action ResponseFunctionWebSearchActionUnion
    
    An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
    - type ResponseFunctionWebSearchActionSearch struct{…}
      
      Action type "search" - Performs a web search query.
      - Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
      - Queries []string
        
        The search queries.
      - Query string
        
        The search query.
      - Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
    - type ResponseFunctionWebSearchActionOpenPage struct{…}
      
      Action type "open_page" - Opens a specific URL from search results.
      - Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
      - URL string
        
        The URL opened by the model.
    - type ResponseFunctionWebSearchActionFindInPage struct{…}
      
      Action type "find_in_page": Searches for a pattern within a loaded page.
      - Pattern string
        
        The pattern or text to search for within the page.
      - Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
      - URL string
        
        The URL of the page searched for the pattern.
  - Status ResponseFunctionWebSearchStatus
    
    The status of the web search tool call.
    - const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
    - const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
    - const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
    - const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
  - Type WebSearchCall
    
    The type of the web search tool call. Always web_search_call.
    - const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
- type ResponseComputerToolCall struct{…}
  
  A tool call to a computer use tool. See the computer use guide for more information.
  - ID string
    
    The unique ID of the computer call.
  - CallID string
    
    An identifier used when responding to the tool call with output.
  - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
    
    The pending safety checks for the computer call.
    - ID string
      
      The ID of the pending safety check.
    - Code string
      
      The type of the pending safety check.
    - Message string
      
      Details about the pending safety check.
  - Status ResponseComputerToolCallStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
    - const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
    - const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
  - Type ResponseComputerToolCallType
    
    The type of the computer call. Always computer_call.
    - const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
  - Action ResponseComputerToolCallActionUnion
    
    A click action.
    - type ResponseComputerToolCallActionClick struct{…}
      
      A click action.
      - Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
      - Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
      - X int64
        
        The x-coordinate where the click occurred.
      - Y int64
        
        The y-coordinate where the click occurred.
      - Keys []string
        
        The keys being held while clicking.
    - type ResponseComputerToolCallActionDoubleClick struct{…}
      
      A double click action.
      - Keys []string
        
        The keys being held while double-clicking.
      - Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
      - X int64
        
        The x-coordinate where the double click occurred.
      - Y int64
        
        The y-coordinate where the double click occurred.
    - type ResponseComputerToolCallActionDrag struct{…}
      
      A drag action.
      - Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
      - Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
      - Keys []string
        
        The keys being held while dragging the mouse.
    - type ResponseComputerToolCallActionKeypress struct{…}
      
      A collection of keypresses the model would like to perform.
      - Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
      - Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
    - type ResponseComputerToolCallActionMove struct{…}
      
      A mouse move action.
      - Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
      - X int64
        
        The x-coordinate to move to.
      - Y int64
        
        The y-coordinate to move to.
      - Keys []string
        
        The keys being held while moving the mouse.
    - type ResponseComputerToolCallActionScreenshot struct{…}
      
      A screenshot action.
      - Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
    - type ResponseComputerToolCallActionScroll struct{…}
      
      A scroll action.
      - ScrollX int64
        
        The horizontal scroll distance.
      - ScrollY int64
        
        The vertical scroll distance.
      - Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
      - X int64
        
        The x-coordinate where the scroll occurred.
      - Y int64
        
        The y-coordinate where the scroll occurred.
      - Keys []string
        
        The keys being held while scrolling.
    - type ResponseComputerToolCallActionType struct{…}
      
      An action to type in text.
      - Text string
        
        The text to type.
      - Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
    - type ResponseComputerToolCallActionWait struct{…}
      
      A wait action.
      - Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
  - Actions ComputerActionList
    
    Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
    - type ComputerActionClick struct{…}
      
      A click action.
      - Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
      - Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
      - X int64
        
        The x-coordinate where the click occurred.
      - Y int64
        
        The y-coordinate where the click occurred.
      - Keys []string
        
        The keys being held while clicking.
    - type ComputerActionDoubleClick struct{…}
      
      A double click action.
      - Keys []string
        
        The keys being held while double-clicking.
      - Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
      - X int64
        
        The x-coordinate where the double click occurred.
      - Y int64
        
        The y-coordinate where the double click occurred.
    - type ComputerActionDrag struct{…}
      
      A drag action.
      - Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
      - Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
      - Keys []string
        
        The keys being held while dragging the mouse.
    - type ComputerActionKeypress struct{…}
      
      A collection of keypresses the model would like to perform.
      - Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
      - Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
    - type ComputerActionMove struct{…}
      
      A mouse move action.
      - Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
      - X int64
        
        The x-coordinate to move to.
      - Y int64
        
        The y-coordinate to move to.
      - Keys []string
        
        The keys being held while moving the mouse.
    - type ComputerActionScreenshot struct{…}
      
      A screenshot action.
      - Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
    - type ComputerActionScroll struct{…}
      
      A scroll action.
      - ScrollX int64
        
        The horizontal scroll distance.
      - ScrollY int64
        
        The vertical scroll distance.
      - Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
      - X int64
        
        The x-coordinate where the scroll occurred.
      - Y int64
        
        The y-coordinate where the scroll occurred.
      - Keys []string
        
        The keys being held while scrolling.
    - type ComputerActionType struct{…}
      
      An action to type in text.
      - Text string
        
        The text to type.
      - Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
    - type ComputerActionWait struct{…}
      
      A wait action.
      - Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
- type ResponseComputerToolCallOutputItem struct{…}
  - ID string
    
    The unique ID of the computer call tool output.
  - CallID string
    
    The ID of the computer tool call that produced the output.
  - Output ResponseComputerToolCallOutputScreenshot
    
    A computer screenshot image used with the computer use tool.
    - Type ComputerScreenshot
      
      Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
      - const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
    - FileID string
      
      The identifier of an uploaded file that contains the screenshot.
    - ImageURL string
      
      The URL of the screenshot image.
  - Status ResponseComputerToolCallOutputItemStatus
    
    The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
    - const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
    - const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
    - const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
    - const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
  - Type ComputerCallOutput
    
    The type of the computer tool call output. Always computer_call_output.
    - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
  - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
    
    The safety checks reported by the API that have been acknowledged by the developer.
    - ID string
      
      The ID of the pending safety check.
    - Code string
      
      The type of the pending safety check.
    - Message string
      
      Details about the pending safety check.
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseReasoningItem struct{…}
  
  A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
  - ID string
    
    The unique identifier of the reasoning content.
  - Summary []ResponseReasoningItemSummary
    
    Reasoning summary content.
    - Text string
      
      A summary of the reasoning output from the model so far.
    - Type SummaryText
      
      The type of the object. Always summary_text.
      - const SummaryTextSummaryText SummaryText = "summary_text"
  - Type Reasoning
    
    The type of the object. Always reasoning.
    - const ReasoningReasoning Reasoning = "reasoning"
  - Content []ResponseReasoningItemContent
    
    Reasoning text content.
    - Text string
      
      The reasoning text from the model.
    - Type ReasoningText
      
      The type of the reasoning text. Always reasoning_text.
      - const ReasoningTextReasoningText ReasoningText = "reasoning_text"
  - EncryptedContent string
    
    The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
  - Status ResponseReasoningItemStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
    - const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
    - const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
- type ResponseToolSearchCall struct{…}
  - ID string
    
    The unique ID of the tool search call item.
  - Arguments any
    
    Arguments used for the tool search call.
  - CallID string
    
    The unique ID of the tool search call generated by the model.
  - Execution ResponseToolSearchCallExecution
    
    Whether tool search was executed by the server or by the client.
    - const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
    - const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
  - Status ResponseToolSearchCallStatus
    
    The status of the tool search call item that was recorded.
    - const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
    - const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
    - const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
  - Type ToolSearchCall
    
    The type of the item. Always tool_search_call.
    - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseToolSearchOutputItem struct{…}
  - ID string
    
    The unique ID of the tool search output item.
  - CallID string
    
    The unique ID of the tool search call generated by the model.
  - Execution ResponseToolSearchOutputItemExecution
    
    Whether tool search was executed by the server or by the client.
    - const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
    - const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
  - Status ResponseToolSearchOutputItemStatus
    
    The status of the tool search output item that was recorded.
    - const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
    - const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
    - const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
  - Tools []ToolUnion
    
    The loaded tool definitions returned by tool search.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
      - Name string
        
        The name of the function to call.
      - Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
      - Strict bool
        
        Whether to enforce strict parameter validation. Default true.
      - Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
      - DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
      - Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
      - VectorStoreIDs []string
        
        The IDs of the vector stores to search.
      - Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
      - MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
      - RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
      - Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
      - DisplayHeight int64
        
        The height of the computer display.
      - DisplayWidth int64
        
        The width of the computer display.
      - Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
      - Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
      - Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
      - SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
      - UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
      - Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
      - AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
      - Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
      - ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
      - DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
      - Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
      - RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
      - ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
      - ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
      - TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
      - Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
      - Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
      - Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
      - Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
      - Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
      - InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
      - InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
      - Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
      - Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
      - OutputCompression int64
        
        Compression level for the output image. Default: 100.
      - OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
      - PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
      - Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
      - Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
      - Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
      - Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
      - Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
      - Name string
        
        The name of the custom tool, used to identify it in tool calls.
      - Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
      - DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
      - Description string
        
        Optional description of the custom tool, used to provide more context.
      - Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
      - Description string
        
        A description of the namespace shown to the model.
      - Name string
        
        The namespace name used in tool calls (for example, crm).
      - Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
      - Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
      - Description string
        
        Description shown to the model for a client-executed tool search tool.
      - Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
      - Parameters any
        
        Parameter schema for a client-executed tool search tool.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
      - SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
      - SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
      - UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
      - Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
  - Type ToolSearchOutput
    
    The type of the item. Always tool_search_output.
    - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseOutputItemAdditionalTools struct{…}
  - ID string
    
    The unique ID of the additional tools item.
  - Role string
    
    The role that provided the additional tools.
    - const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
    - const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
    - const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
    - const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
    - const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
    - const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
    - const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
    - const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
  - Tools []ToolUnion
    
    The additional tool definitions made available at this item.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
  - Type AdditionalTools
    
    The type of the item. Always additional_tools.
    - const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
- type ResponseCompactionItem struct{…}
  
  A compaction item generated by the v1/responses/compact API.
  - ID string
    
    The unique ID of the compaction item.
  - EncryptedContent string
    
    The encrypted content that was produced by compaction.
  - Type Compaction
    
    The type of the item. Always compaction.
    - const CompactionCompaction Compaction = "compaction"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseOutputItemImageGenerationCall struct{…}
  
  An image generation request made by the model.
  - ID string
    
    The unique ID of the image generation call.
  - Result string
    
    The generated image encoded in base64.
  - Status string
    
    The status of the image generation call.
    - const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
    - const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
    - const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
    - const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
  - Type ImageGenerationCall
    
    The type of the image generation call. Always image_generation_call.
    - const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
- type ResponseCodeInterpreterToolCall struct{…}
  
  A tool call to run code.
  - ID string
    
    The unique ID of the code interpreter tool call.
  - Code string
    
    The code to run, or null if not available.
  - ContainerID string
    
    The ID of the container used to run the code.
  - Outputs []ResponseCodeInterpreterToolCallOutputUnion
    
    The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
    - type ResponseCodeInterpreterToolCallOutputLogs struct{…}
      
      The logs output from the code interpreter.
      - Logs string
        
        The logs output from the code interpreter.
      - Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
    - type ResponseCodeInterpreterToolCallOutputImage struct{…}
      
      The image output from the code interpreter.
      - Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
      - URL string
        
        The URL of the image output from the code interpreter.
  - Status ResponseCodeInterpreterToolCallStatus
    
    The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
    - const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
    - const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
    - const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
    - const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
    - const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
  - Type CodeInterpreterCall
    
    The type of the code interpreter tool call. Always code_interpreter_call.
    - const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
- type ResponseOutputItemLocalShellCall struct{…}
  
  A tool call to run a command on the local shell.
  - ID string
    
    The unique ID of the local shell call.
  - Action ResponseOutputItemLocalShellCallAction
    
    Execute a shell command on the server.
    - Command []string
      
      The command to run.
    - Env map[string, string]
      
      Environment variables to set for the command.
    - Type Exec
      
      The type of the local shell action. Always exec.
      - const ExecExec Exec = "exec"
    - TimeoutMs int64
      
      Optional timeout in milliseconds for the command.
    - User string
      
      Optional user to run the command as.
    - WorkingDirectory string
      
      Optional working directory to run the command in.
  - CallID string
    
    The unique ID of the local shell tool call generated by the model.
  - Status string
    
    The status of the local shell call.
    - const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
    - const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
    - const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
  - Type LocalShellCall
    
    The type of the local shell call. Always local_shell_call.
    - const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
- type ResponseOutputItemLocalShellCallOutput struct{…}
  
  The output of a local shell tool call.
  - ID string
    
    The unique ID of the local shell tool call generated by the model.
  - Output string
    
    A JSON string of the output of the local shell tool call.
  - Type LocalShellCallOutput
    
    The type of the local shell tool call output. Always local_shell_call_output.
    - const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
  - Status string
    
    The status of the item. One of in_progress, completed, or incomplete.
    - const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
    - const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
    - const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
- type ResponseFunctionShellToolCall struct{…}
  
  A tool call that executes one or more shell commands in a managed environment.
  - ID string
    
    The unique ID of the shell tool call. Populated when this item is returned via API.
  - Action ResponseFunctionShellToolCallAction
    
    The shell commands and limits that describe how to run the tool call.
    - Commands []string
    - MaxOutputLength int64
      
      Optional maximum number of characters to return from each command.
    - TimeoutMs int64
      
      Optional timeout in milliseconds for the commands.
  - CallID string
    
    The unique ID of the shell tool call generated by the model.
  - Environment ResponseFunctionShellToolCallEnvironmentUnion
    
    Represents the use of a local environment to perform shell actions.
    - type ResponseLocalEnvironment struct{…}
      
      Represents the use of a local environment to perform shell actions.
      - Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
    - type ResponseContainerReference struct{…}
      
      Represents a container created with /v1/containers.
      - ContainerID string
      - Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
  - Status ResponseFunctionShellToolCallStatus
    
    The status of the shell call. One of in_progress, completed, or incomplete.
    - const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
    - const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
    - const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
  - Type ShellCall
    
    The type of the item. Always shell_call.
    - const ShellCallShellCall ShellCall = "shell_call"
  - CreatedBy string
    
    The ID of the entity that created this tool call.
- type ResponseFunctionShellToolCallOutput struct{…}
  
  The output of a shell tool call that was emitted.
  - ID string
    
    The unique ID of the shell call output. Populated when this item is returned via API.
  - CallID string
    
    The unique ID of the shell tool call generated by the model.
  - MaxOutputLength int64
    
    The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
  - Output []ResponseFunctionShellToolCallOutputOutput
    
    An array of shell call output contents
    - Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
      
      Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
      - type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
      - type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
    - Stderr string
      
      The standard error output that was captured.
    - Stdout string
      
      The standard output that was captured.
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - Status ResponseFunctionShellToolCallOutputStatus
    
    The status of the shell call output. One of in_progress, completed, or incomplete.
    - const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
    - const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
    - const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
  - Type ShellCallOutput
    
    The type of the shell call output. Always shell_call_output.
    - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseApplyPatchToolCall struct{…}
  
  A tool call that applies file diffs by creating, deleting, or updating files.
  - ID string
    
    The unique ID of the apply patch tool call. Populated when this item is returned via API.
  - CallID string
    
    The unique ID of the apply patch tool call generated by the model.
  - Operation ResponseApplyPatchToolCallOperationUnion
    
    One of the create_file, delete_file, or update_file operations applied via apply_patch.
    - type ResponseApplyPatchToolCallOperationCreateFile struct{…}
      
      Instruction describing how to create a file via the apply_patch tool.
      - Diff string
        
        Diff to apply.
      - Path string
        
        Path of the file to create.
      - Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
    - type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
      
      Instruction describing how to delete a file via the apply_patch tool.
      - Path string
        
        Path of the file to delete.
      - Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
    - type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
      
      Instruction describing how to update a file via the apply_patch tool.
      - Diff string
        
        Diff to apply.
      - Path string
        
        Path of the file to update.
      - Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
  - Status ResponseApplyPatchToolCallStatus
    
    The status of the apply patch tool call. One of in_progress or completed.
    - const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
    - const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
  - Type ApplyPatchCall
    
    The type of the item. Always apply_patch_call.
    - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
  - CreatedBy string
    
    The ID of the entity that created this tool call.
- type ResponseApplyPatchToolCallOutput struct{…}
  
  The output emitted by an apply patch tool call.
  - ID string
    
    The unique ID of the apply patch tool call output. Populated when this item is returned via API.
  - CallID string
    
    The unique ID of the apply patch tool call generated by the model.
  - Status ResponseApplyPatchToolCallOutputStatus
    
    The status of the apply patch tool call output. One of completed or failed.
    - const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
    - const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
  - Type ApplyPatchCallOutput
    
    The type of the item. Always apply_patch_call_output.
    - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
  - CreatedBy string
    
    The ID of the entity that created this tool call output.
  - Output string
    
    Optional textual output returned by the apply patch tool.
- type ResponseOutputItemMcpCall struct{…}
  
  An invocation of a tool on an MCP server.
  - ID string
    
    The unique ID of the tool call.
  - Arguments string
    
    A JSON string of the arguments passed to the tool.
  - Name string
    
    The name of the tool that was run.
  - ServerLabel string
    
    The label of the MCP server running the tool.
  - Type McpCall
    
    The type of the item. Always mcp_call.
    - const McpCallMcpCall McpCall = "mcp_call"
  - ApprovalRequestID string
    
    Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
  - Error string
    
    The error from the tool call, if any.
  - Output string
    
    The output from the tool call.
  - Status string
    
    The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
    - const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
    - const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
    - const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
    - const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
    - const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
- type ResponseOutputItemMcpListTools struct{…}
  
  A list of tools available on an MCP server.
  - ID string
    
    The unique ID of the list.
  - ServerLabel string
    
    The label of the MCP server.
  - Tools []ResponseOutputItemMcpListToolsTool
    
    The tools available on the server.
    - InputSchema any
      
      The JSON schema describing the tool's input.
    - Name string
      
      The name of the tool.
    - Annotations any
      
      Additional annotations about the tool.
    - Description string
      
      The description of the tool.
  - Type McpListTools
    
    The type of the item. Always mcp_list_tools.
    - const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
  - Error string
    
    Error message if the server could not list tools.
- type ResponseOutputItemMcpApprovalRequest struct{…}
  
  A request for human approval of a tool invocation.
  - ID string
    
    The unique ID of the approval request.
  - Arguments string
    
    A JSON string of arguments for the tool.
  - Name string
    
    The name of the tool to run.
  - ServerLabel string
    
    The label of the MCP server making the request.
  - Type McpApprovalRequest
    
    The type of the item. Always mcp_approval_request.
    - const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
- type ResponseOutputItemMcpApprovalResponse struct{…}
  
  A response to an MCP approval request.
  - ID string
    
    The unique ID of the approval response
  - ApprovalRequestID string
    
    The ID of the approval request being answered.
  - Approve bool
    
    Whether the request was approved.
  - Type McpApprovalResponse
    
    The type of the item. Always mcp_approval_response.
    - const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
  - Reason string
    
    Optional reason for the decision.
- type ResponseCustomToolCall struct{…}
  
  A call to a custom tool created by the model.
  - CallID string
    
    An identifier used to map this custom tool call to a tool call output.
  - Input string
    
    The input for the custom tool call generated by the model.
  - Name string
    
    The name of the custom tool being called.
  - Type CustomToolCall
    
    The type of the custom tool call. Always custom_tool_call.
    - const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
  - ID string
    
    The unique ID of the custom tool call in the OpenAI platform.
  - Namespace string
    
    The namespace of the custom tool being called.
- type ResponseCustomToolCallOutputItem struct{…}
  
  The output of a custom tool call from your code, being sent back to the model.
  - ID string
    
    The unique ID of the custom tool call output item.
  - Status string
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
    - const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
    - const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
  - CreatedBy string
    
    The identifier of the actor that created the item.

Response Output Item Added Event

type ResponseOutputItemAddedEvent struct{…}

Emitted when a new output item is added.
- Item ResponseOutputItemUnion
  
  The output item that was added.
  - type ResponseOutputMessage struct{…}
    
    An output message from the model.
    - ID string
      
      The unique ID of the output message.
    - Content []ResponseOutputMessageContentUnion
      
      The content of the output message.
      - type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
      - type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
    - Role Assistant
      
      The role of the output message. Always assistant.
      - const AssistantAssistant Assistant = "assistant"
    - Status ResponseOutputMessageStatus
      
      The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
      - const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
      - const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
      - const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
    - Type Message
      
      The type of the output message. Always message.
      - const MessageMessage Message = "message"
    - Phase ResponseOutputMessagePhase
      
      Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
      - const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
      - const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
  - type ResponseFileSearchToolCall struct{…}
    
    The results of a file search tool call. See the file search guide for more information.
    - ID string
      
      The unique ID of the file search tool call.
    - Queries []string
      
      The queries used to search for files.
    - Status ResponseFileSearchToolCallStatus
      
      The status of the file search tool call. One of in_progress, searching, incomplete or failed,
      - const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
      - const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
      - const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
      - const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
      - const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
    - Type FileSearchCall
      
      The type of the file search tool call. Always file_search_call.
      - const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
    - Results []ResponseFileSearchToolCallResult
      
      The results of the file search tool call.
      - Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
      - FileID string
        
        The unique ID of the file.
      - Filename string
        
        The name of the file.
      - Score float64
        
        The relevance score of the file - a value between 0 and 1.
      - Text string
        
        The text that was retrieved from the file.
  - type ResponseFunctionToolCall struct{…}
    
    A tool call to run a function. See the function calling guide for more information.
    - Arguments string
      
      A JSON string of the arguments to pass to the function.
    - CallID string
      
      The unique ID of the function tool call generated by the model.
    - Name string
      
      The name of the function to run.
    - Type FunctionCall
      
      The type of the function tool call. Always function_call.
      - const FunctionCallFunctionCall FunctionCall = "function_call"
    - ID string
      
      The unique ID of the function tool call.
    - Namespace string
      
      The namespace of the function to run.
    - Status ResponseFunctionToolCallStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
      - const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
      - const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
  - type ResponseFunctionToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the function call tool output.
    - CallID string
      
      The unique ID of the function tool call generated by the model.
    - Output ResponseFunctionToolCallOutputItemOutputUnion
      
      The output from the function call generated by your code. Can be a string or an list of output content.
      - string
      - type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
    - Status ResponseFunctionToolCallOutputItemStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
      - const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
      - const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
    - Type FunctionCallOutput
      
      The type of the function tool call output. Always function_call_output.
      - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseFunctionWebSearch struct{…}
    
    The results of a web search tool call. See the web search guide for more information.
    - ID string
      
      The unique ID of the web search tool call.
    - Action ResponseFunctionWebSearchActionUnion
      
      An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
      - type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
      - type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
      - type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
    - Status ResponseFunctionWebSearchStatus
      
      The status of the web search tool call.
      - const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
      - const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
      - const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
      - const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
    - Type WebSearchCall
      
      The type of the web search tool call. Always web_search_call.
      - const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
  - type ResponseComputerToolCall struct{…}
    
    A tool call to a computer use tool. See the computer use guide for more information.
    - ID string
      
      The unique ID of the computer call.
    - CallID string
      
      An identifier used when responding to the tool call with output.
    - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
      
      The pending safety checks for the computer call.
      - ID string
        
        The ID of the pending safety check.
      - Code string
        
        The type of the pending safety check.
      - Message string
        
        Details about the pending safety check.
    - Status ResponseComputerToolCallStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
      - const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
      - const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
    - Type ResponseComputerToolCallType
      
      The type of the computer call. Always computer_call.
      - const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
    - Action ResponseComputerToolCallActionUnion
      
      A click action.
      - type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
      - type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
      - type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
      - type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
      - type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
      - type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
      - type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
      - type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
      - type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
    - Actions ComputerActionList
      
      Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
      - type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
      - type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
      - type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
      - type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
      - type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
      - type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
      - type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
      - type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
      - type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
  - type ResponseComputerToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the computer call tool output.
    - CallID string
      
      The ID of the computer tool call that produced the output.
    - Output ResponseComputerToolCallOutputScreenshot
      
      A computer screenshot image used with the computer use tool.
      - Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
      - FileID string
        
        The identifier of an uploaded file that contains the screenshot.
      - ImageURL string
        
        The URL of the screenshot image.
    - Status ResponseComputerToolCallOutputItemStatus
      
      The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
      - const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
      - const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
      - const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
      - const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
    - Type ComputerCallOutput
      
      The type of the computer tool call output. Always computer_call_output.
      - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
    - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
      
      The safety checks reported by the API that have been acknowledged by the developer.
      - ID string
        
        The ID of the pending safety check.
      - Code string
        
        The type of the pending safety check.
      - Message string
        
        Details about the pending safety check.
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseReasoningItem struct{…}
    
    A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
    - ID string
      
      The unique identifier of the reasoning content.
    - Summary []ResponseReasoningItemSummary
      
      Reasoning summary content.
      - Text string
        
        A summary of the reasoning output from the model so far.
      - Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
    - Type Reasoning
      
      The type of the object. Always reasoning.
      - const ReasoningReasoning Reasoning = "reasoning"
    - Content []ResponseReasoningItemContent
      
      Reasoning text content.
      - Text string
        
        The reasoning text from the model.
      - Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
    - EncryptedContent string
      
      The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
    - Status ResponseReasoningItemStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
      - const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
      - const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
  - type ResponseToolSearchCall struct{…}
    - ID string
      
      The unique ID of the tool search call item.
    - Arguments any
      
      Arguments used for the tool search call.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchCallExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
      - const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
    - Status ResponseToolSearchCallStatus
      
      The status of the tool search call item that was recorded.
      - const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
      - const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
      - const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
    - Type ToolSearchCall
      
      The type of the item. Always tool_search_call.
      - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseToolSearchOutputItem struct{…}
    - ID string
      
      The unique ID of the tool search output item.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchOutputItemExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
      - const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
    - Status ResponseToolSearchOutputItemStatus
      
      The status of the tool search output item that was recorded.
      - const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
      - const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
      - const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
    - Tools []ToolUnion
      
      The loaded tool definitions returned by tool search.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
    - Type ToolSearchOutput
      
      The type of the item. Always tool_search_output.
      - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemAdditionalTools struct{…}
    - ID string
      
      The unique ID of the additional tools item.
    - Role string
      
      The role that provided the additional tools.
      - const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
      - const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
      - const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
      - const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
      - const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
      - const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
      - const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
      - const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
    - Tools []ToolUnion
      
      The additional tool definitions made available at this item.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - Type AdditionalTools
      
      The type of the item. Always additional_tools.
      - const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
  - type ResponseCompactionItem struct{…}
    
    A compaction item generated by the v1/responses/compact API.
    - ID string
      
      The unique ID of the compaction item.
    - EncryptedContent string
      
      The encrypted content that was produced by compaction.
    - Type Compaction
      
      The type of the item. Always compaction.
      - const CompactionCompaction Compaction = "compaction"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemImageGenerationCall struct{…}
    
    An image generation request made by the model.
    - ID string
      
      The unique ID of the image generation call.
    - Result string
      
      The generated image encoded in base64.
    - Status string
      
      The status of the image generation call.
      - const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
      - const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
      - const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
      - const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
    - Type ImageGenerationCall
      
      The type of the image generation call. Always image_generation_call.
      - const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
  - type ResponseCodeInterpreterToolCall struct{…}
    
    A tool call to run code.
    - ID string
      
      The unique ID of the code interpreter tool call.
    - Code string
      
      The code to run, or null if not available.
    - ContainerID string
      
      The ID of the container used to run the code.
    - Outputs []ResponseCodeInterpreterToolCallOutputUnion
      
      The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
      - type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
      - type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
    - Status ResponseCodeInterpreterToolCallStatus
      
      The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
      - const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
      - const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
      - const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
      - const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
      - const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
    - Type CodeInterpreterCall
      
      The type of the code interpreter tool call. Always code_interpreter_call.
      - const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
  - type ResponseOutputItemLocalShellCall struct{…}
    
    A tool call to run a command on the local shell.
    - ID string
      
      The unique ID of the local shell call.
    - Action ResponseOutputItemLocalShellCallAction
      
      Execute a shell command on the server.
      - Command []string
        
        The command to run.
      - Env map[string, string]
        
        Environment variables to set for the command.
      - Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
      - User string
        
        Optional user to run the command as.
      - WorkingDirectory string
        
        Optional working directory to run the command in.
    - CallID string
      
      The unique ID of the local shell tool call generated by the model.
    - Status string
      
      The status of the local shell call.
      - const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
      - const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
    - Type LocalShellCall
      
      The type of the local shell call. Always local_shell_call.
      - const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
  - type ResponseOutputItemLocalShellCallOutput struct{…}
    
    The output of a local shell tool call.
    - ID string
      
      The unique ID of the local shell tool call generated by the model.
    - Output string
      
      A JSON string of the output of the local shell tool call.
    - Type LocalShellCallOutput
      
      The type of the local shell tool call output. Always local_shell_call_output.
      - const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete.
      - const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
      - const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
  - type ResponseFunctionShellToolCall struct{…}
    
    A tool call that executes one or more shell commands in a managed environment.
    - ID string
      
      The unique ID of the shell tool call. Populated when this item is returned via API.
    - Action ResponseFunctionShellToolCallAction
      
      The shell commands and limits that describe how to run the tool call.
      - Commands []string
      - MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - Environment ResponseFunctionShellToolCallEnvironmentUnion
      
      Represents the use of a local environment to perform shell actions.
      - type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
      - type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
    - Status ResponseFunctionShellToolCallStatus
      
      The status of the shell call. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
      - const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
      - const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
    - Type ShellCall
      
      The type of the item. Always shell_call.
      - const ShellCallShellCall ShellCall = "shell_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseFunctionShellToolCallOutput struct{…}
    
    The output of a shell tool call that was emitted.
    - ID string
      
      The unique ID of the shell call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - MaxOutputLength int64
      
      The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
    - Output []ResponseFunctionShellToolCallOutputOutput
      
      An array of shell call output contents
      - Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
      - Stderr string
        
        The standard error output that was captured.
      - Stdout string
        
        The standard output that was captured.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - Status ResponseFunctionShellToolCallOutputStatus
      
      The status of the shell call output. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
      - const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
      - const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
    - Type ShellCallOutput
      
      The type of the shell call output. Always shell_call_output.
      - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseApplyPatchToolCall struct{…}
    
    A tool call that applies file diffs by creating, deleting, or updating files.
    - ID string
      
      The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Operation ResponseApplyPatchToolCallOperationUnion
      
      One of the create_file, delete_file, or update_file operations applied via apply_patch.
      - type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
      - type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
      - type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
    - Status ResponseApplyPatchToolCallStatus
      
      The status of the apply patch tool call. One of in_progress or completed.
      - const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
      - const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
    - Type ApplyPatchCall
      
      The type of the item. Always apply_patch_call.
      - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseApplyPatchToolCallOutput struct{…}
    
    The output emitted by an apply patch tool call.
    - ID string
      
      The unique ID of the apply patch tool call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Status ResponseApplyPatchToolCallOutputStatus
      
      The status of the apply patch tool call output. One of completed or failed.
      - const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
      - const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
    - Type ApplyPatchCallOutput
      
      The type of the item. Always apply_patch_call_output.
      - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
    - CreatedBy string
      
      The ID of the entity that created this tool call output.
    - Output string
      
      Optional textual output returned by the apply patch tool.
  - type ResponseOutputItemMcpCall struct{…}
    
    An invocation of a tool on an MCP server.
    - ID string
      
      The unique ID of the tool call.
    - Arguments string
      
      A JSON string of the arguments passed to the tool.
    - Name string
      
      The name of the tool that was run.
    - ServerLabel string
      
      The label of the MCP server running the tool.
    - Type McpCall
      
      The type of the item. Always mcp_call.
      - const McpCallMcpCall McpCall = "mcp_call"
    - ApprovalRequestID string
      
      Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
    - Error string
      
      The error from the tool call, if any.
    - Output string
      
      The output from the tool call.
    - Status string
      
      The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
      - const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
      - const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
      - const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
      - const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
      - const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
  - type ResponseOutputItemMcpListTools struct{…}
    
    A list of tools available on an MCP server.
    - ID string
      
      The unique ID of the list.
    - ServerLabel string
      
      The label of the MCP server.
    - Tools []ResponseOutputItemMcpListToolsTool
      
      The tools available on the server.
      - InputSchema any
        
        The JSON schema describing the tool's input.
      - Name string
        
        The name of the tool.
      - Annotations any
        
        Additional annotations about the tool.
      - Description string
        
        The description of the tool.
    - Type McpListTools
      
      The type of the item. Always mcp_list_tools.
      - const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
    - Error string
      
      Error message if the server could not list tools.
  - type ResponseOutputItemMcpApprovalRequest struct{…}
    
    A request for human approval of a tool invocation.
    - ID string
      
      The unique ID of the approval request.
    - Arguments string
      
      A JSON string of arguments for the tool.
    - Name string
      
      The name of the tool to run.
    - ServerLabel string
      
      The label of the MCP server making the request.
    - Type McpApprovalRequest
      
      The type of the item. Always mcp_approval_request.
      - const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
  - type ResponseOutputItemMcpApprovalResponse struct{…}
    
    A response to an MCP approval request.
    - ID string
      
      The unique ID of the approval response
    - ApprovalRequestID string
      
      The ID of the approval request being answered.
    - Approve bool
      
      Whether the request was approved.
    - Type McpApprovalResponse
      
      The type of the item. Always mcp_approval_response.
      - const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
    - Reason string
      
      Optional reason for the decision.
  - type ResponseCustomToolCall struct{…}
    
    A call to a custom tool created by the model.
    - CallID string
      
      An identifier used to map this custom tool call to a tool call output.
    - Input string
      
      The input for the custom tool call generated by the model.
    - Name string
      
      The name of the custom tool being called.
    - Type CustomToolCall
      
      The type of the custom tool call. Always custom_tool_call.
      - const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
    - ID string
      
      The unique ID of the custom tool call in the OpenAI platform.
    - Namespace string
      
      The namespace of the custom tool being called.
  - type ResponseCustomToolCallOutputItem struct{…}
    
    The output of a custom tool call from your code, being sent back to the model.
    - ID string
      
      The unique ID of the custom tool call output item.
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
      - const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
      - const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
    - CreatedBy string
      
      The identifier of the actor that created the item.
- OutputIndex int64
  
  The index of the output item that was added.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseOutputItemAdded
  
  The type of the event. Always response.output_item.added.
  - const ResponseOutputItemAddedResponseOutputItemAdded ResponseOutputItemAdded = "response.output_item.added"

Response Output Item Done Event

type ResponseOutputItemDoneEvent struct{…}

Emitted when an output item is marked done.
- Item ResponseOutputItemUnion
  
  The output item that was marked done.
  - type ResponseOutputMessage struct{…}
    
    An output message from the model.
    - ID string
      
      The unique ID of the output message.
    - Content []ResponseOutputMessageContentUnion
      
      The content of the output message.
      - type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
      - type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
    - Role Assistant
      
      The role of the output message. Always assistant.
      - const AssistantAssistant Assistant = "assistant"
    - Status ResponseOutputMessageStatus
      
      The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
      - const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
      - const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
      - const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
    - Type Message
      
      The type of the output message. Always message.
      - const MessageMessage Message = "message"
    - Phase ResponseOutputMessagePhase
      
      Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
      - const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
      - const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
  - type ResponseFileSearchToolCall struct{…}
    
    The results of a file search tool call. See the file search guide for more information.
    - ID string
      
      The unique ID of the file search tool call.
    - Queries []string
      
      The queries used to search for files.
    - Status ResponseFileSearchToolCallStatus
      
      The status of the file search tool call. One of in_progress, searching, incomplete or failed,
      - const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
      - const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
      - const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
      - const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
      - const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
    - Type FileSearchCall
      
      The type of the file search tool call. Always file_search_call.
      - const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
    - Results []ResponseFileSearchToolCallResult
      
      The results of the file search tool call.
      - Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
      - FileID string
        
        The unique ID of the file.
      - Filename string
        
        The name of the file.
      - Score float64
        
        The relevance score of the file - a value between 0 and 1.
      - Text string
        
        The text that was retrieved from the file.
  - type ResponseFunctionToolCall struct{…}
    
    A tool call to run a function. See the function calling guide for more information.
    - Arguments string
      
      A JSON string of the arguments to pass to the function.
    - CallID string
      
      The unique ID of the function tool call generated by the model.
    - Name string
      
      The name of the function to run.
    - Type FunctionCall
      
      The type of the function tool call. Always function_call.
      - const FunctionCallFunctionCall FunctionCall = "function_call"
    - ID string
      
      The unique ID of the function tool call.
    - Namespace string
      
      The namespace of the function to run.
    - Status ResponseFunctionToolCallStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
      - const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
      - const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
  - type ResponseFunctionToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the function call tool output.
    - CallID string
      
      The unique ID of the function tool call generated by the model.
    - Output ResponseFunctionToolCallOutputItemOutputUnion
      
      The output from the function call generated by your code. Can be a string or an list of output content.
      - string
      - type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
    - Status ResponseFunctionToolCallOutputItemStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
      - const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
      - const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
    - Type FunctionCallOutput
      
      The type of the function tool call output. Always function_call_output.
      - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseFunctionWebSearch struct{…}
    
    The results of a web search tool call. See the web search guide for more information.
    - ID string
      
      The unique ID of the web search tool call.
    - Action ResponseFunctionWebSearchActionUnion
      
      An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
      - type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
      - type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
      - type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
    - Status ResponseFunctionWebSearchStatus
      
      The status of the web search tool call.
      - const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
      - const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
      - const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
      - const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
    - Type WebSearchCall
      
      The type of the web search tool call. Always web_search_call.
      - const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
  - type ResponseComputerToolCall struct{…}
    
    A tool call to a computer use tool. See the computer use guide for more information.
    - ID string
      
      The unique ID of the computer call.
    - CallID string
      
      An identifier used when responding to the tool call with output.
    - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
      
      The pending safety checks for the computer call.
      - ID string
        
        The ID of the pending safety check.
      - Code string
        
        The type of the pending safety check.
      - Message string
        
        Details about the pending safety check.
    - Status ResponseComputerToolCallStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
      - const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
      - const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
    - Type ResponseComputerToolCallType
      
      The type of the computer call. Always computer_call.
      - const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
    - Action ResponseComputerToolCallActionUnion
      
      A click action.
      - type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
      - type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
      - type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
      - type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
      - type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
      - type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
      - type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
      - type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
      - type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
    - Actions ComputerActionList
      
      Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
      - type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
      - type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
      - type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
      - type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
      - type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
      - type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
      - type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
      - type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
      - type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
  - type ResponseComputerToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the computer call tool output.
    - CallID string
      
      The ID of the computer tool call that produced the output.
    - Output ResponseComputerToolCallOutputScreenshot
      
      A computer screenshot image used with the computer use tool.
      - Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
      - FileID string
        
        The identifier of an uploaded file that contains the screenshot.
      - ImageURL string
        
        The URL of the screenshot image.
    - Status ResponseComputerToolCallOutputItemStatus
      
      The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
      - const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
      - const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
      - const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
      - const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
    - Type ComputerCallOutput
      
      The type of the computer tool call output. Always computer_call_output.
      - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
    - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
      
      The safety checks reported by the API that have been acknowledged by the developer.
      - ID string
        
        The ID of the pending safety check.
      - Code string
        
        The type of the pending safety check.
      - Message string
        
        Details about the pending safety check.
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseReasoningItem struct{…}
    
    A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
    - ID string
      
      The unique identifier of the reasoning content.
    - Summary []ResponseReasoningItemSummary
      
      Reasoning summary content.
      - Text string
        
        A summary of the reasoning output from the model so far.
      - Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
    - Type Reasoning
      
      The type of the object. Always reasoning.
      - const ReasoningReasoning Reasoning = "reasoning"
    - Content []ResponseReasoningItemContent
      
      Reasoning text content.
      - Text string
        
        The reasoning text from the model.
      - Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
    - EncryptedContent string
      
      The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
    - Status ResponseReasoningItemStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
      - const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
      - const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
  - type ResponseToolSearchCall struct{…}
    - ID string
      
      The unique ID of the tool search call item.
    - Arguments any
      
      Arguments used for the tool search call.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchCallExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
      - const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
    - Status ResponseToolSearchCallStatus
      
      The status of the tool search call item that was recorded.
      - const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
      - const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
      - const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
    - Type ToolSearchCall
      
      The type of the item. Always tool_search_call.
      - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseToolSearchOutputItem struct{…}
    - ID string
      
      The unique ID of the tool search output item.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchOutputItemExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
      - const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
    - Status ResponseToolSearchOutputItemStatus
      
      The status of the tool search output item that was recorded.
      - const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
      - const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
      - const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
    - Tools []ToolUnion
      
      The loaded tool definitions returned by tool search.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
    - Type ToolSearchOutput
      
      The type of the item. Always tool_search_output.
      - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemAdditionalTools struct{…}
    - ID string
      
      The unique ID of the additional tools item.
    - Role string
      
      The role that provided the additional tools.
      - const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
      - const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
      - const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
      - const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
      - const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
      - const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
      - const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
      - const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
    - Tools []ToolUnion
      
      The additional tool definitions made available at this item.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - Type AdditionalTools
      
      The type of the item. Always additional_tools.
      - const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
  - type ResponseCompactionItem struct{…}
    
    A compaction item generated by the v1/responses/compact API.
    - ID string
      
      The unique ID of the compaction item.
    - EncryptedContent string
      
      The encrypted content that was produced by compaction.
    - Type Compaction
      
      The type of the item. Always compaction.
      - const CompactionCompaction Compaction = "compaction"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseOutputItemImageGenerationCall struct{…}
    
    An image generation request made by the model.
    - ID string
      
      The unique ID of the image generation call.
    - Result string
      
      The generated image encoded in base64.
    - Status string
      
      The status of the image generation call.
      - const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
      - const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
      - const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
      - const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
    - Type ImageGenerationCall
      
      The type of the image generation call. Always image_generation_call.
      - const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
  - type ResponseCodeInterpreterToolCall struct{…}
    
    A tool call to run code.
    - ID string
      
      The unique ID of the code interpreter tool call.
    - Code string
      
      The code to run, or null if not available.
    - ContainerID string
      
      The ID of the container used to run the code.
    - Outputs []ResponseCodeInterpreterToolCallOutputUnion
      
      The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
      - type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
      - type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
    - Status ResponseCodeInterpreterToolCallStatus
      
      The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
      - const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
      - const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
      - const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
      - const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
      - const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
    - Type CodeInterpreterCall
      
      The type of the code interpreter tool call. Always code_interpreter_call.
      - const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
  - type ResponseOutputItemLocalShellCall struct{…}
    
    A tool call to run a command on the local shell.
    - ID string
      
      The unique ID of the local shell call.
    - Action ResponseOutputItemLocalShellCallAction
      
      Execute a shell command on the server.
      - Command []string
        
        The command to run.
      - Env map[string, string]
        
        Environment variables to set for the command.
      - Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
      - User string
        
        Optional user to run the command as.
      - WorkingDirectory string
        
        Optional working directory to run the command in.
    - CallID string
      
      The unique ID of the local shell tool call generated by the model.
    - Status string
      
      The status of the local shell call.
      - const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
      - const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
    - Type LocalShellCall
      
      The type of the local shell call. Always local_shell_call.
      - const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
  - type ResponseOutputItemLocalShellCallOutput struct{…}
    
    The output of a local shell tool call.
    - ID string
      
      The unique ID of the local shell tool call generated by the model.
    - Output string
      
      A JSON string of the output of the local shell tool call.
    - Type LocalShellCallOutput
      
      The type of the local shell tool call output. Always local_shell_call_output.
      - const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete.
      - const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
      - const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
      - const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
  - type ResponseFunctionShellToolCall struct{…}
    
    A tool call that executes one or more shell commands in a managed environment.
    - ID string
      
      The unique ID of the shell tool call. Populated when this item is returned via API.
    - Action ResponseFunctionShellToolCallAction
      
      The shell commands and limits that describe how to run the tool call.
      - Commands []string
      - MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - Environment ResponseFunctionShellToolCallEnvironmentUnion
      
      Represents the use of a local environment to perform shell actions.
      - type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
      - type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
    - Status ResponseFunctionShellToolCallStatus
      
      The status of the shell call. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
      - const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
      - const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
    - Type ShellCall
      
      The type of the item. Always shell_call.
      - const ShellCallShellCall ShellCall = "shell_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseFunctionShellToolCallOutput struct{…}
    
    The output of a shell tool call that was emitted.
    - ID string
      
      The unique ID of the shell call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - MaxOutputLength int64
      
      The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
    - Output []ResponseFunctionShellToolCallOutputOutput
      
      An array of shell call output contents
      - Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
      - Stderr string
        
        The standard error output that was captured.
      - Stdout string
        
        The standard output that was captured.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - Status ResponseFunctionShellToolCallOutputStatus
      
      The status of the shell call output. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
      - const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
      - const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
    - Type ShellCallOutput
      
      The type of the shell call output. Always shell_call_output.
      - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseApplyPatchToolCall struct{…}
    
    A tool call that applies file diffs by creating, deleting, or updating files.
    - ID string
      
      The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Operation ResponseApplyPatchToolCallOperationUnion
      
      One of the create_file, delete_file, or update_file operations applied via apply_patch.
      - type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
      - type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
      - type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
    - Status ResponseApplyPatchToolCallStatus
      
      The status of the apply patch tool call. One of in_progress or completed.
      - const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
      - const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
    - Type ApplyPatchCall
      
      The type of the item. Always apply_patch_call.
      - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseApplyPatchToolCallOutput struct{…}
    
    The output emitted by an apply patch tool call.
    - ID string
      
      The unique ID of the apply patch tool call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Status ResponseApplyPatchToolCallOutputStatus
      
      The status of the apply patch tool call output. One of completed or failed.
      - const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
      - const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
    - Type ApplyPatchCallOutput
      
      The type of the item. Always apply_patch_call_output.
      - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
    - CreatedBy string
      
      The ID of the entity that created this tool call output.
    - Output string
      
      Optional textual output returned by the apply patch tool.
  - type ResponseOutputItemMcpCall struct{…}
    
    An invocation of a tool on an MCP server.
    - ID string
      
      The unique ID of the tool call.
    - Arguments string
      
      A JSON string of the arguments passed to the tool.
    - Name string
      
      The name of the tool that was run.
    - ServerLabel string
      
      The label of the MCP server running the tool.
    - Type McpCall
      
      The type of the item. Always mcp_call.
      - const McpCallMcpCall McpCall = "mcp_call"
    - ApprovalRequestID string
      
      Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
    - Error string
      
      The error from the tool call, if any.
    - Output string
      
      The output from the tool call.
    - Status string
      
      The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
      - const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
      - const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
      - const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
      - const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
      - const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
  - type ResponseOutputItemMcpListTools struct{…}
    
    A list of tools available on an MCP server.
    - ID string
      
      The unique ID of the list.
    - ServerLabel string
      
      The label of the MCP server.
    - Tools []ResponseOutputItemMcpListToolsTool
      
      The tools available on the server.
      - InputSchema any
        
        The JSON schema describing the tool's input.
      - Name string
        
        The name of the tool.
      - Annotations any
        
        Additional annotations about the tool.
      - Description string
        
        The description of the tool.
    - Type McpListTools
      
      The type of the item. Always mcp_list_tools.
      - const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
    - Error string
      
      Error message if the server could not list tools.
  - type ResponseOutputItemMcpApprovalRequest struct{…}
    
    A request for human approval of a tool invocation.
    - ID string
      
      The unique ID of the approval request.
    - Arguments string
      
      A JSON string of arguments for the tool.
    - Name string
      
      The name of the tool to run.
    - ServerLabel string
      
      The label of the MCP server making the request.
    - Type McpApprovalRequest
      
      The type of the item. Always mcp_approval_request.
      - const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
  - type ResponseOutputItemMcpApprovalResponse struct{…}
    
    A response to an MCP approval request.
    - ID string
      
      The unique ID of the approval response
    - ApprovalRequestID string
      
      The ID of the approval request being answered.
    - Approve bool
      
      Whether the request was approved.
    - Type McpApprovalResponse
      
      The type of the item. Always mcp_approval_response.
      - const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
    - Reason string
      
      Optional reason for the decision.
  - type ResponseCustomToolCall struct{…}
    
    A call to a custom tool created by the model.
    - CallID string
      
      An identifier used to map this custom tool call to a tool call output.
    - Input string
      
      The input for the custom tool call generated by the model.
    - Name string
      
      The name of the custom tool being called.
    - Type CustomToolCall
      
      The type of the custom tool call. Always custom_tool_call.
      - const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
    - ID string
      
      The unique ID of the custom tool call in the OpenAI platform.
    - Namespace string
      
      The namespace of the custom tool being called.
  - type ResponseCustomToolCallOutputItem struct{…}
    
    The output of a custom tool call from your code, being sent back to the model.
    - ID string
      
      The unique ID of the custom tool call output item.
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
      - const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
      - const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
    - CreatedBy string
      
      The identifier of the actor that created the item.
- OutputIndex int64
  
  The index of the output item that was marked done.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseOutputItemDone
  
  The type of the event. Always response.output_item.done.
  - const ResponseOutputItemDoneResponseOutputItemDone ResponseOutputItemDone = "response.output_item.done"

Response Output Message

type ResponseOutputMessage struct{…}

An output message from the model.
- ID string
  
  The unique ID of the output message.
- Content []ResponseOutputMessageContentUnion
  
  The content of the output message.
  - type ResponseOutputText struct{…}
    
    A text output from the model.
    - Annotations []ResponseOutputTextAnnotationUnion
      
      The annotations of the text output.
      - type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
      - type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
      - type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
      - type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
    - Text string
      
      The text output from the model.
    - Type OutputText
      
      The type of the output text. Always output_text.
      - const OutputTextOutputText OutputText = "output_text"
    - Logprobs []ResponseOutputTextLogprob
      - Token string
      - Bytes []int64
      - Logprob float64
      - TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
  - type ResponseOutputRefusal struct{…}
    
    A refusal from the model.
    - Refusal string
      
      The refusal explanation from the model.
    - Type Refusal
      
      The type of the refusal. Always refusal.
      - const RefusalRefusal Refusal = "refusal"
- Role Assistant
  
  The role of the output message. Always assistant.
  - const AssistantAssistant Assistant = "assistant"
- Status ResponseOutputMessageStatus
  
  The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
  - const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
  - const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
  - const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
- Type Message
  
  The type of the output message. Always message.
  - const MessageMessage Message = "message"
- Phase ResponseOutputMessagePhase
  
  Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
  - const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
  - const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"

Response Output Refusal

type ResponseOutputRefusal struct{…}

A refusal from the model.
- Refusal string
  
  The refusal explanation from the model.
- Type Refusal
  
  The type of the refusal. Always refusal.
  - const RefusalRefusal Refusal = "refusal"

Response Output Text

type ResponseOutputText struct{…}

A text output from the model.
- Annotations []ResponseOutputTextAnnotationUnion
  
  The annotations of the text output.
  - type ResponseOutputTextAnnotationFileCitation struct{…}
    
    A citation to a file.
    - FileID string
      
      The ID of the file.
    - Filename string
      
      The filename of the file cited.
    - Index int64
      
      The index of the file in the list of files.
    - Type FileCitation
      
      The type of the file citation. Always file_citation.
      - const FileCitationFileCitation FileCitation = "file_citation"
  - type ResponseOutputTextAnnotationURLCitation struct{…}
    
    A citation for a web resource used to generate a model response.
    - EndIndex int64
      
      The index of the last character of the URL citation in the message.
    - StartIndex int64
      
      The index of the first character of the URL citation in the message.
    - Title string
      
      The title of the web resource.
    - Type URLCitation
      
      The type of the URL citation. Always url_citation.
      - const URLCitationURLCitation URLCitation = "url_citation"
    - URL string
      
      The URL of the web resource.
  - type ResponseOutputTextAnnotationContainerFileCitation struct{…}
    
    A citation for a container file used to generate a model response.
    - ContainerID string
      
      The ID of the container file.
    - EndIndex int64
      
      The index of the last character of the container file citation in the message.
    - FileID string
      
      The ID of the file.
    - Filename string
      
      The filename of the container file cited.
    - StartIndex int64
      
      The index of the first character of the container file citation in the message.
    - Type ContainerFileCitation
      
      The type of the container file citation. Always container_file_citation.
      - const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
  - type ResponseOutputTextAnnotationFilePath struct{…}
    
    A path to a file.
    - FileID string
      
      The ID of the file.
    - Index int64
      
      The index of the file in the list of files.
    - Type FilePath
      
      The type of the file path. Always file_path.
      - const FilePathFilePath FilePath = "file_path"
- Text string
  
  The text output from the model.
- Type OutputText
  
  The type of the output text. Always output_text.
  - const OutputTextOutputText OutputText = "output_text"
- Logprobs []ResponseOutputTextLogprob
  - Token string
  - Bytes []int64
  - Logprob float64
  - TopLogprobs []ResponseOutputTextLogprobTopLogprob
    - Token string
    - Bytes []int64
    - Logprob float64

Response Output Text Annotation Added Event

type ResponseOutputTextAnnotationAddedEvent struct{…}

Emitted when an annotation is added to output text content.
- Annotation any
  
  The annotation object being added. (See annotation schema for details.)
- AnnotationIndex int64
  
  The index of the annotation within the content part.
- ContentIndex int64
  
  The index of the content part within the output item.
- ItemID string
  
  The unique identifier of the item to which the annotation is being added.
- OutputIndex int64
  
  The index of the output item in the response's output array.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseOutputTextAnnotationAdded
  
  The type of the event. Always 'response.output_text.annotation.added'.
  - const ResponseOutputTextAnnotationAddedResponseOutputTextAnnotationAdded ResponseOutputTextAnnotationAdded = "response.output_text.annotation.added"

Response Prompt

type ResponsePrompt struct{…}

Reference to a prompt template and its variables. Learn more.
- ID string
  
  The unique identifier of the prompt template to use.
- Variables map[string, ResponsePromptVariableUnion]
  
  Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
  - string
  - type ResponseInputText struct{…}
    
    A text input to the model.
    - Text string
      
      The text input to the model.
    - Type InputText
      
      The type of the input item. Always input_text.
      - const InputTextInputText InputText = "input_text"
  - type ResponseInputImage struct{…}
    
    An image input to the model. Learn about image inputs.
    - Detail ResponseInputImageDetail
      
      The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
      - const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
      - const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
      - const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
      - const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
    - Type InputImage
      
      The type of the input item. Always input_image.
      - const InputImageInputImage InputImage = "input_image"
    - FileID string
      
      The ID of the file to be sent to the model.
    - ImageURL string
      
      The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
  - type ResponseInputFile struct{…}
    
    A file input to the model.
    - Type InputFile
      
      The type of the input item. Always input_file.
      - const InputFileInputFile InputFile = "input_file"
    - Detail ResponseInputFileDetail
      
      The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
      - const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
      - const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
    - FileData string
      
      The content of the file to be sent to the model.
    - FileID string
      
      The ID of the file to be sent to the model.
    - FileURL string
      
      The URL of the file to be sent to the model.
    - Filename string
      
      The name of the file to be sent to the model.
- Version string
  
  Optional version of the prompt template.

Response Queued Event

type ResponseQueuedEvent struct{…}

Emitted when a response is queued and waiting to be processed.
- Response Response
  
  The full response object that is queued.
  - ID string
    
    Unique identifier for this Response.
  - CreatedAt float64
    
    Unix timestamp (in seconds) of when this Response was created.
  - Error ResponseError
    
    An error object returned when the model fails to generate a Response.
    - Code ResponseErrorCode
      
      The error code for the response.
      - const ResponseErrorCodeServerError ResponseErrorCode = "server_error"
      - const ResponseErrorCodeRateLimitExceeded ResponseErrorCode = "rate_limit_exceeded"
      - const ResponseErrorCodeInvalidPrompt ResponseErrorCode = "invalid_prompt"
      - const ResponseErrorCodeVectorStoreTimeout ResponseErrorCode = "vector_store_timeout"
      - const ResponseErrorCodeInvalidImage ResponseErrorCode = "invalid_image"
      - const ResponseErrorCodeInvalidImageFormat ResponseErrorCode = "invalid_image_format"
      - const ResponseErrorCodeInvalidBase64Image ResponseErrorCode = "invalid_base64_image"
      - const ResponseErrorCodeInvalidImageURL ResponseErrorCode = "invalid_image_url"
      - const ResponseErrorCodeImageTooLarge ResponseErrorCode = "image_too_large"
      - const ResponseErrorCodeImageTooSmall ResponseErrorCode = "image_too_small"
      - const ResponseErrorCodeImageParseError ResponseErrorCode = "image_parse_error"
      - const ResponseErrorCodeImageContentPolicyViolation ResponseErrorCode = "image_content_policy_violation"
      - const ResponseErrorCodeInvalidImageMode ResponseErrorCode = "invalid_image_mode"
      - const ResponseErrorCodeImageFileTooLarge ResponseErrorCode = "image_file_too_large"
      - const ResponseErrorCodeUnsupportedImageMediaType ResponseErrorCode = "unsupported_image_media_type"
      - const ResponseErrorCodeEmptyImageFile ResponseErrorCode = "empty_image_file"
      - const ResponseErrorCodeFailedToDownloadImage ResponseErrorCode = "failed_to_download_image"
      - const ResponseErrorCodeImageFileNotFound ResponseErrorCode = "image_file_not_found"
    - Message string
      
      A human-readable description of the error.
  - IncompleteDetails ResponseIncompleteDetails
    
    Details about why the response is incomplete.
    - Reason string
      
      The reason why the response is incomplete.
      - const ResponseIncompleteDetailsReasonMaxOutputTokens ResponseIncompleteDetailsReason = "max_output_tokens"
      - const ResponseIncompleteDetailsReasonContentFilter ResponseIncompleteDetailsReason = "content_filter"
  - Instructions ResponseInstructionsUnion
    
    A system (or developer) message inserted into the model's context.
    
    When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
    - string
    - type ResponseInstructionsInputItemList []ResponseInputItemUnion
      
      A list of one or many input items to the model, containing different content types.
      - type EasyInputMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
        
        Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
        
        Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
        
        Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
      - type ResponseInputItemMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
        
        Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
        
        Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
        
        Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
        
        Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
      - type ResponseOutputMessage struct{…}
        
        An output message from the model.
        
        ID string
        
        The unique ID of the output message.
        
        Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
        
        Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
        
        Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
        
        Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
        
        Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
      - type ResponseFileSearchToolCall struct{…}
        
        The results of a file search tool call. See the file search guide for more information.
        
        ID string
        
        The unique ID of the file search tool call.
        
        Queries []string
        
        The queries used to search for files.
        
        Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
        
        Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
        
        Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
      - type ResponseComputerToolCall struct{…}
        
        A tool call to a computer use tool. See the computer use guide for more information.
        
        ID string
        
        The unique ID of the computer call.
        
        CallID string
        
        An identifier used when responding to the tool call with output.
        
        PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
        
        Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
        
        Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
        
        Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
      - type ResponseInputItemComputerCallOutput struct{…}
        
        The output of a computer tool call.
        
        CallID string
        
        The ID of the computer tool call that produced the output.
        
        Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
        
        Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
        
        ID string
        
        The ID of the computer tool call output.
        
        AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
      - type ResponseFunctionWebSearch struct{…}
        
        The results of a web search tool call. See the web search guide for more information.
        
        ID string
        
        The unique ID of the web search tool call.
        
        Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
        
        Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
        
        Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
      - type ResponseFunctionToolCall struct{…}
        
        A tool call to run a function. See the function calling guide for more information.
        
        Arguments string
        
        A JSON string of the arguments to pass to the function.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Name string
        
        The name of the function to run.
        
        Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
        
        ID string
        
        The unique ID of the function tool call.
        
        Namespace string
        
        The namespace of the function to run.
        
        Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
      - type ResponseInputItemFunctionCallOutput struct{…}
        
        The output of a function tool call.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
        
        ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
      - type ResponseInputItemToolSearchCall struct{…}
        
        Arguments any
        
        The arguments supplied to the tool search call.
        
        Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
        
        ID string
        
        The unique ID of this tool search call.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
        
        Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
      - type ResponseToolSearchOutputItemParamResp struct{…}
        
        Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
        
        Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
        
        ID string
        
        The unique ID of this tool search output.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
        
        Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
      - type ResponseInputItemAdditionalTools struct{…}
        
        Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
        
        Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
        
        ID string
        
        The unique ID of this additional tools item.
      - type ResponseReasoningItem struct{…}
        
        A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
        
        ID string
        
        The unique identifier of the reasoning content.
        
        Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
        
        Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
        
        Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
        
        EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
        
        Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
      - type ResponseCompactionItemParamResp struct{…}
        
        A compaction item generated by the v1/responses/compact API.
        
        EncryptedContent string
        
        The encrypted content of the compaction summary.
        
        Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
        
        ID string
        
        The ID of the compaction item.
      - type ResponseInputItemImageGenerationCall struct{…}
        
        An image generation request made by the model.
        
        ID string
        
        The unique ID of the image generation call.
        
        Result string
        
        The generated image encoded in base64.
        
        Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
        
        Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
      - type ResponseCodeInterpreterToolCall struct{…}
        
        A tool call to run code.
        
        ID string
        
        The unique ID of the code interpreter tool call.
        
        Code string
        
        The code to run, or null if not available.
        
        ContainerID string
        
        The ID of the container used to run the code.
        
        Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
        
        Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
        
        Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
      - type ResponseInputItemLocalShellCall struct{…}
        
        A tool call to run a command on the local shell.
        
        ID string
        
        The unique ID of the local shell call.
        
        Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
        
        CallID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
        
        Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
      - type ResponseInputItemLocalShellCallOutput struct{…}
        
        The output of a local shell tool call.
        
        ID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Output string
        
        A JSON string of the output of the local shell tool call.
        
        Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
      - type ResponseInputItemShellCall struct{…}
        
        A tool representing a request to execute one or more shell commands.
        
        Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
        
        ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
        
        Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
        
        Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
      - type ResponseInputItemShellCallOutput struct{…}
        
        The streamed output items emitted by a shell tool call.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
        
        Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
        
        ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
        
        MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
        
        Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
      - type ResponseInputItemApplyPatchCall struct{…}
        
        A tool call representing a request to create, delete, or update files using diff patches.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
        
        Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
        
        Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
        
        ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
      - type ResponseInputItemApplyPatchCallOutput struct{…}
        
        The streamed output emitted by an apply patch tool call.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
        
        Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
        
        ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
        
        Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
      - type ResponseInputItemMcpListTools struct{…}
        
        A list of tools available on an MCP server.
        
        ID string
        
        The unique ID of the list.
        
        ServerLabel string
        
        The label of the MCP server.
        
        Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
        
        Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
        
        Error string
        
        Error message if the server could not list tools.
      - type ResponseInputItemMcpApprovalRequest struct{…}
        
        A request for human approval of a tool invocation.
        
        ID string
        
        The unique ID of the approval request.
        
        Arguments string
        
        A JSON string of arguments for the tool.
        
        Name string
        
        The name of the tool to run.
        
        ServerLabel string
        
        The label of the MCP server making the request.
        
        Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
      - type ResponseInputItemMcpApprovalResponse struct{…}
        
        A response to an MCP approval request.
        
        ApprovalRequestID string
        
        The ID of the approval request being answered.
        
        Approve bool
        
        Whether the request was approved.
        
        Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
        
        ID string
        
        The unique ID of the approval response
        
        Reason string
        
        Optional reason for the decision.
      - type ResponseInputItemMcpCall struct{…}
        
        An invocation of a tool on an MCP server.
        
        ID string
        
        The unique ID of the tool call.
        
        Arguments string
        
        A JSON string of the arguments passed to the tool.
        
        Name string
        
        The name of the tool that was run.
        
        ServerLabel string
        
        The label of the MCP server running the tool.
        
        Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
        
        ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
        
        Error string
        
        The error from the tool call, if any.
        
        Output string
        
        The output from the tool call.
        
        Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
      - type ResponseCustomToolCallOutput struct{…}
        
        The output of a custom tool call from your code, being sent back to the model.
        
        CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
        
        Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
        
        ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
      - type ResponseCustomToolCall struct{…}
        
        A call to a custom tool created by the model.
        
        CallID string
        
        An identifier used to map this custom tool call to a tool call output.
        
        Input string
        
        The input for the custom tool call generated by the model.
        
        Name string
        
        The name of the custom tool being called.
        
        Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
        
        ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
        
        Namespace string
        
        The namespace of the custom tool being called.
      - type ResponseInputItemCompactionTrigger struct{…}
        
        Compacts the current context. Must be the final input item.
        
        Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
      - type ResponseInputItemItemReference struct{…}
        
        An internal identifier for an item to reference.
        
        ID string
        
        The ID of the item to reference.
        
        Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
  - Metadata Metadata
    
    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
    
    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
  - Model ResponsesModel
    
    Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
    - string
    - type ChatModel string
      - const ChatModelGPT5_4 ChatModel = "gpt-5.4"
      - const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"
      - const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"
      - const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"
      - const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"
      - const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"
      - const ChatModelGPT5_2 ChatModel = "gpt-5.2"
      - const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"
      - const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"
      - const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"
      - const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"
      - const ChatModelGPT5_1 ChatModel = "gpt-5.1"
      - const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"
      - const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"
      - const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"
      - const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"
      - const ChatModelGPT5 ChatModel = "gpt-5"
      - const ChatModelGPT5Mini ChatModel = "gpt-5-mini"
      - const ChatModelGPT5Nano ChatModel = "gpt-5-nano"
      - const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"
      - const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"
      - const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"
      - const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"
      - const ChatModelGPT4_1 ChatModel = "gpt-4.1"
      - const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"
      - const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"
      - const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"
      - const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"
      - const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"
      - const ChatModelO4Mini ChatModel = "o4-mini"
      - const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"
      - const ChatModelO3 ChatModel = "o3"
      - const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"
      - const ChatModelO3Mini ChatModel = "o3-mini"
      - const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"
      - const ChatModelO1 ChatModel = "o1"
      - const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"
      - const ChatModelO1Preview ChatModel = "o1-preview"
      - const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"
      - const ChatModelO1Mini ChatModel = "o1-mini"
      - const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"
      - const ChatModelGPT4o ChatModel = "gpt-4o"
      - const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"
      - const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"
      - const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"
      - const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"
      - const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"
      - const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"
      - const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"
      - const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"
      - const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"
      - const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"
      - const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"
      - const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"
      - const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"
      - const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"
      - const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"
      - const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"
      - const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"
      - const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"
      - const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"
      - const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"
      - const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"
      - const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"
      - const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"
      - const ChatModelGPT4 ChatModel = "gpt-4"
      - const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"
      - const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"
      - const ChatModelGPT4_32k ChatModel = "gpt-4-32k"
      - const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"
      - const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"
      - const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"
      - const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"
      - const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"
      - const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"
      - const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"
      - const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"
      - const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"
    - type ResponsesModel string
      - const ResponsesModelO1Pro ResponsesModel = "o1-pro"
      - const ResponsesModelO1Pro2025_03_19 ResponsesModel = "o1-pro-2025-03-19"
      - const ResponsesModelO3Pro ResponsesModel = "o3-pro"
      - const ResponsesModelO3Pro2025_06_10 ResponsesModel = "o3-pro-2025-06-10"
      - const ResponsesModelO3DeepResearch ResponsesModel = "o3-deep-research"
      - const ResponsesModelO3DeepResearch2025_06_26 ResponsesModel = "o3-deep-research-2025-06-26"
      - const ResponsesModelO4MiniDeepResearch ResponsesModel = "o4-mini-deep-research"
      - const ResponsesModelO4MiniDeepResearch2025_06_26 ResponsesModel = "o4-mini-deep-research-2025-06-26"
      - const ResponsesModelComputerUsePreview ResponsesModel = "computer-use-preview"
      - const ResponsesModelComputerUsePreview2025_03_11 ResponsesModel = "computer-use-preview-2025-03-11"
      - const ResponsesModelGPT5Codex ResponsesModel = "gpt-5-codex"
      - const ResponsesModelGPT5Pro ResponsesModel = "gpt-5-pro"
      - const ResponsesModelGPT5Pro2025_10_06 ResponsesModel = "gpt-5-pro-2025-10-06"
      - const ResponsesModelGPT5_1CodexMax ResponsesModel = "gpt-5.1-codex-max"
  - Object Response
    
    The object type of this resource - always set to response.
    - const ResponseResponse Response = "response"
  - Output []ResponseOutputItemUnion
    
    An array of content items generated by the model.
    - The length and order of items in the output array is dependent on the model's response.
    - Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
    - type ResponseFunctionToolCallOutputItem struct{…}
      - ID string
        
        The unique ID of the function call tool output.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Output ResponseFunctionToolCallOutputItemOutputUnion
        
        The output from the function call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Status ResponseFunctionToolCallOutputItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
        
        const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
        
        const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
      - Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
    - type ResponseComputerToolCallOutputItem struct{…}
      - ID string
        
        The unique ID of the computer call tool output.
      - CallID string
        
        The ID of the computer tool call that produced the output.
      - Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
      - Status ResponseComputerToolCallOutputItemStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
        
        const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
        
        const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
        
        const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
      - Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
      - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
    - type ResponseToolSearchCall struct{…}
      - ID string
        
        The unique ID of the tool search call item.
      - Arguments any
        
        Arguments used for the tool search call.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchCallExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
        
        const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
      - Status ResponseToolSearchCallStatus
        
        The status of the tool search call item that was recorded.
        
        const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
        
        const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
        
        const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
      - Type ToolSearchCall
        
        The type of the item. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseToolSearchOutputItem struct{…}
      - ID string
        
        The unique ID of the tool search output item.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchOutputItemExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
        
        const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
      - Status ResponseToolSearchOutputItemStatus
        
        The status of the tool search output item that was recorded.
        
        const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
        
        const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
        
        const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
      - Tools []ToolUnion
        
        The loaded tool definitions returned by tool search.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type ToolSearchOutput
        
        The type of the item. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseOutputItemAdditionalTools struct{…}
      - ID string
        
        The unique ID of the additional tools item.
      - Role string
        
        The role that provided the additional tools.
        
        const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
        
        const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
        
        const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
        
        const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
        
        const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
        
        const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
        
        const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
        
        const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
      - Tools []ToolUnion
        
        The additional tool definitions made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type AdditionalTools
        
        The type of the item. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
    - type ResponseCompactionItem struct{…}
      
      A compaction item generated by the v1/responses/compact API.
      - ID string
        
        The unique ID of the compaction item.
      - EncryptedContent string
        
        The encrypted content that was produced by compaction.
      - Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseOutputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
      - ID string
        
        The unique ID of the image generation call.
      - Result string
        
        The generated image encoded in base64.
      - Status string
        
        The status of the image generation call.
        
        const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
        
        const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
        
        const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
      - Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
    - type ResponseOutputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
      - ID string
        
        The unique ID of the local shell call.
      - Action ResponseOutputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
      - CallID string
        
        The unique ID of the local shell tool call generated by the model.
      - Status string
        
        The status of the local shell call.
        
        const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
        
        const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
      - Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
    - type ResponseOutputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
      - ID string
        
        The unique ID of the local shell tool call generated by the model.
      - Output string
        
        A JSON string of the output of the local shell tool call.
      - Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
    - type ResponseFunctionShellToolCall struct{…}
      
      A tool call that executes one or more shell commands in a managed environment.
      - ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
      - Action ResponseFunctionShellToolCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Environment ResponseFunctionShellToolCallEnvironmentUnion
        
        Represents the use of a local environment to perform shell actions.
        
        type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
        
        type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
      - Status ResponseFunctionShellToolCallStatus
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
        
        const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
        
        const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
      - Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
      - CreatedBy string
        
        The ID of the entity that created this tool call.
    - type ResponseFunctionShellToolCallOutput struct{…}
      
      The output of a shell tool call that was emitted.
      - ID string
        
        The unique ID of the shell call output. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - MaxOutputLength int64
        
        The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
      - Output []ResponseFunctionShellToolCallOutputOutput
        
        An array of shell call output contents
        
        Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        The standard error output that was captured.
        
        Stdout string
        
        The standard output that was captured.
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - Status ResponseFunctionShellToolCallOutputStatus
        
        The status of the shell call output. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
        
        const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
        
        const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
      - Type ShellCallOutput
        
        The type of the shell call output. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - type ResponseApplyPatchToolCall struct{…}
      
      A tool call that applies file diffs by creating, deleting, or updating files.
      - ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Operation ResponseApplyPatchToolCallOperationUnion
        
        One of the create_file, delete_file, or update_file operations applied via apply_patch.
        
        type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
      - Status ResponseApplyPatchToolCallStatus
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
        
        const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
      - Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
      - CreatedBy string
        
        The ID of the entity that created this tool call.
    - type ResponseApplyPatchToolCallOutput struct{…}
      
      The output emitted by an apply patch tool call.
      - ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Status ResponseApplyPatchToolCallOutputStatus
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
        
        const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
      - Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
      - CreatedBy string
        
        The ID of the entity that created this tool call output.
      - Output string
        
        Optional textual output returned by the apply patch tool.
    - type ResponseOutputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
      - ID string
        
        The unique ID of the tool call.
      - Arguments string
        
        A JSON string of the arguments passed to the tool.
      - Name string
        
        The name of the tool that was run.
      - ServerLabel string
        
        The label of the MCP server running the tool.
      - Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
      - ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
      - Error string
        
        The error from the tool call, if any.
      - Output string
        
        The output from the tool call.
      - Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
        
        const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
        
        const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
        
        const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
        
        const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
    - type ResponseOutputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
      - ID string
        
        The unique ID of the list.
      - ServerLabel string
        
        The label of the MCP server.
      - Tools []ResponseOutputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
      - Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
      - Error string
        
        Error message if the server could not list tools.
    - type ResponseOutputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
      - ID string
        
        The unique ID of the approval request.
      - Arguments string
        
        A JSON string of arguments for the tool.
      - Name string
        
        The name of the tool to run.
      - ServerLabel string
        
        The label of the MCP server making the request.
      - Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
    - type ResponseOutputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
      - ID string
        
        The unique ID of the approval response
      - ApprovalRequestID string
        
        The ID of the approval request being answered.
      - Approve bool
        
        Whether the request was approved.
      - Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
      - Reason string
        
        Optional reason for the decision.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
    - type ResponseCustomToolCallOutputItem struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
      - ID string
        
        The unique ID of the custom tool call output item.
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
        
        const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
        
        const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
      - CreatedBy string
        
        The identifier of the actor that created the item.
  - ParallelToolCalls bool
    
    Whether to allow the model to run tool calls in parallel.
  - Temperature float64
    
    What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
  - ToolChoice ResponseToolChoiceUnion
    
    How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.
    - type ToolChoiceOptions string
      
      Controls which (if any) tool is called by the model.
      
      none means the model will not call any tool and instead generates a message.
      
      auto means the model can pick between generating a message or calling one or more tools.
      
      required means the model must call one or more tools.
      - const ToolChoiceOptionsNone ToolChoiceOptions = "none"
      - const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
      - const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
    - type ToolChoiceAllowed struct{…}
      
      Constrains the tools available to the model to a pre-defined set.
      - Mode ToolChoiceAllowedMode
        
        Constrains the tools available to the model to a pre-defined set.
        
        auto allows the model to pick from among the allowed tools and generate a message.
        
        required requires the model to call one or more of the allowed tools.
        
        const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
        
        const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
      - Tools []map[string, any]
        
        A list of tool definitions that the model should be allowed to call.
        
        For the Responses API, the list of tool definitions might look like:
        
        [ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ]
      - Type AllowedTools
        
        Allowed tool configuration type. Always allowed_tools.
        
        const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
    - type ToolChoiceTypes struct{…}
      
      Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
      - Type ToolChoiceTypesType
        
        The type of hosted tool the model should to use. Learn more about built-in tools.
        
        Allowed values are:
        
        file_search
        
        web_search_preview
        
        computer
        
        computer_use_preview
        
        computer_use
        
        code_interpreter
        
        image_generation
        
        const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
        
        const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
        
        const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
        
        const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
        
        const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
        
        const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
        
        const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
        
        const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
    - type ToolChoiceFunction struct{…}
      
      Use this option to force the model to call a specific function.
      - Name string
        
        The name of the function to call.
      - Type Function
        
        For function calling, the type is always function.
        
        const FunctionFunction Function = "function"
    - type ToolChoiceMcp struct{…}
      
      Use this option to force the model to call a specific tool on a remote MCP server.
      - ServerLabel string
        
        The label of the MCP server to use.
      - Type Mcp
        
        For MCP tools, the type is always mcp.
        
        const McpMcp Mcp = "mcp"
      - Name string
        
        The name of the tool to call on the server.
    - type ToolChoiceCustom struct{…}
      
      Use this option to force the model to call a specific custom tool.
      - Name string
        
        The name of the custom tool to call.
      - Type Custom
        
        For custom tool calling, the type is always custom.
        
        const CustomCustom Custom = "custom"
    - type ToolChoiceApplyPatch struct{…}
      
      Forces the model to call the apply_patch tool when executing a tool call.
      - Type ApplyPatch
        
        The tool to call. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
    - type ToolChoiceShell struct{…}
      
      Forces the model to call the shell tool when a tool call is required.
      - Type Shell
        
        The tool to call. Always shell.
        
        const ShellShell Shell = "shell"
  - Tools []ToolUnion
    
    An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
    
    We support the following categories of tools:
    - Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
    - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
    - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
  - TopP float64
    
    An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
    
    We generally recommend altering this or temperature but not both.
  - Background bool
    
    Whether to run the model response in the background. Learn more.
  - CompletedAt float64
    
    Unix timestamp (in seconds) of when this Response was completed. Only present when the status is completed.
  - Conversation ResponseConversation
    
    The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
    - ID string
      
      The unique ID of the conversation that this response was associated with.
  - MaxOutputTokens int64
    
    An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
  - MaxToolCalls int64
    
    The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
  - Moderation ResponseModeration
    
    Moderation results for the response input and output, if moderated completions were requested.
    - Input ResponseModerationInputUnion
      
      Moderation for the response input.
      - type ResponseModerationInputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeText ResponseModerationInputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeImage ResponseModerationInputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
      - type ResponseModerationInputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
    - Output ResponseModerationOutputUnion
      
      Moderation for the response output.
      - type ResponseModerationOutputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeText ResponseModerationOutputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeImage ResponseModerationOutputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
      - type ResponseModerationOutputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
  - PreviousResponseID string
    
    The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
  - Prompt ResponsePrompt
    
    Reference to a prompt template and its variables. Learn more.
    - ID string
      
      The unique identifier of the prompt template to use.
    - Variables map[string, ResponsePromptVariableUnion]
      
      Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
      - string
      - type ResponseInputText struct{…}
        
        A text input to the model.
      - type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
      - type ResponseInputFile struct{…}
        
        A file input to the model.
    - Version string
      
      Optional version of the prompt template.
  - PromptCacheKey string
    
    Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
  - PromptCacheRetention ResponsePromptCacheRetention
    
    The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.
    
    For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:
    - Organizations without ZDR enabled default to 24h.
    - Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.
    - const ResponsePromptCacheRetentionInMemory ResponsePromptCacheRetention = "in_memory"
    - const ResponsePromptCacheRetention24h ResponsePromptCacheRetention = "24h"
  - Reasoning Reasoning
    
    gpt-5 and o-series models only
    
    Configuration options for reasoning models.
    - Context ReasoningContext
      
      Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
      - const ReasoningContextAuto ReasoningContext = "auto"
      - const ReasoningContextCurrentTurn ReasoningContext = "current_turn"
      - const ReasoningContextAllTurns ReasoningContext = "all_turns"
    - Effort ReasoningEffort
      
      Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
      - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
      - All models before gpt-5.1 default to medium reasoning effort, and do not support none.
      - The gpt-5-pro model defaults to (and only supports) high reasoning effort.
      - xhigh is supported for all models after gpt-5.1-codex-max.
      - const ReasoningEffortNone ReasoningEffort = "none"
      - const ReasoningEffortMinimal ReasoningEffort = "minimal"
      - const ReasoningEffortLow ReasoningEffort = "low"
      - const ReasoningEffortMedium ReasoningEffort = "medium"
      - const ReasoningEffortHigh ReasoningEffort = "high"
      - const ReasoningEffortXhigh ReasoningEffort = "xhigh"
    - GenerateSummary ReasoningGenerateSummary
      
      Deprecated: use summary instead.
      
      A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
      - const ReasoningGenerateSummaryAuto ReasoningGenerateSummary = "auto"
      - const ReasoningGenerateSummaryConcise ReasoningGenerateSummary = "concise"
      - const ReasoningGenerateSummaryDetailed ReasoningGenerateSummary = "detailed"
    - Summary ReasoningSummary
      
      A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
      
      concise is supported for computer-use-preview models and all reasoning models after gpt-5.
      - const ReasoningSummaryAuto ReasoningSummary = "auto"
      - const ReasoningSummaryConcise ReasoningSummary = "concise"
      - const ReasoningSummaryDetailed ReasoningSummary = "detailed"
  - SafetyIdentifier string
    
    A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
  - ServiceTier ResponseServiceTier
    
    Specifies the processing type used for serving the request.
    - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
    - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
    - If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
    - When not set, the default behavior is 'auto'.
    When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
    - const ResponseServiceTierAuto ResponseServiceTier = "auto"
    - const ResponseServiceTierDefault ResponseServiceTier = "default"
    - const ResponseServiceTierFlex ResponseServiceTier = "flex"
    - const ResponseServiceTierScale ResponseServiceTier = "scale"
    - const ResponseServiceTierPriority ResponseServiceTier = "priority"
  - Status ResponseStatus
    
    The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
    - const ResponseStatusCompleted ResponseStatus = "completed"
    - const ResponseStatusFailed ResponseStatus = "failed"
    - const ResponseStatusInProgress ResponseStatus = "in_progress"
    - const ResponseStatusCancelled ResponseStatus = "cancelled"
    - const ResponseStatusQueued ResponseStatus = "queued"
    - const ResponseStatusIncomplete ResponseStatus = "incomplete"
  - Text ResponseTextConfig
    
    Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
    - Text inputs and outputs
    - Structured Outputs
    - Format ResponseFormatTextConfigUnion
      
      An object specifying the format that the model must output.
      
      Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
      
      The default format is { "type": "text" } with no additional options.
      
      Not recommended for gpt-4o and newer models:
      
      Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
      - type ResponseFormatText struct{…}
        
        Default response format. Used to generate text responses.
        
        Type Text
        
        The type of response format being defined. Always text.
        
        const TextText Text = "text"
      - type ResponseFormatTextJSONSchemaConfig struct{…}
        
        JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
        
        Name string
        
        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
        
        Schema map[string, any]
        
        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
        
        Type JSONSchema
        
        The type of response format being defined. Always json_schema.
        
        const JSONSchemaJSONSchema JSONSchema = "json_schema"
        
        Description string
        
        A description of what the response format is for, used by the model to determine how to respond in the format.
        
        Strict bool
        
        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
      - type ResponseFormatJSONObject struct{…}
        
        JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
        
        Type JSONObject
        
        The type of response format being defined. Always json_object.
        
        const JSONObjectJSONObject JSONObject = "json_object"
    - Verbosity ResponseTextConfigVerbosity
      
      Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
      - const ResponseTextConfigVerbosityLow ResponseTextConfigVerbosity = "low"
      - const ResponseTextConfigVerbosityMedium ResponseTextConfigVerbosity = "medium"
      - const ResponseTextConfigVerbosityHigh ResponseTextConfigVerbosity = "high"
  - TopLogprobs int64
    
    An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
  - Truncation ResponseTruncation
    
    The truncation strategy to use for the model response.
    - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
    - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
    - const ResponseTruncationAuto ResponseTruncation = "auto"
    - const ResponseTruncationDisabled ResponseTruncation = "disabled"
  - Usage ResponseUsage
    
    Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
    - InputTokens int64
      
      The number of input tokens.
    - InputTokensDetails ResponseUsageInputTokensDetails
      
      A detailed breakdown of the input tokens.
      - CachedTokens int64
        
        The number of tokens that were retrieved from the cache. More on prompt caching.
    - OutputTokens int64
      
      The number of output tokens.
    - OutputTokensDetails ResponseUsageOutputTokensDetails
      
      A detailed breakdown of the output tokens.
      - ReasoningTokens int64
        
        The number of reasoning tokens.
    - TotalTokens int64
      
      The total number of tokens used.
  - User string
    
    This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
- SequenceNumber int64
  
  The sequence number for this event.
- Type ResponseQueued
  
  The type of the event. Always 'response.queued'.
  - const ResponseQueuedResponseQueued ResponseQueued = "response.queued"

Response Reasoning Item

type ResponseReasoningItem struct{…}

A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
- ID string
  
  The unique identifier of the reasoning content.
- Summary []ResponseReasoningItemSummary
  
  Reasoning summary content.
  - Text string
    
    A summary of the reasoning output from the model so far.
  - Type SummaryText
    
    The type of the object. Always summary_text.
    - const SummaryTextSummaryText SummaryText = "summary_text"
- Type Reasoning
  
  The type of the object. Always reasoning.
  - const ReasoningReasoning Reasoning = "reasoning"
- Content []ResponseReasoningItemContent
  
  Reasoning text content.
  - Text string
    
    The reasoning text from the model.
  - Type ReasoningText
    
    The type of the reasoning text. Always reasoning_text.
    - const ReasoningTextReasoningText ReasoningText = "reasoning_text"
- EncryptedContent string
  
  The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
- Status ResponseReasoningItemStatus
  
  The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
  - const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
  - const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
  - const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"

Response Reasoning Summary Part Added Event

type ResponseReasoningSummaryPartAddedEvent struct{…}

Emitted when a new reasoning summary part is added.
- ItemID string
  
  The ID of the item this summary part is associated with.
- OutputIndex int64
  
  The index of the output item this summary part is associated with.
- Part ResponseReasoningSummaryPartAddedEventPart
  
  The summary part that was added.
  - Text string
    
    The text of the summary part.
  - Type SummaryText
    
    The type of the summary part. Always summary_text.
    - const SummaryTextSummaryText SummaryText = "summary_text"
- SequenceNumber int64
  
  The sequence number of this event.
- SummaryIndex int64
  
  The index of the summary part within the reasoning summary.
- Type ResponseReasoningSummaryPartAdded
  
  The type of the event. Always response.reasoning_summary_part.added.
  - const ResponseReasoningSummaryPartAddedResponseReasoningSummaryPartAdded ResponseReasoningSummaryPartAdded = "response.reasoning_summary_part.added"

Response Reasoning Summary Part Done Event

type ResponseReasoningSummaryPartDoneEvent struct{…}

Emitted when a reasoning summary part is completed.
- ItemID string
  
  The ID of the item this summary part is associated with.
- OutputIndex int64
  
  The index of the output item this summary part is associated with.
- Part ResponseReasoningSummaryPartDoneEventPart
  
  The completed summary part.
  - Text string
    
    The text of the summary part.
  - Type SummaryText
    
    The type of the summary part. Always summary_text.
    - const SummaryTextSummaryText SummaryText = "summary_text"
- SequenceNumber int64
  
  The sequence number of this event.
- SummaryIndex int64
  
  The index of the summary part within the reasoning summary.
- Type ResponseReasoningSummaryPartDone
  
  The type of the event. Always response.reasoning_summary_part.done.
  - const ResponseReasoningSummaryPartDoneResponseReasoningSummaryPartDone ResponseReasoningSummaryPartDone = "response.reasoning_summary_part.done"

Response Reasoning Summary Text Delta Event

type ResponseReasoningSummaryTextDeltaEvent struct{…}

Emitted when a delta is added to a reasoning summary text.
- Delta string
  
  The text delta that was added to the summary.
- ItemID string
  
  The ID of the item this summary text delta is associated with.
- OutputIndex int64
  
  The index of the output item this summary text delta is associated with.
- SequenceNumber int64
  
  The sequence number of this event.
- SummaryIndex int64
  
  The index of the summary part within the reasoning summary.
- Type ResponseReasoningSummaryTextDelta
  
  The type of the event. Always response.reasoning_summary_text.delta.
  - const ResponseReasoningSummaryTextDeltaResponseReasoningSummaryTextDelta ResponseReasoningSummaryTextDelta = "response.reasoning_summary_text.delta"

Response Reasoning Summary Text Done Event

type ResponseReasoningSummaryTextDoneEvent struct{…}

Emitted when a reasoning summary text is completed.
- ItemID string
  
  The ID of the item this summary text is associated with.
- OutputIndex int64
  
  The index of the output item this summary text is associated with.
- SequenceNumber int64
  
  The sequence number of this event.
- SummaryIndex int64
  
  The index of the summary part within the reasoning summary.
- Text string
  
  The full text of the completed reasoning summary.
- Type ResponseReasoningSummaryTextDone
  
  The type of the event. Always response.reasoning_summary_text.done.
  - const ResponseReasoningSummaryTextDoneResponseReasoningSummaryTextDone ResponseReasoningSummaryTextDone = "response.reasoning_summary_text.done"

Response Reasoning Text Delta Event

type ResponseReasoningTextDeltaEvent struct{…}

Emitted when a delta is added to a reasoning text.
- ContentIndex int64
  
  The index of the reasoning content part this delta is associated with.
- Delta string
  
  The text delta that was added to the reasoning content.
- ItemID string
  
  The ID of the item this reasoning text delta is associated with.
- OutputIndex int64
  
  The index of the output item this reasoning text delta is associated with.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseReasoningTextDelta
  
  The type of the event. Always response.reasoning_text.delta.
  - const ResponseReasoningTextDeltaResponseReasoningTextDelta ResponseReasoningTextDelta = "response.reasoning_text.delta"

Response Reasoning Text Done Event

type ResponseReasoningTextDoneEvent struct{…}

Emitted when a reasoning text is completed.
- ContentIndex int64
  
  The index of the reasoning content part.
- ItemID string
  
  The ID of the item this reasoning text is associated with.
- OutputIndex int64
  
  The index of the output item this reasoning text is associated with.
- SequenceNumber int64
  
  The sequence number of this event.
- Text string
  
  The full text of the completed reasoning content.
- Type ResponseReasoningTextDone
  
  The type of the event. Always response.reasoning_text.done.
  - const ResponseReasoningTextDoneResponseReasoningTextDone ResponseReasoningTextDone = "response.reasoning_text.done"

Response Refusal Delta Event

type ResponseRefusalDeltaEvent struct{…}

Emitted when there is a partial refusal text.
- ContentIndex int64
  
  The index of the content part that the refusal text is added to.
- Delta string
  
  The refusal text that is added.
- ItemID string
  
  The ID of the output item that the refusal text is added to.
- OutputIndex int64
  
  The index of the output item that the refusal text is added to.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseRefusalDelta
  
  The type of the event. Always response.refusal.delta.
  - const ResponseRefusalDeltaResponseRefusalDelta ResponseRefusalDelta = "response.refusal.delta"

Response Refusal Done Event

type ResponseRefusalDoneEvent struct{…}

Emitted when refusal text is finalized.
- ContentIndex int64
  
  The index of the content part that the refusal text is finalized.
- ItemID string
  
  The ID of the output item that the refusal text is finalized.
- OutputIndex int64
  
  The index of the output item that the refusal text is finalized.
- Refusal string
  
  The refusal text that is finalized.
- SequenceNumber int64
  
  The sequence number of this event.
- Type ResponseRefusalDone
  
  The type of the event. Always response.refusal.done.
  - const ResponseRefusalDoneResponseRefusalDone ResponseRefusalDone = "response.refusal.done"

Response Status

type ResponseStatus string

The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
- const ResponseStatusCompleted ResponseStatus = "completed"
- const ResponseStatusFailed ResponseStatus = "failed"
- const ResponseStatusInProgress ResponseStatus = "in_progress"
- const ResponseStatusCancelled ResponseStatus = "cancelled"
- const ResponseStatusQueued ResponseStatus = "queued"
- const ResponseStatusIncomplete ResponseStatus = "incomplete"

Response Stream Event

type ResponseStreamEventUnion interface{…}

Emitted when there is a partial audio response.
- type ResponseAudioDeltaEvent struct{…}
  
  Emitted when there is a partial audio response.
  - Delta string
    
    A chunk of Base64 encoded response audio bytes.
  - SequenceNumber int64
    
    A sequence number for this chunk of the stream response.
  - Type ResponseAudioDelta
    
    The type of the event. Always response.audio.delta.
    - const ResponseAudioDeltaResponseAudioDelta ResponseAudioDelta = "response.audio.delta"
- type ResponseAudioDoneEvent struct{…}
  
  Emitted when the audio response is complete.
  - SequenceNumber int64
    
    The sequence number of the delta.
  - Type ResponseAudioDone
    
    The type of the event. Always response.audio.done.
    - const ResponseAudioDoneResponseAudioDone ResponseAudioDone = "response.audio.done"
- type ResponseAudioTranscriptDeltaEvent struct{…}
  
  Emitted when there is a partial transcript of audio.
  - Delta string
    
    The partial transcript of the audio response.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseAudioTranscriptDelta
    
    The type of the event. Always response.audio.transcript.delta.
    - const ResponseAudioTranscriptDeltaResponseAudioTranscriptDelta ResponseAudioTranscriptDelta = "response.audio.transcript.delta"
- type ResponseAudioTranscriptDoneEvent struct{…}
  
  Emitted when the full audio transcript is completed.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseAudioTranscriptDone
    
    The type of the event. Always response.audio.transcript.done.
    - const ResponseAudioTranscriptDoneResponseAudioTranscriptDone ResponseAudioTranscriptDone = "response.audio.transcript.done"
- type ResponseCodeInterpreterCallCodeDeltaEvent struct{…}
  
  Emitted when a partial code snippet is streamed by the code interpreter.
  - Delta string
    
    The partial code snippet being streamed by the code interpreter.
  - ItemID string
    
    The unique identifier of the code interpreter tool call item.
  - OutputIndex int64
    
    The index of the output item in the response for which the code is being streamed.
  - SequenceNumber int64
    
    The sequence number of this event, used to order streaming events.
  - Type ResponseCodeInterpreterCallCodeDelta
    
    The type of the event. Always response.code_interpreter_call_code.delta.
    - const ResponseCodeInterpreterCallCodeDeltaResponseCodeInterpreterCallCodeDelta ResponseCodeInterpreterCallCodeDelta = "response.code_interpreter_call_code.delta"
- type ResponseCodeInterpreterCallCodeDoneEvent struct{…}
  
  Emitted when the code snippet is finalized by the code interpreter.
  - Code string
    
    The final code snippet output by the code interpreter.
  - ItemID string
    
    The unique identifier of the code interpreter tool call item.
  - OutputIndex int64
    
    The index of the output item in the response for which the code is finalized.
  - SequenceNumber int64
    
    The sequence number of this event, used to order streaming events.
  - Type ResponseCodeInterpreterCallCodeDone
    
    The type of the event. Always response.code_interpreter_call_code.done.
    - const ResponseCodeInterpreterCallCodeDoneResponseCodeInterpreterCallCodeDone ResponseCodeInterpreterCallCodeDone = "response.code_interpreter_call_code.done"
- type ResponseCodeInterpreterCallCompletedEvent struct{…}
  
  Emitted when the code interpreter call is completed.
  - ItemID string
    
    The unique identifier of the code interpreter tool call item.
  - OutputIndex int64
    
    The index of the output item in the response for which the code interpreter call is completed.
  - SequenceNumber int64
    
    The sequence number of this event, used to order streaming events.
  - Type ResponseCodeInterpreterCallCompleted
    
    The type of the event. Always response.code_interpreter_call.completed.
    - const ResponseCodeInterpreterCallCompletedResponseCodeInterpreterCallCompleted ResponseCodeInterpreterCallCompleted = "response.code_interpreter_call.completed"
- type ResponseCodeInterpreterCallInProgressEvent struct{…}
  
  Emitted when a code interpreter call is in progress.
  - ItemID string
    
    The unique identifier of the code interpreter tool call item.
  - OutputIndex int64
    
    The index of the output item in the response for which the code interpreter call is in progress.
  - SequenceNumber int64
    
    The sequence number of this event, used to order streaming events.
  - Type ResponseCodeInterpreterCallInProgress
    
    The type of the event. Always response.code_interpreter_call.in_progress.
    - const ResponseCodeInterpreterCallInProgressResponseCodeInterpreterCallInProgress ResponseCodeInterpreterCallInProgress = "response.code_interpreter_call.in_progress"
- type ResponseCodeInterpreterCallInterpretingEvent struct{…}
  
  Emitted when the code interpreter is actively interpreting the code snippet.
  - ItemID string
    
    The unique identifier of the code interpreter tool call item.
  - OutputIndex int64
    
    The index of the output item in the response for which the code interpreter is interpreting code.
  - SequenceNumber int64
    
    The sequence number of this event, used to order streaming events.
  - Type ResponseCodeInterpreterCallInterpreting
    
    The type of the event. Always response.code_interpreter_call.interpreting.
    - const ResponseCodeInterpreterCallInterpretingResponseCodeInterpreterCallInterpreting ResponseCodeInterpreterCallInterpreting = "response.code_interpreter_call.interpreting"
- type ResponseCompletedEvent struct{…}
  
  Emitted when the model response is complete.
  - Response Response
    
    Properties of the completed response.
    - ID string
      
      Unique identifier for this Response.
    - CreatedAt float64
      
      Unix timestamp (in seconds) of when this Response was created.
    - Error ResponseError
      
      An error object returned when the model fails to generate a Response.
      - Code ResponseErrorCode
        
        The error code for the response.
        
        const ResponseErrorCodeServerError ResponseErrorCode = "server_error"
        
        const ResponseErrorCodeRateLimitExceeded ResponseErrorCode = "rate_limit_exceeded"
        
        const ResponseErrorCodeInvalidPrompt ResponseErrorCode = "invalid_prompt"
        
        const ResponseErrorCodeVectorStoreTimeout ResponseErrorCode = "vector_store_timeout"
        
        const ResponseErrorCodeInvalidImage ResponseErrorCode = "invalid_image"
        
        const ResponseErrorCodeInvalidImageFormat ResponseErrorCode = "invalid_image_format"
        
        const ResponseErrorCodeInvalidBase64Image ResponseErrorCode = "invalid_base64_image"
        
        const ResponseErrorCodeInvalidImageURL ResponseErrorCode = "invalid_image_url"
        
        const ResponseErrorCodeImageTooLarge ResponseErrorCode = "image_too_large"
        
        const ResponseErrorCodeImageTooSmall ResponseErrorCode = "image_too_small"
        
        const ResponseErrorCodeImageParseError ResponseErrorCode = "image_parse_error"
        
        const ResponseErrorCodeImageContentPolicyViolation ResponseErrorCode = "image_content_policy_violation"
        
        const ResponseErrorCodeInvalidImageMode ResponseErrorCode = "invalid_image_mode"
        
        const ResponseErrorCodeImageFileTooLarge ResponseErrorCode = "image_file_too_large"
        
        const ResponseErrorCodeUnsupportedImageMediaType ResponseErrorCode = "unsupported_image_media_type"
        
        const ResponseErrorCodeEmptyImageFile ResponseErrorCode = "empty_image_file"
        
        const ResponseErrorCodeFailedToDownloadImage ResponseErrorCode = "failed_to_download_image"
        
        const ResponseErrorCodeImageFileNotFound ResponseErrorCode = "image_file_not_found"
      - Message string
        
        A human-readable description of the error.
    - IncompleteDetails ResponseIncompleteDetails
      
      Details about why the response is incomplete.
      - Reason string
        
        The reason why the response is incomplete.
        
        const ResponseIncompleteDetailsReasonMaxOutputTokens ResponseIncompleteDetailsReason = "max_output_tokens"
        
        const ResponseIncompleteDetailsReasonContentFilter ResponseIncompleteDetailsReason = "content_filter"
    - Instructions ResponseInstructionsUnion
      
      A system (or developer) message inserted into the model's context.
      
      When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
      - string
      - type ResponseInstructionsInputItemList []ResponseInputItemUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type EasyInputMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
        
        Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
        
        Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
        
        Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
        
        type ResponseInputItemMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
        
        Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
        
        Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
        
        Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
        
        Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
        
        type ResponseOutputMessage struct{…}
        
        An output message from the model.
        
        ID string
        
        The unique ID of the output message.
        
        Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
        
        Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
        
        Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
        
        Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
        
        Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
        
        type ResponseFileSearchToolCall struct{…}
        
        The results of a file search tool call. See the file search guide for more information.
        
        ID string
        
        The unique ID of the file search tool call.
        
        Queries []string
        
        The queries used to search for files.
        
        Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
        
        Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
        
        Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
        
        type ResponseComputerToolCall struct{…}
        
        A tool call to a computer use tool. See the computer use guide for more information.
        
        ID string
        
        The unique ID of the computer call.
        
        CallID string
        
        An identifier used when responding to the tool call with output.
        
        PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
        
        Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
        
        Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
        
        Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
        
        type ResponseInputItemComputerCallOutput struct{…}
        
        The output of a computer tool call.
        
        CallID string
        
        The ID of the computer tool call that produced the output.
        
        Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
        
        Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
        
        ID string
        
        The ID of the computer tool call output.
        
        AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
        
        type ResponseFunctionWebSearch struct{…}
        
        The results of a web search tool call. See the web search guide for more information.
        
        ID string
        
        The unique ID of the web search tool call.
        
        Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
        
        Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
        
        Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
        
        type ResponseFunctionToolCall struct{…}
        
        A tool call to run a function. See the function calling guide for more information.
        
        Arguments string
        
        A JSON string of the arguments to pass to the function.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Name string
        
        The name of the function to run.
        
        Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
        
        ID string
        
        The unique ID of the function tool call.
        
        Namespace string
        
        The namespace of the function to run.
        
        Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
        
        type ResponseInputItemFunctionCallOutput struct{…}
        
        The output of a function tool call.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
        
        ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
        
        type ResponseInputItemToolSearchCall struct{…}
        
        Arguments any
        
        The arguments supplied to the tool search call.
        
        Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
        
        ID string
        
        The unique ID of this tool search call.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
        
        Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
        
        type ResponseToolSearchOutputItemParamResp struct{…}
        
        Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
        
        Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
        
        ID string
        
        The unique ID of this tool search output.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
        
        Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
        
        type ResponseInputItemAdditionalTools struct{…}
        
        Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
        
        Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
        
        ID string
        
        The unique ID of this additional tools item.
        
        type ResponseReasoningItem struct{…}
        
        A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
        
        ID string
        
        The unique identifier of the reasoning content.
        
        Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
        
        Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
        
        Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
        
        EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
        
        Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
        
        type ResponseCompactionItemParamResp struct{…}
        
        A compaction item generated by the v1/responses/compact API.
        
        EncryptedContent string
        
        The encrypted content of the compaction summary.
        
        Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
        
        ID string
        
        The ID of the compaction item.
        
        type ResponseInputItemImageGenerationCall struct{…}
        
        An image generation request made by the model.
        
        ID string
        
        The unique ID of the image generation call.
        
        Result string
        
        The generated image encoded in base64.
        
        Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
        
        Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
        
        type ResponseCodeInterpreterToolCall struct{…}
        
        A tool call to run code.
        
        ID string
        
        The unique ID of the code interpreter tool call.
        
        Code string
        
        The code to run, or null if not available.
        
        ContainerID string
        
        The ID of the container used to run the code.
        
        Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
        
        Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
        
        Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
        
        type ResponseInputItemLocalShellCall struct{…}
        
        A tool call to run a command on the local shell.
        
        ID string
        
        The unique ID of the local shell call.
        
        Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
        
        CallID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
        
        Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
        
        type ResponseInputItemLocalShellCallOutput struct{…}
        
        The output of a local shell tool call.
        
        ID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Output string
        
        A JSON string of the output of the local shell tool call.
        
        Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
        
        type ResponseInputItemShellCall struct{…}
        
        A tool representing a request to execute one or more shell commands.
        
        Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
        
        ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
        
        Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
        
        Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
        
        type ResponseInputItemShellCallOutput struct{…}
        
        The streamed output items emitted by a shell tool call.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
        
        Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
        
        ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
        
        MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
        
        Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
        
        type ResponseInputItemApplyPatchCall struct{…}
        
        A tool call representing a request to create, delete, or update files using diff patches.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
        
        Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
        
        Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
        
        ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
        
        type ResponseInputItemApplyPatchCallOutput struct{…}
        
        The streamed output emitted by an apply patch tool call.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
        
        Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
        
        ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
        
        Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
        
        type ResponseInputItemMcpListTools struct{…}
        
        A list of tools available on an MCP server.
        
        ID string
        
        The unique ID of the list.
        
        ServerLabel string
        
        The label of the MCP server.
        
        Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
        
        Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
        
        Error string
        
        Error message if the server could not list tools.
        
        type ResponseInputItemMcpApprovalRequest struct{…}
        
        A request for human approval of a tool invocation.
        
        ID string
        
        The unique ID of the approval request.
        
        Arguments string
        
        A JSON string of arguments for the tool.
        
        Name string
        
        The name of the tool to run.
        
        ServerLabel string
        
        The label of the MCP server making the request.
        
        Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
        
        type ResponseInputItemMcpApprovalResponse struct{…}
        
        A response to an MCP approval request.
        
        ApprovalRequestID string
        
        The ID of the approval request being answered.
        
        Approve bool
        
        Whether the request was approved.
        
        Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
        
        ID string
        
        The unique ID of the approval response
        
        Reason string
        
        Optional reason for the decision.
        
        type ResponseInputItemMcpCall struct{…}
        
        An invocation of a tool on an MCP server.
        
        ID string
        
        The unique ID of the tool call.
        
        Arguments string
        
        A JSON string of the arguments passed to the tool.
        
        Name string
        
        The name of the tool that was run.
        
        ServerLabel string
        
        The label of the MCP server running the tool.
        
        Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
        
        ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
        
        Error string
        
        The error from the tool call, if any.
        
        Output string
        
        The output from the tool call.
        
        Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
        
        type ResponseCustomToolCallOutput struct{…}
        
        The output of a custom tool call from your code, being sent back to the model.
        
        CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
        
        Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
        
        ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
        
        type ResponseCustomToolCall struct{…}
        
        A call to a custom tool created by the model.
        
        CallID string
        
        An identifier used to map this custom tool call to a tool call output.
        
        Input string
        
        The input for the custom tool call generated by the model.
        
        Name string
        
        The name of the custom tool being called.
        
        Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
        
        ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
        
        Namespace string
        
        The namespace of the custom tool being called.
        
        type ResponseInputItemCompactionTrigger struct{…}
        
        Compacts the current context. Must be the final input item.
        
        Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
        
        type ResponseInputItemItemReference struct{…}
        
        An internal identifier for an item to reference.
        
        ID string
        
        The ID of the item to reference.
        
        Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
    - Metadata Metadata
      
      Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
      
      Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
    - Model ResponsesModel
      
      Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
      - string
      - type ChatModel string
        
        const ChatModelGPT5_4 ChatModel = "gpt-5.4"
        
        const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"
        
        const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"
        
        const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"
        
        const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"
        
        const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"
        
        const ChatModelGPT5_2 ChatModel = "gpt-5.2"
        
        const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"
        
        const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"
        
        const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"
        
        const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"
        
        const ChatModelGPT5_1 ChatModel = "gpt-5.1"
        
        const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"
        
        const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"
        
        const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"
        
        const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"
        
        const ChatModelGPT5 ChatModel = "gpt-5"
        
        const ChatModelGPT5Mini ChatModel = "gpt-5-mini"
        
        const ChatModelGPT5Nano ChatModel = "gpt-5-nano"
        
        const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"
        
        const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"
        
        const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"
        
        const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"
        
        const ChatModelGPT4_1 ChatModel = "gpt-4.1"
        
        const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"
        
        const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"
        
        const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"
        
        const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"
        
        const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"
        
        const ChatModelO4Mini ChatModel = "o4-mini"
        
        const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"
        
        const ChatModelO3 ChatModel = "o3"
        
        const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"
        
        const ChatModelO3Mini ChatModel = "o3-mini"
        
        const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"
        
        const ChatModelO1 ChatModel = "o1"
        
        const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"
        
        const ChatModelO1Preview ChatModel = "o1-preview"
        
        const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"
        
        const ChatModelO1Mini ChatModel = "o1-mini"
        
        const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"
        
        const ChatModelGPT4o ChatModel = "gpt-4o"
        
        const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"
        
        const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"
        
        const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"
        
        const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"
        
        const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"
        
        const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"
        
        const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"
        
        const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"
        
        const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"
        
        const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"
        
        const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"
        
        const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"
        
        const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"
        
        const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"
        
        const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"
        
        const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"
        
        const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"
        
        const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"
        
        const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"
        
        const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"
        
        const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"
        
        const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"
        
        const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"
        
        const ChatModelGPT4 ChatModel = "gpt-4"
        
        const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"
        
        const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"
        
        const ChatModelGPT4_32k ChatModel = "gpt-4-32k"
        
        const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"
        
        const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"
        
        const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"
        
        const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"
        
        const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"
        
        const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"
        
        const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"
        
        const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"
        
        const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"
      - type ResponsesModel string
        
        const ResponsesModelO1Pro ResponsesModel = "o1-pro"
        
        const ResponsesModelO1Pro2025_03_19 ResponsesModel = "o1-pro-2025-03-19"
        
        const ResponsesModelO3Pro ResponsesModel = "o3-pro"
        
        const ResponsesModelO3Pro2025_06_10 ResponsesModel = "o3-pro-2025-06-10"
        
        const ResponsesModelO3DeepResearch ResponsesModel = "o3-deep-research"
        
        const ResponsesModelO3DeepResearch2025_06_26 ResponsesModel = "o3-deep-research-2025-06-26"
        
        const ResponsesModelO4MiniDeepResearch ResponsesModel = "o4-mini-deep-research"
        
        const ResponsesModelO4MiniDeepResearch2025_06_26 ResponsesModel = "o4-mini-deep-research-2025-06-26"
        
        const ResponsesModelComputerUsePreview ResponsesModel = "computer-use-preview"
        
        const ResponsesModelComputerUsePreview2025_03_11 ResponsesModel = "computer-use-preview-2025-03-11"
        
        const ResponsesModelGPT5Codex ResponsesModel = "gpt-5-codex"
        
        const ResponsesModelGPT5Pro ResponsesModel = "gpt-5-pro"
        
        const ResponsesModelGPT5Pro2025_10_06 ResponsesModel = "gpt-5-pro-2025-10-06"
        
        const ResponsesModelGPT5_1CodexMax ResponsesModel = "gpt-5.1-codex-max"
    - Object Response
      
      The object type of this resource - always set to response.
      - const ResponseResponse Response = "response"
    - Output []ResponseOutputItemUnion
      
      An array of content items generated by the model.
      - The length and order of items in the output array is dependent on the model's response.
      - Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.
      - type ResponseOutputMessage struct{…}
        
        An output message from the model.
      - type ResponseFileSearchToolCall struct{…}
        
        The results of a file search tool call. See the file search guide for more information.
      - type ResponseFunctionToolCall struct{…}
        
        A tool call to run a function. See the function calling guide for more information.
      - type ResponseFunctionToolCallOutputItem struct{…}
        
        ID string
        
        The unique ID of the function call tool output.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Output ResponseFunctionToolCallOutputItemOutputUnion
        
        The output from the function call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Status ResponseFunctionToolCallOutputItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
        
        const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
        
        const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
        
        Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - type ResponseFunctionWebSearch struct{…}
        
        The results of a web search tool call. See the web search guide for more information.
      - type ResponseComputerToolCall struct{…}
        
        A tool call to a computer use tool. See the computer use guide for more information.
      - type ResponseComputerToolCallOutputItem struct{…}
        
        ID string
        
        The unique ID of the computer call tool output.
        
        CallID string
        
        The ID of the computer tool call that produced the output.
        
        Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Status ResponseComputerToolCallOutputItemStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
        
        const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
        
        const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
        
        const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
        
        Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
        
        AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - type ResponseReasoningItem struct{…}
        
        A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
      - type ResponseToolSearchCall struct{…}
        
        ID string
        
        The unique ID of the tool search call item.
        
        Arguments any
        
        Arguments used for the tool search call.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution ResponseToolSearchCallExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
        
        const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
        
        Status ResponseToolSearchCallStatus
        
        The status of the tool search call item that was recorded.
        
        const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
        
        const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
        
        const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
        
        Type ToolSearchCall
        
        The type of the item. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - type ResponseToolSearchOutputItem struct{…}
        
        ID string
        
        The unique ID of the tool search output item.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution ResponseToolSearchOutputItemExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
        
        const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
        
        Status ResponseToolSearchOutputItemStatus
        
        The status of the tool search output item that was recorded.
        
        const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
        
        const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
        
        const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
        
        Tools []ToolUnion
        
        The loaded tool definitions returned by tool search.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ToolSearchOutput
        
        The type of the item. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - type ResponseOutputItemAdditionalTools struct{…}
        
        ID string
        
        The unique ID of the additional tools item.
        
        Role string
        
        The role that provided the additional tools.
        
        const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
        
        const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
        
        const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
        
        const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
        
        const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
        
        const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
        
        const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
        
        const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
        
        Tools []ToolUnion
        
        The additional tool definitions made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type AdditionalTools
        
        The type of the item. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
      - type ResponseCompactionItem struct{…}
        
        A compaction item generated by the v1/responses/compact API.
        
        ID string
        
        The unique ID of the compaction item.
        
        EncryptedContent string
        
        The encrypted content that was produced by compaction.
        
        Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - type ResponseOutputItemImageGenerationCall struct{…}
        
        An image generation request made by the model.
        
        ID string
        
        The unique ID of the image generation call.
        
        Result string
        
        The generated image encoded in base64.
        
        Status string
        
        The status of the image generation call.
        
        const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
        
        const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
        
        const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
        
        Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
      - type ResponseCodeInterpreterToolCall struct{…}
        
        A tool call to run code.
      - type ResponseOutputItemLocalShellCall struct{…}
        
        A tool call to run a command on the local shell.
        
        ID string
        
        The unique ID of the local shell call.
        
        Action ResponseOutputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
        
        CallID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Status string
        
        The status of the local shell call.
        
        const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
        
        const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
        
        Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
      - type ResponseOutputItemLocalShellCallOutput struct{…}
        
        The output of a local shell tool call.
        
        ID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Output string
        
        A JSON string of the output of the local shell tool call.
        
        Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
      - type ResponseFunctionShellToolCall struct{…}
        
        A tool call that executes one or more shell commands in a managed environment.
        
        ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
        
        Action ResponseFunctionShellToolCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Environment ResponseFunctionShellToolCallEnvironmentUnion
        
        Represents the use of a local environment to perform shell actions.
        
        type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
        
        type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        Status ResponseFunctionShellToolCallStatus
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
        
        const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
        
        const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
        
        Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
        
        CreatedBy string
        
        The ID of the entity that created this tool call.
      - type ResponseFunctionShellToolCallOutput struct{…}
        
        The output of a shell tool call that was emitted.
        
        ID string
        
        The unique ID of the shell call output. Populated when this item is returned via API.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        MaxOutputLength int64
        
        The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
        
        Output []ResponseFunctionShellToolCallOutputOutput
        
        An array of shell call output contents
        
        Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        The standard error output that was captured.
        
        Stdout string
        
        The standard output that was captured.
        
        CreatedBy string
        
        The identifier of the actor that created the item.
        
        Status ResponseFunctionShellToolCallOutputStatus
        
        The status of the shell call output. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
        
        const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
        
        const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
        
        Type ShellCallOutput
        
        The type of the shell call output. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - type ResponseApplyPatchToolCall struct{…}
        
        A tool call that applies file diffs by creating, deleting, or updating files.
        
        ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Operation ResponseApplyPatchToolCallOperationUnion
        
        One of the create_file, delete_file, or update_file operations applied via apply_patch.
        
        type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
        
        Status ResponseApplyPatchToolCallStatus
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
        
        const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
        
        Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
        
        CreatedBy string
        
        The ID of the entity that created this tool call.
      - type ResponseApplyPatchToolCallOutput struct{…}
        
        The output emitted by an apply patch tool call.
        
        ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Status ResponseApplyPatchToolCallOutputStatus
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
        
        const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
        
        Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
        
        CreatedBy string
        
        The ID of the entity that created this tool call output.
        
        Output string
        
        Optional textual output returned by the apply patch tool.
      - type ResponseOutputItemMcpCall struct{…}
        
        An invocation of a tool on an MCP server.
        
        ID string
        
        The unique ID of the tool call.
        
        Arguments string
        
        A JSON string of the arguments passed to the tool.
        
        Name string
        
        The name of the tool that was run.
        
        ServerLabel string
        
        The label of the MCP server running the tool.
        
        Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
        
        ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
        
        Error string
        
        The error from the tool call, if any.
        
        Output string
        
        The output from the tool call.
        
        Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
        
        const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
        
        const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
        
        const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
        
        const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
      - type ResponseOutputItemMcpListTools struct{…}
        
        A list of tools available on an MCP server.
        
        ID string
        
        The unique ID of the list.
        
        ServerLabel string
        
        The label of the MCP server.
        
        Tools []ResponseOutputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
        
        Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
        
        Error string
        
        Error message if the server could not list tools.
      - type ResponseOutputItemMcpApprovalRequest struct{…}
        
        A request for human approval of a tool invocation.
        
        ID string
        
        The unique ID of the approval request.
        
        Arguments string
        
        A JSON string of arguments for the tool.
        
        Name string
        
        The name of the tool to run.
        
        ServerLabel string
        
        The label of the MCP server making the request.
        
        Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
      - type ResponseOutputItemMcpApprovalResponse struct{…}
        
        A response to an MCP approval request.
        
        ID string
        
        The unique ID of the approval response
        
        ApprovalRequestID string
        
        The ID of the approval request being answered.
        
        Approve bool
        
        Whether the request was approved.
        
        Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
        
        Reason string
        
        Optional reason for the decision.
      - type ResponseCustomToolCall struct{…}
        
        A call to a custom tool created by the model.
      - type ResponseCustomToolCallOutputItem struct{…}
        
        The output of a custom tool call from your code, being sent back to the model.
        
        ID string
        
        The unique ID of the custom tool call output item.
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
        
        const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
        
        const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
        
        CreatedBy string
        
        The identifier of the actor that created the item.
    - ParallelToolCalls bool
      
      Whether to allow the model to run tool calls in parallel.
    - Temperature float64
      
      What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
    - ToolChoice ResponseToolChoiceUnion
      
      How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.
      - type ToolChoiceOptions string
        
        Controls which (if any) tool is called by the model.
        
        none means the model will not call any tool and instead generates a message.
        
        auto means the model can pick between generating a message or calling one or more tools.
        
        required means the model must call one or more tools.
        
        const ToolChoiceOptionsNone ToolChoiceOptions = "none"
        
        const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
        
        const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
      - type ToolChoiceAllowed struct{…}
        
        Constrains the tools available to the model to a pre-defined set.
        
        Mode ToolChoiceAllowedMode
        
        Constrains the tools available to the model to a pre-defined set.
        
        auto allows the model to pick from among the allowed tools and generate a message.
        
        required requires the model to call one or more of the allowed tools.
        
        const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
        
        const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
        
        Tools []map[string, any]
        
        A list of tool definitions that the model should be allowed to call.
        
        For the Responses API, the list of tool definitions might look like:
        
        [ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ]
        
        Type AllowedTools
        
        Allowed tool configuration type. Always allowed_tools.
        
        const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
      - type ToolChoiceTypes struct{…}
        
        Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
        
        Type ToolChoiceTypesType
        
        The type of hosted tool the model should to use. Learn more about built-in tools.
        
        Allowed values are:
        
        file_search
        
        web_search_preview
        
        computer
        
        computer_use_preview
        
        computer_use
        
        code_interpreter
        
        image_generation
        
        const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
        
        const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
        
        const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
        
        const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
        
        const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
        
        const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
        
        const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
        
        const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
      - type ToolChoiceFunction struct{…}
        
        Use this option to force the model to call a specific function.
        
        Name string
        
        The name of the function to call.
        
        Type Function
        
        For function calling, the type is always function.
        
        const FunctionFunction Function = "function"
      - type ToolChoiceMcp struct{…}
        
        Use this option to force the model to call a specific tool on a remote MCP server.
        
        ServerLabel string
        
        The label of the MCP server to use.
        
        Type Mcp
        
        For MCP tools, the type is always mcp.
        
        const McpMcp Mcp = "mcp"
        
        Name string
        
        The name of the tool to call on the server.
      - type ToolChoiceCustom struct{…}
        
        Use this option to force the model to call a specific custom tool.
        
        Name string
        
        The name of the custom tool to call.
        
        Type Custom
        
        For custom tool calling, the type is always custom.
        
        const CustomCustom Custom = "custom"
      - type ToolChoiceApplyPatch struct{…}
        
        Forces the model to call the apply_patch tool when executing a tool call.
        
        Type ApplyPatch
        
        The tool to call. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
      - type ToolChoiceShell struct{…}
        
        Forces the model to call the shell tool when a tool call is required.
        
        Type Shell
        
        The tool to call. Always shell.
        
        const ShellShell Shell = "shell"
    - Tools []ToolUnion
      
      An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
      
      We support the following categories of tools:
      - Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
      - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
      - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - TopP float64
      
      An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
      
      We generally recommend altering this or temperature but not both.
    - Background bool
      
      Whether to run the model response in the background. Learn more.
    - CompletedAt float64
      
      Unix timestamp (in seconds) of when this Response was completed. Only present when the status is completed.
    - Conversation ResponseConversation
      
      The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
      - ID string
        
        The unique ID of the conversation that this response was associated with.
    - MaxOutputTokens int64
      
      An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
    - MaxToolCalls int64
      
      The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
    - Moderation ResponseModeration
      
      Moderation results for the response input and output, if moderated completions were requested.
      - Input ResponseModerationInputUnion
        
        Moderation for the response input.
        
        type ResponseModerationInputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeText ResponseModerationInputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeImage ResponseModerationInputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
        
        type ResponseModerationInputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
      - Output ResponseModerationOutputUnion
        
        Moderation for the response output.
        
        type ResponseModerationOutputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeText ResponseModerationOutputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeImage ResponseModerationOutputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
        
        type ResponseModerationOutputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
    - PreviousResponseID string
      
      The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
    - Prompt ResponsePrompt
      
      Reference to a prompt template and its variables. Learn more.
      - ID string
        
        The unique identifier of the prompt template to use.
      - Variables map[string, ResponsePromptVariableUnion]
        
        Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
        
        string
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Version string
        
        Optional version of the prompt template.
    - PromptCacheKey string
      
      Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
    - PromptCacheRetention ResponsePromptCacheRetention
      
      The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.
      
      For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:
      - Organizations without ZDR enabled default to 24h.
      - Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.
      - const ResponsePromptCacheRetentionInMemory ResponsePromptCacheRetention = "in_memory"
      - const ResponsePromptCacheRetention24h ResponsePromptCacheRetention = "24h"
    - Reasoning Reasoning
      
      gpt-5 and o-series models only
      
      Configuration options for reasoning models.
      - Context ReasoningContext
        
        Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
        
        const ReasoningContextAuto ReasoningContext = "auto"
        
        const ReasoningContextCurrentTurn ReasoningContext = "current_turn"
        
        const ReasoningContextAllTurns ReasoningContext = "all_turns"
      - Effort ReasoningEffort
        
        Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
        
        gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
        
        All models before gpt-5.1 default to medium reasoning effort, and do not support none.
        
        The gpt-5-pro model defaults to (and only supports) high reasoning effort.
        
        xhigh is supported for all models after gpt-5.1-codex-max.
        
        const ReasoningEffortNone ReasoningEffort = "none"
        
        const ReasoningEffortMinimal ReasoningEffort = "minimal"
        
        const ReasoningEffortLow ReasoningEffort = "low"
        
        const ReasoningEffortMedium ReasoningEffort = "medium"
        
        const ReasoningEffortHigh ReasoningEffort = "high"
        
        const ReasoningEffortXhigh ReasoningEffort = "xhigh"
      - GenerateSummary ReasoningGenerateSummary
        
        Deprecated: use summary instead.
        
        A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
        
        const ReasoningGenerateSummaryAuto ReasoningGenerateSummary = "auto"
        
        const ReasoningGenerateSummaryConcise ReasoningGenerateSummary = "concise"
        
        const ReasoningGenerateSummaryDetailed ReasoningGenerateSummary = "detailed"
      - Summary ReasoningSummary
        
        A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
        
        concise is supported for computer-use-preview models and all reasoning models after gpt-5.
        
        const ReasoningSummaryAuto ReasoningSummary = "auto"
        
        const ReasoningSummaryConcise ReasoningSummary = "concise"
        
        const ReasoningSummaryDetailed ReasoningSummary = "detailed"
    - SafetyIdentifier string
      
      A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
    - ServiceTier ResponseServiceTier
      
      Specifies the processing type used for serving the request.
      - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
      - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
      - If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
      - When not set, the default behavior is 'auto'.
      When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
      - const ResponseServiceTierAuto ResponseServiceTier = "auto"
      - const ResponseServiceTierDefault ResponseServiceTier = "default"
      - const ResponseServiceTierFlex ResponseServiceTier = "flex"
      - const ResponseServiceTierScale ResponseServiceTier = "scale"
      - const ResponseServiceTierPriority ResponseServiceTier = "priority"
    - Status ResponseStatus
      
      The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
      - const ResponseStatusCompleted ResponseStatus = "completed"
      - const ResponseStatusFailed ResponseStatus = "failed"
      - const ResponseStatusInProgress ResponseStatus = "in_progress"
      - const ResponseStatusCancelled ResponseStatus = "cancelled"
      - const ResponseStatusQueued ResponseStatus = "queued"
      - const ResponseStatusIncomplete ResponseStatus = "incomplete"
    - Text ResponseTextConfig
      
      Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
      - Text inputs and outputs
      - Structured Outputs
      - Format ResponseFormatTextConfigUnion
        
        An object specifying the format that the model must output.
        
        Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
        
        The default format is { "type": "text" } with no additional options.
        
        Not recommended for gpt-4o and newer models:
        
        Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
        
        type ResponseFormatText struct{…}
        
        Default response format. Used to generate text responses.
        
        Type Text
        
        The type of response format being defined. Always text.
        
        const TextText Text = "text"
        
        type ResponseFormatTextJSONSchemaConfig struct{…}
        
        JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
        
        Name string
        
        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
        
        Schema map[string, any]
        
        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
        
        Type JSONSchema
        
        The type of response format being defined. Always json_schema.
        
        const JSONSchemaJSONSchema JSONSchema = "json_schema"
        
        Description string
        
        A description of what the response format is for, used by the model to determine how to respond in the format.
        
        Strict bool
        
        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
        
        type ResponseFormatJSONObject struct{…}
        
        JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
        
        Type JSONObject
        
        The type of response format being defined. Always json_object.
        
        const JSONObjectJSONObject JSONObject = "json_object"
      - Verbosity ResponseTextConfigVerbosity
        
        Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
        
        const ResponseTextConfigVerbosityLow ResponseTextConfigVerbosity = "low"
        
        const ResponseTextConfigVerbosityMedium ResponseTextConfigVerbosity = "medium"
        
        const ResponseTextConfigVerbosityHigh ResponseTextConfigVerbosity = "high"
    - TopLogprobs int64
      
      An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
    - Truncation ResponseTruncation
      
      The truncation strategy to use for the model response.
      - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
      - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
      - const ResponseTruncationAuto ResponseTruncation = "auto"
      - const ResponseTruncationDisabled ResponseTruncation = "disabled"
    - Usage ResponseUsage
      
      Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
      - InputTokens int64
        
        The number of input tokens.
      - InputTokensDetails ResponseUsageInputTokensDetails
        
        A detailed breakdown of the input tokens.
        
        CachedTokens int64
        
        The number of tokens that were retrieved from the cache. More on prompt caching.
      - OutputTokens int64
        
        The number of output tokens.
      - OutputTokensDetails ResponseUsageOutputTokensDetails
        
        A detailed breakdown of the output tokens.
        
        ReasoningTokens int64
        
        The number of reasoning tokens.
      - TotalTokens int64
        
        The total number of tokens used.
    - User string
      
      This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
  - SequenceNumber int64
    
    The sequence number for this event.
  - Type ResponseCompleted
    
    The type of the event. Always response.completed.
    - const ResponseCompletedResponseCompleted ResponseCompleted = "response.completed"
- type ResponseContentPartAddedEvent struct{…}
  
  Emitted when a new content part is added.
  - ContentIndex int64
    
    The index of the content part that was added.
  - ItemID string
    
    The ID of the output item that the content part was added to.
  - OutputIndex int64
    
    The index of the output item that the content part was added to.
  - Part ResponseContentPartAddedEventPartUnion
    
    The content part that was added.
    - type ResponseOutputText struct{…}
      
      A text output from the model.
    - type ResponseOutputRefusal struct{…}
      
      A refusal from the model.
    - type ResponseContentPartAddedEventPartReasoningText struct{…}
      
      Reasoning text from the model.
      - Text string
        
        The reasoning text from the model.
      - Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseContentPartAdded
    
    The type of the event. Always response.content_part.added.
    - const ResponseContentPartAddedResponseContentPartAdded ResponseContentPartAdded = "response.content_part.added"
- type ResponseContentPartDoneEvent struct{…}
  
  Emitted when a content part is done.
  - ContentIndex int64
    
    The index of the content part that is done.
  - ItemID string
    
    The ID of the output item that the content part was added to.
  - OutputIndex int64
    
    The index of the output item that the content part was added to.
  - Part ResponseContentPartDoneEventPartUnion
    
    The content part that is done.
    - type ResponseOutputText struct{…}
      
      A text output from the model.
    - type ResponseOutputRefusal struct{…}
      
      A refusal from the model.
    - type ResponseContentPartDoneEventPartReasoningText struct{…}
      
      Reasoning text from the model.
      - Text string
        
        The reasoning text from the model.
      - Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseContentPartDone
    
    The type of the event. Always response.content_part.done.
    - const ResponseContentPartDoneResponseContentPartDone ResponseContentPartDone = "response.content_part.done"
- type ResponseCreatedEvent struct{…}
  
  An event that is emitted when a response is created.
  - Response Response
    
    The response that was created.
  - SequenceNumber int64
    
    The sequence number for this event.
  - Type ResponseCreated
    
    The type of the event. Always response.created.
    - const ResponseCreatedResponseCreated ResponseCreated = "response.created"
- type ResponseErrorEvent struct{…}
  
  Emitted when an error occurs.
  - Code string
    
    The error code.
  - Message string
    
    The error message.
  - Param string
    
    The error parameter.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type Error
    
    The type of the event. Always error.
    - const ErrorError Error = "error"
- type ResponseFileSearchCallCompletedEvent struct{…}
  
  Emitted when a file search call is completed (results found).
  - ItemID string
    
    The ID of the output item that the file search call is initiated.
  - OutputIndex int64
    
    The index of the output item that the file search call is initiated.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseFileSearchCallCompleted
    
    The type of the event. Always response.file_search_call.completed.
    - const ResponseFileSearchCallCompletedResponseFileSearchCallCompleted ResponseFileSearchCallCompleted = "response.file_search_call.completed"
- type ResponseFileSearchCallInProgressEvent struct{…}
  
  Emitted when a file search call is initiated.
  - ItemID string
    
    The ID of the output item that the file search call is initiated.
  - OutputIndex int64
    
    The index of the output item that the file search call is initiated.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseFileSearchCallInProgress
    
    The type of the event. Always response.file_search_call.in_progress.
    - const ResponseFileSearchCallInProgressResponseFileSearchCallInProgress ResponseFileSearchCallInProgress = "response.file_search_call.in_progress"
- type ResponseFileSearchCallSearchingEvent struct{…}
  
  Emitted when a file search is currently searching.
  - ItemID string
    
    The ID of the output item that the file search call is initiated.
  - OutputIndex int64
    
    The index of the output item that the file search call is searching.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseFileSearchCallSearching
    
    The type of the event. Always response.file_search_call.searching.
    - const ResponseFileSearchCallSearchingResponseFileSearchCallSearching ResponseFileSearchCallSearching = "response.file_search_call.searching"
- type ResponseFunctionCallArgumentsDeltaEvent struct{…}
  
  Emitted when there is a partial function-call arguments delta.
  - Delta string
    
    The function-call arguments delta that is added.
  - ItemID string
    
    The ID of the output item that the function-call arguments delta is added to.
  - OutputIndex int64
    
    The index of the output item that the function-call arguments delta is added to.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseFunctionCallArgumentsDelta
    
    The type of the event. Always response.function_call_arguments.delta.
    - const ResponseFunctionCallArgumentsDeltaResponseFunctionCallArgumentsDelta ResponseFunctionCallArgumentsDelta = "response.function_call_arguments.delta"
- type ResponseFunctionCallArgumentsDoneEvent struct{…}
  
  Emitted when function-call arguments are finalized.
  - Arguments string
    
    The function-call arguments.
  - ItemID string
    
    The ID of the item.
  - Name string
    
    The name of the function that was called.
  - OutputIndex int64
    
    The index of the output item.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseFunctionCallArgumentsDone
    - const ResponseFunctionCallArgumentsDoneResponseFunctionCallArgumentsDone ResponseFunctionCallArgumentsDone = "response.function_call_arguments.done"
- type ResponseInProgressEvent struct{…}
  
  Emitted when the response is in progress.
  - Response Response
    
    The response that is in progress.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseInProgress
    
    The type of the event. Always response.in_progress.
    - const ResponseInProgressResponseInProgress ResponseInProgress = "response.in_progress"
- type ResponseFailedEvent struct{…}
  
  An event that is emitted when a response fails.
  - Response Response
    
    The response that failed.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseFailed
    
    The type of the event. Always response.failed.
    - const ResponseFailedResponseFailed ResponseFailed = "response.failed"
- type ResponseIncompleteEvent struct{…}
  
  An event that is emitted when a response finishes as incomplete.
  - Response Response
    
    The response that was incomplete.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseIncomplete
    
    The type of the event. Always response.incomplete.
    - const ResponseIncompleteResponseIncomplete ResponseIncomplete = "response.incomplete"
- type ResponseOutputItemAddedEvent struct{…}
  
  Emitted when a new output item is added.
  - Item ResponseOutputItemUnion
    
    The output item that was added.
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
    - type ResponseFunctionToolCallOutputItem struct{…}
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
    - type ResponseComputerToolCallOutputItem struct{…}
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
    - type ResponseToolSearchCall struct{…}
    - type ResponseToolSearchOutputItem struct{…}
    - type ResponseOutputItemAdditionalTools struct{…}
    - type ResponseCompactionItem struct{…}
      
      A compaction item generated by the v1/responses/compact API.
    - type ResponseOutputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
    - type ResponseOutputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
    - type ResponseOutputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
    - type ResponseFunctionShellToolCall struct{…}
      
      A tool call that executes one or more shell commands in a managed environment.
    - type ResponseFunctionShellToolCallOutput struct{…}
      
      The output of a shell tool call that was emitted.
    - type ResponseApplyPatchToolCall struct{…}
      
      A tool call that applies file diffs by creating, deleting, or updating files.
    - type ResponseApplyPatchToolCallOutput struct{…}
      
      The output emitted by an apply patch tool call.
    - type ResponseOutputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
    - type ResponseOutputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
    - type ResponseOutputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
    - type ResponseOutputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
    - type ResponseCustomToolCallOutputItem struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
  - OutputIndex int64
    
    The index of the output item that was added.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseOutputItemAdded
    
    The type of the event. Always response.output_item.added.
    - const ResponseOutputItemAddedResponseOutputItemAdded ResponseOutputItemAdded = "response.output_item.added"
- type ResponseOutputItemDoneEvent struct{…}
  
  Emitted when an output item is marked done.
  - Item ResponseOutputItemUnion
    
    The output item that was marked done.
  - OutputIndex int64
    
    The index of the output item that was marked done.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseOutputItemDone
    
    The type of the event. Always response.output_item.done.
    - const ResponseOutputItemDoneResponseOutputItemDone ResponseOutputItemDone = "response.output_item.done"
- type ResponseReasoningSummaryPartAddedEvent struct{…}
  
  Emitted when a new reasoning summary part is added.
  - ItemID string
    
    The ID of the item this summary part is associated with.
  - OutputIndex int64
    
    The index of the output item this summary part is associated with.
  - Part ResponseReasoningSummaryPartAddedEventPart
    
    The summary part that was added.
    - Text string
      
      The text of the summary part.
    - Type SummaryText
      
      The type of the summary part. Always summary_text.
      - const SummaryTextSummaryText SummaryText = "summary_text"
  - SequenceNumber int64
    
    The sequence number of this event.
  - SummaryIndex int64
    
    The index of the summary part within the reasoning summary.
  - Type ResponseReasoningSummaryPartAdded
    
    The type of the event. Always response.reasoning_summary_part.added.
    - const ResponseReasoningSummaryPartAddedResponseReasoningSummaryPartAdded ResponseReasoningSummaryPartAdded = "response.reasoning_summary_part.added"
- type ResponseReasoningSummaryPartDoneEvent struct{…}
  
  Emitted when a reasoning summary part is completed.
  - ItemID string
    
    The ID of the item this summary part is associated with.
  - OutputIndex int64
    
    The index of the output item this summary part is associated with.
  - Part ResponseReasoningSummaryPartDoneEventPart
    
    The completed summary part.
    - Text string
      
      The text of the summary part.
    - Type SummaryText
      
      The type of the summary part. Always summary_text.
      - const SummaryTextSummaryText SummaryText = "summary_text"
  - SequenceNumber int64
    
    The sequence number of this event.
  - SummaryIndex int64
    
    The index of the summary part within the reasoning summary.
  - Type ResponseReasoningSummaryPartDone
    
    The type of the event. Always response.reasoning_summary_part.done.
    - const ResponseReasoningSummaryPartDoneResponseReasoningSummaryPartDone ResponseReasoningSummaryPartDone = "response.reasoning_summary_part.done"
- type ResponseReasoningSummaryTextDeltaEvent struct{…}
  
  Emitted when a delta is added to a reasoning summary text.
  - Delta string
    
    The text delta that was added to the summary.
  - ItemID string
    
    The ID of the item this summary text delta is associated with.
  - OutputIndex int64
    
    The index of the output item this summary text delta is associated with.
  - SequenceNumber int64
    
    The sequence number of this event.
  - SummaryIndex int64
    
    The index of the summary part within the reasoning summary.
  - Type ResponseReasoningSummaryTextDelta
    
    The type of the event. Always response.reasoning_summary_text.delta.
    - const ResponseReasoningSummaryTextDeltaResponseReasoningSummaryTextDelta ResponseReasoningSummaryTextDelta = "response.reasoning_summary_text.delta"
- type ResponseReasoningSummaryTextDoneEvent struct{…}
  
  Emitted when a reasoning summary text is completed.
  - ItemID string
    
    The ID of the item this summary text is associated with.
  - OutputIndex int64
    
    The index of the output item this summary text is associated with.
  - SequenceNumber int64
    
    The sequence number of this event.
  - SummaryIndex int64
    
    The index of the summary part within the reasoning summary.
  - Text string
    
    The full text of the completed reasoning summary.
  - Type ResponseReasoningSummaryTextDone
    
    The type of the event. Always response.reasoning_summary_text.done.
    - const ResponseReasoningSummaryTextDoneResponseReasoningSummaryTextDone ResponseReasoningSummaryTextDone = "response.reasoning_summary_text.done"
- type ResponseReasoningTextDeltaEvent struct{…}
  
  Emitted when a delta is added to a reasoning text.
  - ContentIndex int64
    
    The index of the reasoning content part this delta is associated with.
  - Delta string
    
    The text delta that was added to the reasoning content.
  - ItemID string
    
    The ID of the item this reasoning text delta is associated with.
  - OutputIndex int64
    
    The index of the output item this reasoning text delta is associated with.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseReasoningTextDelta
    
    The type of the event. Always response.reasoning_text.delta.
    - const ResponseReasoningTextDeltaResponseReasoningTextDelta ResponseReasoningTextDelta = "response.reasoning_text.delta"
- type ResponseReasoningTextDoneEvent struct{…}
  
  Emitted when a reasoning text is completed.
  - ContentIndex int64
    
    The index of the reasoning content part.
  - ItemID string
    
    The ID of the item this reasoning text is associated with.
  - OutputIndex int64
    
    The index of the output item this reasoning text is associated with.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Text string
    
    The full text of the completed reasoning content.
  - Type ResponseReasoningTextDone
    
    The type of the event. Always response.reasoning_text.done.
    - const ResponseReasoningTextDoneResponseReasoningTextDone ResponseReasoningTextDone = "response.reasoning_text.done"
- type ResponseRefusalDeltaEvent struct{…}
  
  Emitted when there is a partial refusal text.
  - ContentIndex int64
    
    The index of the content part that the refusal text is added to.
  - Delta string
    
    The refusal text that is added.
  - ItemID string
    
    The ID of the output item that the refusal text is added to.
  - OutputIndex int64
    
    The index of the output item that the refusal text is added to.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseRefusalDelta
    
    The type of the event. Always response.refusal.delta.
    - const ResponseRefusalDeltaResponseRefusalDelta ResponseRefusalDelta = "response.refusal.delta"
- type ResponseRefusalDoneEvent struct{…}
  
  Emitted when refusal text is finalized.
  - ContentIndex int64
    
    The index of the content part that the refusal text is finalized.
  - ItemID string
    
    The ID of the output item that the refusal text is finalized.
  - OutputIndex int64
    
    The index of the output item that the refusal text is finalized.
  - Refusal string
    
    The refusal text that is finalized.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseRefusalDone
    
    The type of the event. Always response.refusal.done.
    - const ResponseRefusalDoneResponseRefusalDone ResponseRefusalDone = "response.refusal.done"
- type ResponseTextDeltaEvent struct{…}
  
  Emitted when there is an additional text delta.
  - ContentIndex int64
    
    The index of the content part that the text delta was added to.
  - Delta string
    
    The text delta that was added.
  - ItemID string
    
    The ID of the output item that the text delta was added to.
  - Logprobs []ResponseTextDeltaEventLogprob
    
    The log probabilities of the tokens in the delta.
    - Token string
      
      A possible text token.
    - Logprob float64
      
      The log probability of this token.
    - TopLogprobs []ResponseTextDeltaEventLogprobTopLogprob
      
      The log probabilities of up to 20 of the most likely tokens.
      - Token string
        
        A possible text token.
      - Logprob float64
        
        The log probability of this token.
  - OutputIndex int64
    
    The index of the output item that the text delta was added to.
  - SequenceNumber int64
    
    The sequence number for this event.
  - Type ResponseOutputTextDelta
    
    The type of the event. Always response.output_text.delta.
    - const ResponseOutputTextDeltaResponseOutputTextDelta ResponseOutputTextDelta = "response.output_text.delta"
- type ResponseTextDoneEvent struct{…}
  
  Emitted when text content is finalized.
  - ContentIndex int64
    
    The index of the content part that the text content is finalized.
  - ItemID string
    
    The ID of the output item that the text content is finalized.
  - Logprobs []ResponseTextDoneEventLogprob
    
    The log probabilities of the tokens in the delta.
    - Token string
      
      A possible text token.
    - Logprob float64
      
      The log probability of this token.
    - TopLogprobs []ResponseTextDoneEventLogprobTopLogprob
      
      The log probabilities of up to 20 of the most likely tokens.
      - Token string
        
        A possible text token.
      - Logprob float64
        
        The log probability of this token.
  - OutputIndex int64
    
    The index of the output item that the text content is finalized.
  - SequenceNumber int64
    
    The sequence number for this event.
  - Text string
    
    The text content that is finalized.
  - Type ResponseOutputTextDone
    
    The type of the event. Always response.output_text.done.
    - const ResponseOutputTextDoneResponseOutputTextDone ResponseOutputTextDone = "response.output_text.done"
- type ResponseWebSearchCallCompletedEvent struct{…}
  
  Emitted when a web search call is completed.
  - ItemID string
    
    Unique ID for the output item associated with the web search call.
  - OutputIndex int64
    
    The index of the output item that the web search call is associated with.
  - SequenceNumber int64
    
    The sequence number of the web search call being processed.
  - Type ResponseWebSearchCallCompleted
    
    The type of the event. Always response.web_search_call.completed.
    - const ResponseWebSearchCallCompletedResponseWebSearchCallCompleted ResponseWebSearchCallCompleted = "response.web_search_call.completed"
- type ResponseWebSearchCallInProgressEvent struct{…}
  
  Emitted when a web search call is initiated.
  - ItemID string
    
    Unique ID for the output item associated with the web search call.
  - OutputIndex int64
    
    The index of the output item that the web search call is associated with.
  - SequenceNumber int64
    
    The sequence number of the web search call being processed.
  - Type ResponseWebSearchCallInProgress
    
    The type of the event. Always response.web_search_call.in_progress.
    - const ResponseWebSearchCallInProgressResponseWebSearchCallInProgress ResponseWebSearchCallInProgress = "response.web_search_call.in_progress"
- type ResponseWebSearchCallSearchingEvent struct{…}
  
  Emitted when a web search call is executing.
  - ItemID string
    
    Unique ID for the output item associated with the web search call.
  - OutputIndex int64
    
    The index of the output item that the web search call is associated with.
  - SequenceNumber int64
    
    The sequence number of the web search call being processed.
  - Type ResponseWebSearchCallSearching
    
    The type of the event. Always response.web_search_call.searching.
    - const ResponseWebSearchCallSearchingResponseWebSearchCallSearching ResponseWebSearchCallSearching = "response.web_search_call.searching"
- type ResponseImageGenCallCompletedEvent struct{…}
  
  Emitted when an image generation tool call has completed and the final image is available.
  - ItemID string
    
    The unique identifier of the image generation item being processed.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseImageGenerationCallCompleted
    
    The type of the event. Always 'response.image_generation_call.completed'.
    - const ResponseImageGenerationCallCompletedResponseImageGenerationCallCompleted ResponseImageGenerationCallCompleted = "response.image_generation_call.completed"
- type ResponseImageGenCallGeneratingEvent struct{…}
  
  Emitted when an image generation tool call is actively generating an image (intermediate state).
  - ItemID string
    
    The unique identifier of the image generation item being processed.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - SequenceNumber int64
    
    The sequence number of the image generation item being processed.
  - Type ResponseImageGenerationCallGenerating
    
    The type of the event. Always 'response.image_generation_call.generating'.
    - const ResponseImageGenerationCallGeneratingResponseImageGenerationCallGenerating ResponseImageGenerationCallGenerating = "response.image_generation_call.generating"
- type ResponseImageGenCallInProgressEvent struct{…}
  
  Emitted when an image generation tool call is in progress.
  - ItemID string
    
    The unique identifier of the image generation item being processed.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - SequenceNumber int64
    
    The sequence number of the image generation item being processed.
  - Type ResponseImageGenerationCallInProgress
    
    The type of the event. Always 'response.image_generation_call.in_progress'.
    - const ResponseImageGenerationCallInProgressResponseImageGenerationCallInProgress ResponseImageGenerationCallInProgress = "response.image_generation_call.in_progress"
- type ResponseImageGenCallPartialImageEvent struct{…}
  
  Emitted when a partial image is available during image generation streaming.
  - ItemID string
    
    The unique identifier of the image generation item being processed.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - PartialImageB64 string
    
    Base64-encoded partial image data, suitable for rendering as an image.
  - PartialImageIndex int64
    
    0-based index for the partial image (backend is 1-based, but this is 0-based for the user).
  - SequenceNumber int64
    
    The sequence number of the image generation item being processed.
  - Type ResponseImageGenerationCallPartialImage
    
    The type of the event. Always 'response.image_generation_call.partial_image'.
    - const ResponseImageGenerationCallPartialImageResponseImageGenerationCallPartialImage ResponseImageGenerationCallPartialImage = "response.image_generation_call.partial_image"
- type ResponseMcpCallArgumentsDeltaEvent struct{…}
  
  Emitted when there is a delta (partial update) to the arguments of an MCP tool call.
  - Delta string
    
    A JSON string containing the partial update to the arguments for the MCP tool call.
  - ItemID string
    
    The unique identifier of the MCP tool call item being processed.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpCallArgumentsDelta
    
    The type of the event. Always 'response.mcp_call_arguments.delta'.
    - const ResponseMcpCallArgumentsDeltaResponseMcpCallArgumentsDelta ResponseMcpCallArgumentsDelta = "response.mcp_call_arguments.delta"
- type ResponseMcpCallArgumentsDoneEvent struct{…}
  
  Emitted when the arguments for an MCP tool call are finalized.
  - Arguments string
    
    A JSON string containing the finalized arguments for the MCP tool call.
  - ItemID string
    
    The unique identifier of the MCP tool call item being processed.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpCallArgumentsDone
    
    The type of the event. Always 'response.mcp_call_arguments.done'.
    - const ResponseMcpCallArgumentsDoneResponseMcpCallArgumentsDone ResponseMcpCallArgumentsDone = "response.mcp_call_arguments.done"
- type ResponseMcpCallCompletedEvent struct{…}
  
  Emitted when an MCP tool call has completed successfully.
  - ItemID string
    
    The ID of the MCP tool call item that completed.
  - OutputIndex int64
    
    The index of the output item that completed.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpCallCompleted
    
    The type of the event. Always 'response.mcp_call.completed'.
    - const ResponseMcpCallCompletedResponseMcpCallCompleted ResponseMcpCallCompleted = "response.mcp_call.completed"
- type ResponseMcpCallFailedEvent struct{…}
  
  Emitted when an MCP tool call has failed.
  - ItemID string
    
    The ID of the MCP tool call item that failed.
  - OutputIndex int64
    
    The index of the output item that failed.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpCallFailed
    
    The type of the event. Always 'response.mcp_call.failed'.
    - const ResponseMcpCallFailedResponseMcpCallFailed ResponseMcpCallFailed = "response.mcp_call.failed"
- type ResponseMcpCallInProgressEvent struct{…}
  
  Emitted when an MCP tool call is in progress.
  - ItemID string
    
    The unique identifier of the MCP tool call item being processed.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpCallInProgress
    
    The type of the event. Always 'response.mcp_call.in_progress'.
    - const ResponseMcpCallInProgressResponseMcpCallInProgress ResponseMcpCallInProgress = "response.mcp_call.in_progress"
- type ResponseMcpListToolsCompletedEvent struct{…}
  
  Emitted when the list of available MCP tools has been successfully retrieved.
  - ItemID string
    
    The ID of the MCP tool call item that produced this output.
  - OutputIndex int64
    
    The index of the output item that was processed.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpListToolsCompleted
    
    The type of the event. Always 'response.mcp_list_tools.completed'.
    - const ResponseMcpListToolsCompletedResponseMcpListToolsCompleted ResponseMcpListToolsCompleted = "response.mcp_list_tools.completed"
- type ResponseMcpListToolsFailedEvent struct{…}
  
  Emitted when the attempt to list available MCP tools has failed.
  - ItemID string
    
    The ID of the MCP tool call item that failed.
  - OutputIndex int64
    
    The index of the output item that failed.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpListToolsFailed
    
    The type of the event. Always 'response.mcp_list_tools.failed'.
    - const ResponseMcpListToolsFailedResponseMcpListToolsFailed ResponseMcpListToolsFailed = "response.mcp_list_tools.failed"
- type ResponseMcpListToolsInProgressEvent struct{…}
  
  Emitted when the system is in the process of retrieving the list of available MCP tools.
  - ItemID string
    
    The ID of the MCP tool call item that is being processed.
  - OutputIndex int64
    
    The index of the output item that is being processed.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpListToolsInProgress
    
    The type of the event. Always 'response.mcp_list_tools.in_progress'.
    - const ResponseMcpListToolsInProgressResponseMcpListToolsInProgress ResponseMcpListToolsInProgress = "response.mcp_list_tools.in_progress"
- type ResponseOutputTextAnnotationAddedEvent struct{…}
  
  Emitted when an annotation is added to output text content.
  - Annotation any
    
    The annotation object being added. (See annotation schema for details.)
  - AnnotationIndex int64
    
    The index of the annotation within the content part.
  - ContentIndex int64
    
    The index of the content part within the output item.
  - ItemID string
    
    The unique identifier of the item to which the annotation is being added.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseOutputTextAnnotationAdded
    
    The type of the event. Always 'response.output_text.annotation.added'.
    - const ResponseOutputTextAnnotationAddedResponseOutputTextAnnotationAdded ResponseOutputTextAnnotationAdded = "response.output_text.annotation.added"
- type ResponseQueuedEvent struct{…}
  
  Emitted when a response is queued and waiting to be processed.
  - Response Response
    
    The full response object that is queued.
  - SequenceNumber int64
    
    The sequence number for this event.
  - Type ResponseQueued
    
    The type of the event. Always 'response.queued'.
    - const ResponseQueuedResponseQueued ResponseQueued = "response.queued"
- type ResponseCustomToolCallInputDeltaEvent struct{…}
  
  Event representing a delta (partial update) to the input of a custom tool call.
  - Delta string
    
    The incremental input data (delta) for the custom tool call.
  - ItemID string
    
    Unique identifier for the API item associated with this event.
  - OutputIndex int64
    
    The index of the output this delta applies to.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseCustomToolCallInputDelta
    
    The event type identifier.
    - const ResponseCustomToolCallInputDeltaResponseCustomToolCallInputDelta ResponseCustomToolCallInputDelta = "response.custom_tool_call_input.delta"
- type ResponseCustomToolCallInputDoneEvent struct{…}
  
  Event indicating that input for a custom tool call is complete.
  - Input string
    
    The complete input data for the custom tool call.
  - ItemID string
    
    Unique identifier for the API item associated with this event.
  - OutputIndex int64
    
    The index of the output this event applies to.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseCustomToolCallInputDone
    
    The event type identifier.
    - const ResponseCustomToolCallInputDoneResponseCustomToolCallInputDone ResponseCustomToolCallInputDone = "response.custom_tool_call_input.done"

Response Text Config

type ResponseTextConfig struct{…}

Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
- Text inputs and outputs
- Structured Outputs
- Format ResponseFormatTextConfigUnion
  
  An object specifying the format that the model must output.
  
  Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
  
  The default format is { "type": "text" } with no additional options.
  
  Not recommended for gpt-4o and newer models:
  
  Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
  - type ResponseFormatText struct{…}
    
    Default response format. Used to generate text responses.
    - Type Text
      
      The type of response format being defined. Always text.
      - const TextText Text = "text"
  - type ResponseFormatTextJSONSchemaConfig struct{…}
    
    JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
    - Name string
      
      The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
    - Schema map[string, any]
      
      The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
    - Type JSONSchema
      
      The type of response format being defined. Always json_schema.
      - const JSONSchemaJSONSchema JSONSchema = "json_schema"
    - Description string
      
      A description of what the response format is for, used by the model to determine how to respond in the format.
    - Strict bool
      
      Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
  - type ResponseFormatJSONObject struct{…}
    
    JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
    - Type JSONObject
      
      The type of response format being defined. Always json_object.
      - const JSONObjectJSONObject JSONObject = "json_object"
- Verbosity ResponseTextConfigVerbosity
  
  Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
  - const ResponseTextConfigVerbosityLow ResponseTextConfigVerbosity = "low"
  - const ResponseTextConfigVerbosityMedium ResponseTextConfigVerbosity = "medium"
  - const ResponseTextConfigVerbosityHigh ResponseTextConfigVerbosity = "high"

Response Text Delta Event

type ResponseTextDeltaEvent struct{…}

Emitted when there is an additional text delta.
- ContentIndex int64
  
  The index of the content part that the text delta was added to.
- Delta string
  
  The text delta that was added.
- ItemID string
  
  The ID of the output item that the text delta was added to.
- Logprobs []ResponseTextDeltaEventLogprob
  
  The log probabilities of the tokens in the delta.
  - Token string
    
    A possible text token.
  - Logprob float64
    
    The log probability of this token.
  - TopLogprobs []ResponseTextDeltaEventLogprobTopLogprob
    
    The log probabilities of up to 20 of the most likely tokens.
    - Token string
      
      A possible text token.
    - Logprob float64
      
      The log probability of this token.
- OutputIndex int64
  
  The index of the output item that the text delta was added to.
- SequenceNumber int64
  
  The sequence number for this event.
- Type ResponseOutputTextDelta
  
  The type of the event. Always response.output_text.delta.
  - const ResponseOutputTextDeltaResponseOutputTextDelta ResponseOutputTextDelta = "response.output_text.delta"

Response Text Done Event

type ResponseTextDoneEvent struct{…}

Emitted when text content is finalized.
- ContentIndex int64
  
  The index of the content part that the text content is finalized.
- ItemID string
  
  The ID of the output item that the text content is finalized.
- Logprobs []ResponseTextDoneEventLogprob
  
  The log probabilities of the tokens in the delta.
  - Token string
    
    A possible text token.
  - Logprob float64
    
    The log probability of this token.
  - TopLogprobs []ResponseTextDoneEventLogprobTopLogprob
    
    The log probabilities of up to 20 of the most likely tokens.
    - Token string
      
      A possible text token.
    - Logprob float64
      
      The log probability of this token.
- OutputIndex int64
  
  The index of the output item that the text content is finalized.
- SequenceNumber int64
  
  The sequence number for this event.
- Text string
  
  The text content that is finalized.
- Type ResponseOutputTextDone
  
  The type of the event. Always response.output_text.done.
  - const ResponseOutputTextDoneResponseOutputTextDone ResponseOutputTextDone = "response.output_text.done"

Response Tool Search Call

type ResponseToolSearchCall struct{…}
- ID string
  
  The unique ID of the tool search call item.
- Arguments any
  
  Arguments used for the tool search call.
- CallID string
  
  The unique ID of the tool search call generated by the model.
- Execution ResponseToolSearchCallExecution
  
  Whether tool search was executed by the server or by the client.
  - const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
  - const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
- Status ResponseToolSearchCallStatus
  
  The status of the tool search call item that was recorded.
  - const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
  - const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
  - const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
- Type ToolSearchCall
  
  The type of the item. Always tool_search_call.
  - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
- CreatedBy string
  
  The identifier of the actor that created the item.

Response Tool Search Output Item

type ResponseToolSearchOutputItem struct{…}
- ID string
  
  The unique ID of the tool search output item.
- CallID string
  
  The unique ID of the tool search call generated by the model.
- Execution ResponseToolSearchOutputItemExecution
  
  Whether tool search was executed by the server or by the client.
  - const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
  - const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
- Status ResponseToolSearchOutputItemStatus
  
  The status of the tool search output item that was recorded.
  - const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
  - const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
  - const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
- Tools []ToolUnion
  
  The loaded tool definitions returned by tool search.
  - type FunctionTool struct{…}
    
    Defines a function in your own code the model can choose to call. Learn more about function calling.
    - Name string
      
      The name of the function to call.
    - Parameters map[string, any]
      
      A JSON schema object describing the parameters of the function.
    - Strict bool
      
      Whether to enforce strict parameter validation. Default true.
    - Type Function
      
      The type of the function tool. Always function.
      - const FunctionFunction Function = "function"
    - DeferLoading bool
      
      Whether this function is deferred and loaded via tool search.
    - Description string
      
      A description of the function. Used by the model to determine whether or not to call the function.
  - type FileSearchTool struct{…}
    
    A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
    - Type FileSearch
      
      The type of the file search tool. Always file_search.
      - const FileSearchFileSearch FileSearch = "file_search"
    - VectorStoreIDs []string
      
      The IDs of the vector stores to search.
    - Filters FileSearchToolFiltersUnion
      
      A filter to apply.
      - type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
      - type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
    - MaxNumResults int64
      
      The maximum number of results to return. This number should be between 1 and 50 inclusive.
    - RankingOptions FileSearchToolRankingOptions
      
      Ranking options for search.
      - HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
      - Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
      - ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
  - type ComputerTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
    - Type Computer
      
      The type of the computer tool. Always computer.
      - const ComputerComputer Computer = "computer"
  - type ComputerUsePreviewTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
    - DisplayHeight int64
      
      The height of the computer display.
    - DisplayWidth int64
      
      The width of the computer display.
    - Environment ComputerUsePreviewToolEnvironment
      
      The type of computer environment to control.
      - const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
      - const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
      - const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
      - const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
      - const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
    - Type ComputerUsePreview
      
      The type of the computer use tool. Always computer_use_preview.
      - const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
  - type WebSearchTool struct{…}
    
    Search the Internet for sources related to the prompt. Learn more about the web search tool.
    - Type WebSearchToolType
      
      The type of the web search tool. One of web_search or web_search_2025_08_26.
      - const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
      - const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
    - Filters WebSearchToolFilters
      
      Filters for the search.
      - AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
    - SearchContextSize WebSearchToolSearchContextSize
      
      High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
      - const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
      - const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
      - const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
    - UserLocation WebSearchToolUserLocation
      
      The approximate location of the user.
      - City string
        
        Free text input for the city of the user, e.g. San Francisco.
      - Country string
        
        The two-letter ISO country code of the user, e.g. US.
      - Region string
        
        Free text input for the region of the user, e.g. California.
      - Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
      - Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
  - type ToolMcp struct{…}
    
    Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
    - ServerLabel string
      
      A label for this MCP server, used to identify it in tool calls.
    - Type Mcp
      
      The type of the MCP tool. Always mcp.
      - const McpMcp Mcp = "mcp"
    - AllowedTools ToolMcpAllowedToolsUnion
      
      List of allowed tool names or a filter object.
      - type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
      - type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
    - Authorization string
      
      An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
    - ConnectorID string
      
      Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
      
      Currently supported connector_id values are:
      - Dropbox: connector_dropbox
      - Gmail: connector_gmail
      - Google Calendar: connector_googlecalendar
      - Google Drive: connector_googledrive
      - Microsoft Teams: connector_microsoftteams
      - Outlook Calendar: connector_outlookcalendar
      - Outlook Email: connector_outlookemail
      - SharePoint: connector_sharepoint
      - const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
      - const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
      - const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
      - const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
      - const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
      - const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
      - const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
      - const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
    - DeferLoading bool
      
      Whether this MCP tool is deferred and discovered via tool search.
    - Headers map[string, string]
      
      Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
    - RequireApproval ToolMcpRequireApprovalUnion
      
      Specify which of the MCP server's tools require approval.
      - type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
      - type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
    - ServerDescription string
      
      Optional description of the MCP server, used to provide more context.
    - ServerURL string
      
      The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
    - TunnelID string
      
      The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
  - type ToolCodeInterpreter struct{…}
    
    A tool that runs Python code to help generate a response to a prompt.
    - Container ToolCodeInterpreterContainerUnion
      
      The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
      - string
      - type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
    - Type CodeInterpreter
      
      The type of the code interpreter tool. Always code_interpreter.
      - const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
  - type ToolImageGeneration struct{…}
    
    A tool that generates images using the GPT image models.
    - Type ImageGeneration
      
      The type of the image generation tool. Always image_generation.
      - const ImageGenerationImageGeneration ImageGeneration = "image_generation"
    - Action string
      
      Whether to generate a new image or edit an existing image. Default: auto.
      - const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
      - const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
      - const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
    - Background string
      
      Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
      
      gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
      
      If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
      - const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
      - const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
      - const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
    - InputFidelity string
      
      Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
      - const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
      - const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
    - InputImageMask ToolImageGenerationInputImageMask
      
      Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
      - FileID string
        
        File ID for the mask image.
      - ImageURL string
        
        Base64-encoded mask image.
    - Model string
      
      The image generation model to use. Default: gpt-image-1.
      - string
      - string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
    - Moderation string
      
      Moderation level for the generated image. Default: auto.
      - const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
      - const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
    - OutputCompression int64
      
      Compression level for the output image. Default: 100.
    - OutputFormat string
      
      The output format of the generated image. One of png, webp, or jpeg. Default: png.
      - const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
      - const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
      - const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
    - PartialImages int64
      
      Number of partial images to generate in streaming mode, from 0 (default value) to 3.
    - Quality string
      
      The quality of the generated image. One of low, medium, high, or auto. Default: auto.
      - const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
      - const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
      - const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
      - const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
    - Size string
      
      The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
      - string
      - string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
  - type ToolLocalShell struct{…}
    
    A tool that allows the model to execute shell commands in a local environment.
    - Type LocalShell
      
      The type of the local shell tool. Always local_shell.
      - const LocalShellLocalShell LocalShell = "local_shell"
  - type FunctionShellTool struct{…}
    
    A tool that allows the model to execute shell commands.
    - Type Shell
      
      The type of the shell tool. Always shell.
      - const ShellShell Shell = "shell"
    - Environment FunctionShellToolEnvironmentUnion
      - type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
      - type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
      - type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
  - type CustomTool struct{…}
    
    A custom tool that processes input using a specified format. Learn more about custom tools
    - Name string
      
      The name of the custom tool, used to identify it in tool calls.
    - Type Custom
      
      The type of the custom tool. Always custom.
      - const CustomCustom Custom = "custom"
    - DeferLoading bool
      
      Whether this tool should be deferred and discovered via tool search.
    - Description string
      
      Optional description of the custom tool, used to provide more context.
    - Format CustomToolInputFormatUnion
      
      The input format for the custom tool. Default is unconstrained text.
      - type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
      - type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
  - type NamespaceTool struct{…}
    
    Groups function/custom tools under a shared namespace.
    - Description string
      
      A description of the namespace shown to the model.
    - Name string
      
      The namespace name used in tool calls (for example, crm).
    - Tools []NamespaceToolToolUnion
      
      The function/custom tools available inside this namespace.
      - type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
    - Type Namespace
      
      The type of the tool. Always namespace.
      - const NamespaceNamespace Namespace = "namespace"
  - type ToolSearchTool struct{…}
    
    Hosted or BYOT tool search configuration for deferred tools.
    - Type ToolSearch
      
      The type of the tool. Always tool_search.
      - const ToolSearchToolSearch ToolSearch = "tool_search"
    - Description string
      
      Description shown to the model for a client-executed tool search tool.
    - Execution ToolSearchToolExecution
      
      Whether tool search is executed by the server or by the client.
      - const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
      - const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
    - Parameters any
      
      Parameter schema for a client-executed tool search tool.
  - type WebSearchPreviewTool struct{…}
    
    This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
    - Type WebSearchPreviewToolType
      
      The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
      - const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
      - const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
    - SearchContentTypes []string
      - const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
      - const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
    - SearchContextSize WebSearchPreviewToolSearchContextSize
      
      High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
      - const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
      - const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
      - const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
    - UserLocation WebSearchPreviewToolUserLocation
      
      The user's location.
      - Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
      - City string
        
        Free text input for the city of the user, e.g. San Francisco.
      - Country string
        
        The two-letter ISO country code of the user, e.g. US.
      - Region string
        
        Free text input for the region of the user, e.g. California.
      - Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
  - type ApplyPatchTool struct{…}
    
    Allows the assistant to create, delete, or update files using unified diffs.
    - Type ApplyPatch
      
      The type of the tool. Always apply_patch.
      - const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
- Type ToolSearchOutput
  
  The type of the item. Always tool_search_output.
  - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
- CreatedBy string
  
  The identifier of the actor that created the item.

Response Tool Search Output Item Param

type ResponseToolSearchOutputItemParamResp struct{…}
- Tools []ToolUnion
  
  The loaded tool definitions returned by the tool search output.
  - type FunctionTool struct{…}
    
    Defines a function in your own code the model can choose to call. Learn more about function calling.
    - Name string
      
      The name of the function to call.
    - Parameters map[string, any]
      
      A JSON schema object describing the parameters of the function.
    - Strict bool
      
      Whether to enforce strict parameter validation. Default true.
    - Type Function
      
      The type of the function tool. Always function.
      - const FunctionFunction Function = "function"
    - DeferLoading bool
      
      Whether this function is deferred and loaded via tool search.
    - Description string
      
      A description of the function. Used by the model to determine whether or not to call the function.
  - type FileSearchTool struct{…}
    
    A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
    - Type FileSearch
      
      The type of the file search tool. Always file_search.
      - const FileSearchFileSearch FileSearch = "file_search"
    - VectorStoreIDs []string
      
      The IDs of the vector stores to search.
    - Filters FileSearchToolFiltersUnion
      
      A filter to apply.
      - type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
      - type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
    - MaxNumResults int64
      
      The maximum number of results to return. This number should be between 1 and 50 inclusive.
    - RankingOptions FileSearchToolRankingOptions
      
      Ranking options for search.
      - HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
      - Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
      - ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
  - type ComputerTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
    - Type Computer
      
      The type of the computer tool. Always computer.
      - const ComputerComputer Computer = "computer"
  - type ComputerUsePreviewTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
    - DisplayHeight int64
      
      The height of the computer display.
    - DisplayWidth int64
      
      The width of the computer display.
    - Environment ComputerUsePreviewToolEnvironment
      
      The type of computer environment to control.
      - const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
      - const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
      - const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
      - const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
      - const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
    - Type ComputerUsePreview
      
      The type of the computer use tool. Always computer_use_preview.
      - const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
  - type WebSearchTool struct{…}
    
    Search the Internet for sources related to the prompt. Learn more about the web search tool.
    - Type WebSearchToolType
      
      The type of the web search tool. One of web_search or web_search_2025_08_26.
      - const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
      - const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
    - Filters WebSearchToolFilters
      
      Filters for the search.
      - AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
    - SearchContextSize WebSearchToolSearchContextSize
      
      High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
      - const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
      - const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
      - const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
    - UserLocation WebSearchToolUserLocation
      
      The approximate location of the user.
      - City string
        
        Free text input for the city of the user, e.g. San Francisco.
      - Country string
        
        The two-letter ISO country code of the user, e.g. US.
      - Region string
        
        Free text input for the region of the user, e.g. California.
      - Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
      - Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
  - type ToolMcp struct{…}
    
    Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
    - ServerLabel string
      
      A label for this MCP server, used to identify it in tool calls.
    - Type Mcp
      
      The type of the MCP tool. Always mcp.
      - const McpMcp Mcp = "mcp"
    - AllowedTools ToolMcpAllowedToolsUnion
      
      List of allowed tool names or a filter object.
      - type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
      - type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
    - Authorization string
      
      An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
    - ConnectorID string
      
      Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
      
      Currently supported connector_id values are:
      - Dropbox: connector_dropbox
      - Gmail: connector_gmail
      - Google Calendar: connector_googlecalendar
      - Google Drive: connector_googledrive
      - Microsoft Teams: connector_microsoftteams
      - Outlook Calendar: connector_outlookcalendar
      - Outlook Email: connector_outlookemail
      - SharePoint: connector_sharepoint
      - const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
      - const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
      - const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
      - const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
      - const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
      - const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
      - const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
      - const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
    - DeferLoading bool
      
      Whether this MCP tool is deferred and discovered via tool search.
    - Headers map[string, string]
      
      Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
    - RequireApproval ToolMcpRequireApprovalUnion
      
      Specify which of the MCP server's tools require approval.
      - type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
      - type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
    - ServerDescription string
      
      Optional description of the MCP server, used to provide more context.
    - ServerURL string
      
      The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
    - TunnelID string
      
      The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
  - type ToolCodeInterpreter struct{…}
    
    A tool that runs Python code to help generate a response to a prompt.
    - Container ToolCodeInterpreterContainerUnion
      
      The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
      - string
      - type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
    - Type CodeInterpreter
      
      The type of the code interpreter tool. Always code_interpreter.
      - const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
  - type ToolImageGeneration struct{…}
    
    A tool that generates images using the GPT image models.
    - Type ImageGeneration
      
      The type of the image generation tool. Always image_generation.
      - const ImageGenerationImageGeneration ImageGeneration = "image_generation"
    - Action string
      
      Whether to generate a new image or edit an existing image. Default: auto.
      - const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
      - const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
      - const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
    - Background string
      
      Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
      
      gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
      
      If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
      - const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
      - const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
      - const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
    - InputFidelity string
      
      Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
      - const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
      - const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
    - InputImageMask ToolImageGenerationInputImageMask
      
      Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
      - FileID string
        
        File ID for the mask image.
      - ImageURL string
        
        Base64-encoded mask image.
    - Model string
      
      The image generation model to use. Default: gpt-image-1.
      - string
      - string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
    - Moderation string
      
      Moderation level for the generated image. Default: auto.
      - const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
      - const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
    - OutputCompression int64
      
      Compression level for the output image. Default: 100.
    - OutputFormat string
      
      The output format of the generated image. One of png, webp, or jpeg. Default: png.
      - const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
      - const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
      - const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
    - PartialImages int64
      
      Number of partial images to generate in streaming mode, from 0 (default value) to 3.
    - Quality string
      
      The quality of the generated image. One of low, medium, high, or auto. Default: auto.
      - const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
      - const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
      - const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
      - const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
    - Size string
      
      The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
      - string
      - string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
  - type ToolLocalShell struct{…}
    
    A tool that allows the model to execute shell commands in a local environment.
    - Type LocalShell
      
      The type of the local shell tool. Always local_shell.
      - const LocalShellLocalShell LocalShell = "local_shell"
  - type FunctionShellTool struct{…}
    
    A tool that allows the model to execute shell commands.
    - Type Shell
      
      The type of the shell tool. Always shell.
      - const ShellShell Shell = "shell"
    - Environment FunctionShellToolEnvironmentUnion
      - type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
      - type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
      - type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
  - type CustomTool struct{…}
    
    A custom tool that processes input using a specified format. Learn more about custom tools
    - Name string
      
      The name of the custom tool, used to identify it in tool calls.
    - Type Custom
      
      The type of the custom tool. Always custom.
      - const CustomCustom Custom = "custom"
    - DeferLoading bool
      
      Whether this tool should be deferred and discovered via tool search.
    - Description string
      
      Optional description of the custom tool, used to provide more context.
    - Format CustomToolInputFormatUnion
      
      The input format for the custom tool. Default is unconstrained text.
      - type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
      - type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
  - type NamespaceTool struct{…}
    
    Groups function/custom tools under a shared namespace.
    - Description string
      
      A description of the namespace shown to the model.
    - Name string
      
      The namespace name used in tool calls (for example, crm).
    - Tools []NamespaceToolToolUnion
      
      The function/custom tools available inside this namespace.
      - type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
    - Type Namespace
      
      The type of the tool. Always namespace.
      - const NamespaceNamespace Namespace = "namespace"
  - type ToolSearchTool struct{…}
    
    Hosted or BYOT tool search configuration for deferred tools.
    - Type ToolSearch
      
      The type of the tool. Always tool_search.
      - const ToolSearchToolSearch ToolSearch = "tool_search"
    - Description string
      
      Description shown to the model for a client-executed tool search tool.
    - Execution ToolSearchToolExecution
      
      Whether tool search is executed by the server or by the client.
      - const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
      - const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
    - Parameters any
      
      Parameter schema for a client-executed tool search tool.
  - type WebSearchPreviewTool struct{…}
    
    This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
    - Type WebSearchPreviewToolType
      
      The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
      - const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
      - const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
    - SearchContentTypes []string
      - const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
      - const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
    - SearchContextSize WebSearchPreviewToolSearchContextSize
      
      High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
      - const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
      - const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
      - const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
    - UserLocation WebSearchPreviewToolUserLocation
      
      The user's location.
      - Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
      - City string
        
        Free text input for the city of the user, e.g. San Francisco.
      - Country string
        
        The two-letter ISO country code of the user, e.g. US.
      - Region string
        
        Free text input for the region of the user, e.g. California.
      - Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
  - type ApplyPatchTool struct{…}
    
    Allows the assistant to create, delete, or update files using unified diffs.
    - Type ApplyPatch
      
      The type of the tool. Always apply_patch.
      - const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
- Type ToolSearchOutput
  
  The item type. Always tool_search_output.
  - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
- ID string
  
  The unique ID of this tool search output.
- CallID string
  
  The unique ID of the tool search call generated by the model.
- Execution ResponseToolSearchOutputItemParamExecution
  
  Whether tool search was executed by the server or by the client.
  - const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
  - const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
- Status ResponseToolSearchOutputItemParamStatus
  
  The status of the tool search output.
  - const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
  - const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
  - const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"

Response Usage

type ResponseUsage struct{…}

Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
- InputTokens int64
  
  The number of input tokens.
- InputTokensDetails ResponseUsageInputTokensDetails
  
  A detailed breakdown of the input tokens.
  - CachedTokens int64
    
    The number of tokens that were retrieved from the cache. More on prompt caching.
- OutputTokens int64
  
  The number of output tokens.
- OutputTokensDetails ResponseUsageOutputTokensDetails
  
  A detailed breakdown of the output tokens.
  - ReasoningTokens int64
    
    The number of reasoning tokens.
- TotalTokens int64
  
  The total number of tokens used.

Response Web Search Call Completed Event

type ResponseWebSearchCallCompletedEvent struct{…}

Emitted when a web search call is completed.
- ItemID string
  
  Unique ID for the output item associated with the web search call.
- OutputIndex int64
  
  The index of the output item that the web search call is associated with.
- SequenceNumber int64
  
  The sequence number of the web search call being processed.
- Type ResponseWebSearchCallCompleted
  
  The type of the event. Always response.web_search_call.completed.
  - const ResponseWebSearchCallCompletedResponseWebSearchCallCompleted ResponseWebSearchCallCompleted = "response.web_search_call.completed"

Response Web Search Call In Progress Event

type ResponseWebSearchCallInProgressEvent struct{…}

Emitted when a web search call is initiated.
- ItemID string
  
  Unique ID for the output item associated with the web search call.
- OutputIndex int64
  
  The index of the output item that the web search call is associated with.
- SequenceNumber int64
  
  The sequence number of the web search call being processed.
- Type ResponseWebSearchCallInProgress
  
  The type of the event. Always response.web_search_call.in_progress.
  - const ResponseWebSearchCallInProgressResponseWebSearchCallInProgress ResponseWebSearchCallInProgress = "response.web_search_call.in_progress"

Response Web Search Call Searching Event

type ResponseWebSearchCallSearchingEvent struct{…}

Emitted when a web search call is executing.
- ItemID string
  
  Unique ID for the output item associated with the web search call.
- OutputIndex int64
  
  The index of the output item that the web search call is associated with.
- SequenceNumber int64
  
  The sequence number of the web search call being processed.
- Type ResponseWebSearchCallSearching
  
  The type of the event. Always response.web_search_call.searching.
  - const ResponseWebSearchCallSearchingResponseWebSearchCallSearching ResponseWebSearchCallSearching = "response.web_search_call.searching"

Responses Client Event

type ResponsesClientEvent struct{…}
- Type ResponseCreate
  
  The type of the client event. Always response.create.
  - const ResponseCreateResponseCreate ResponseCreate = "response.create"
- Background bool
  
  Whether to run the model response in the background. Learn more.
- ContextManagement []ResponsesClientEventContextManagement
  
  Context management configuration for this request.
  - Type string
    
    The context management entry type. Currently only 'compaction' is supported.
  - CompactThreshold int64
    
    Token threshold at which compaction should be triggered for this entry.
- Conversation ResponsesClientEventConversationUnion
  
  The conversation that this response belongs to. Items from this conversation are prepended to input_items for this response request. Input items and output items from this response are automatically added to this conversation after this response completes.
  - string
  - type ResponseConversationParamResp struct{…}
    
    The conversation that this response belongs to.
    - ID string
      
      The unique ID of the conversation.
- Include []ResponseIncludable
  
  Specify additional output data to include in the model response. Currently supported values are:
  - web_search_call.action.sources: Include the sources of the web search tool call.
  - code_interpreter_call.outputs: Includes the outputs of python code execution in code interpreter tool call items.
  - computer_call_output.output.image_url: Include image urls from the computer call output.
  - file_search_call.results: Include the search results of the file search tool call.
  - message.input_image.image_url: Include image urls from the input message.
  - message.output_text.logprobs: Include logprobs with assistant messages.
  - reasoning.encrypted_content: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the store parameter is set to false, or when an organization is enrolled in the zero data retention program).
  - const ResponseIncludableFileSearchCallResults ResponseIncludable = "file_search_call.results"
  - const ResponseIncludableWebSearchCallResults ResponseIncludable = "web_search_call.results"
  - const ResponseIncludableWebSearchCallActionSources ResponseIncludable = "web_search_call.action.sources"
  - const ResponseIncludableMessageInputImageImageURL ResponseIncludable = "message.input_image.image_url"
  - const ResponseIncludableComputerCallOutputOutputImageURL ResponseIncludable = "computer_call_output.output.image_url"
  - const ResponseIncludableCodeInterpreterCallOutputs ResponseIncludable = "code_interpreter_call.outputs"
  - const ResponseIncludableReasoningEncryptedContent ResponseIncludable = "reasoning.encrypted_content"
  - const ResponseIncludableMessageOutputTextLogprobs ResponseIncludable = "message.output_text.logprobs"
- Input ResponsesClientEventInputUnion
  
  Text, image, or file inputs to the model, used to generate a response.
  
  Learn more:
  - Text inputs and outputs
  - Image inputs
  - File inputs
  - Conversation state
  - Function calling
  - string
  - type ResponseInput []ResponseInputItemUnion
    
    A list of one or many input items to the model, containing different content types.
    - type EasyInputMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
      - Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
      - Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
      - Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
    - type ResponseInputItemMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
      - Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
      - Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
      - Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
      - Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
      - ID string
        
        The unique ID of the output message.
      - Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
      - Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
      - Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
      - Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
      - Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
      - ID string
        
        The unique ID of the file search tool call.
      - Queries []string
        
        The queries used to search for files.
      - Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
      - Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
      - Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
      - ID string
        
        The unique ID of the computer call.
      - CallID string
        
        An identifier used when responding to the tool call with output.
      - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
      - Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
      - Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
      - Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
    - type ResponseInputItemComputerCallOutput struct{…}
      
      The output of a computer tool call.
      - CallID string
        
        The ID of the computer tool call that produced the output.
      - Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
      - Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
      - ID string
        
        The ID of the computer tool call output.
      - AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
      - ID string
        
        The unique ID of the web search tool call.
      - Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
      - Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
      - Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
      - Arguments string
        
        A JSON string of the arguments to pass to the function.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Name string
        
        The name of the function to run.
      - Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
      - ID string
        
        The unique ID of the function tool call.
      - Namespace string
        
        The namespace of the function to run.
      - Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
    - type ResponseInputItemFunctionCallOutput struct{…}
      
      The output of a function tool call.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
      - ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
    - type ResponseInputItemToolSearchCall struct{…}
      - Arguments any
        
        The arguments supplied to the tool search call.
      - Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
      - ID string
        
        The unique ID of this tool search call.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
      - Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
    - type ResponseToolSearchOutputItemParamResp struct{…}
      - Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
      - Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
      - ID string
        
        The unique ID of this tool search output.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
      - Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
    - type ResponseInputItemAdditionalTools struct{…}
      - Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
      - Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
      - ID string
        
        The unique ID of this additional tools item.
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
      - ID string
        
        The unique identifier of the reasoning content.
      - Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
      - Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
      - Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
      - EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
      - Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
    - type ResponseCompactionItemParamResp struct{…}
      
      A compaction item generated by the v1/responses/compact API.
      - EncryptedContent string
        
        The encrypted content of the compaction summary.
      - Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
      - ID string
        
        The ID of the compaction item.
    - type ResponseInputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
      - ID string
        
        The unique ID of the image generation call.
      - Result string
        
        The generated image encoded in base64.
      - Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
      - Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
      - ID string
        
        The unique ID of the code interpreter tool call.
      - Code string
        
        The code to run, or null if not available.
      - ContainerID string
        
        The ID of the container used to run the code.
      - Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
      - Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
      - Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
    - type ResponseInputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
      - ID string
        
        The unique ID of the local shell call.
      - Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
      - CallID string
        
        The unique ID of the local shell tool call generated by the model.
      - Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
      - Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
    - type ResponseInputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
      - ID string
        
        The unique ID of the local shell tool call generated by the model.
      - Output string
        
        A JSON string of the output of the local shell tool call.
      - Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
    - type ResponseInputItemShellCall struct{…}
      
      A tool representing a request to execute one or more shell commands.
      - Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
      - ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
      - Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
      - Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
    - type ResponseInputItemShellCallOutput struct{…}
      
      The streamed output items emitted by a shell tool call.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
      - Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
      - ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
      - MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
      - Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
    - type ResponseInputItemApplyPatchCall struct{…}
      
      A tool call representing a request to create, delete, or update files using diff patches.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
      - Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
      - Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
      - ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - type ResponseInputItemApplyPatchCallOutput struct{…}
      
      The streamed output emitted by an apply patch tool call.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
      - Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
      - ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
      - Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
    - type ResponseInputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
      - ID string
        
        The unique ID of the list.
      - ServerLabel string
        
        The label of the MCP server.
      - Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
      - Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
      - Error string
        
        Error message if the server could not list tools.
    - type ResponseInputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
      - ID string
        
        The unique ID of the approval request.
      - Arguments string
        
        A JSON string of arguments for the tool.
      - Name string
        
        The name of the tool to run.
      - ServerLabel string
        
        The label of the MCP server making the request.
      - Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
    - type ResponseInputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
      - ApprovalRequestID string
        
        The ID of the approval request being answered.
      - Approve bool
        
        Whether the request was approved.
      - Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
      - ID string
        
        The unique ID of the approval response
      - Reason string
        
        Optional reason for the decision.
    - type ResponseInputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
      - ID string
        
        The unique ID of the tool call.
      - Arguments string
        
        A JSON string of the arguments passed to the tool.
      - Name string
        
        The name of the tool that was run.
      - ServerLabel string
        
        The label of the MCP server running the tool.
      - Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
      - ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
      - Error string
        
        The error from the tool call, if any.
      - Output string
        
        The output from the tool call.
      - Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
    - type ResponseCustomToolCallOutput struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
      - CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
      - Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
      - ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
      - CallID string
        
        An identifier used to map this custom tool call to a tool call output.
      - Input string
        
        The input for the custom tool call generated by the model.
      - Name string
        
        The name of the custom tool being called.
      - Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
      - ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
      - Namespace string
        
        The namespace of the custom tool being called.
    - type ResponseInputItemCompactionTrigger struct{…}
      
      Compacts the current context. Must be the final input item.
      - Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
    - type ResponseInputItemItemReference struct{…}
      
      An internal identifier for an item to reference.
      - ID string
        
        The ID of the item to reference.
      - Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
- Instructions string
  
  A system (or developer) message inserted into the model's context.
  
  When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
- MaxOutputTokens int64
  
  An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
- MaxToolCalls int64
  
  The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
- Metadata Metadata
  
  Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
  
  Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
- Model ResponsesModel
  
  Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
  - string
  - type ChatModel string
    - const ChatModelGPT5_4 ChatModel = "gpt-5.4"
    - const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"
    - const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"
    - const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"
    - const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"
    - const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"
    - const ChatModelGPT5_2 ChatModel = "gpt-5.2"
    - const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"
    - const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"
    - const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"
    - const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"
    - const ChatModelGPT5_1 ChatModel = "gpt-5.1"
    - const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"
    - const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"
    - const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"
    - const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"
    - const ChatModelGPT5 ChatModel = "gpt-5"
    - const ChatModelGPT5Mini ChatModel = "gpt-5-mini"
    - const ChatModelGPT5Nano ChatModel = "gpt-5-nano"
    - const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"
    - const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"
    - const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"
    - const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"
    - const ChatModelGPT4_1 ChatModel = "gpt-4.1"
    - const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"
    - const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"
    - const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"
    - const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"
    - const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"
    - const ChatModelO4Mini ChatModel = "o4-mini"
    - const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"
    - const ChatModelO3 ChatModel = "o3"
    - const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"
    - const ChatModelO3Mini ChatModel = "o3-mini"
    - const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"
    - const ChatModelO1 ChatModel = "o1"
    - const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"
    - const ChatModelO1Preview ChatModel = "o1-preview"
    - const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"
    - const ChatModelO1Mini ChatModel = "o1-mini"
    - const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"
    - const ChatModelGPT4o ChatModel = "gpt-4o"
    - const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"
    - const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"
    - const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"
    - const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"
    - const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"
    - const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"
    - const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"
    - const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"
    - const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"
    - const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"
    - const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"
    - const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"
    - const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"
    - const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"
    - const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"
    - const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"
    - const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"
    - const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"
    - const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"
    - const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"
    - const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"
    - const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"
    - const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"
    - const ChatModelGPT4 ChatModel = "gpt-4"
    - const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"
    - const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"
    - const ChatModelGPT4_32k ChatModel = "gpt-4-32k"
    - const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"
    - const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"
    - const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"
    - const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"
    - const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"
    - const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"
    - const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"
    - const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"
    - const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"
  - type ResponsesModel string
    - const ResponsesModelO1Pro ResponsesModel = "o1-pro"
    - const ResponsesModelO1Pro2025_03_19 ResponsesModel = "o1-pro-2025-03-19"
    - const ResponsesModelO3Pro ResponsesModel = "o3-pro"
    - const ResponsesModelO3Pro2025_06_10 ResponsesModel = "o3-pro-2025-06-10"
    - const ResponsesModelO3DeepResearch ResponsesModel = "o3-deep-research"
    - const ResponsesModelO3DeepResearch2025_06_26 ResponsesModel = "o3-deep-research-2025-06-26"
    - const ResponsesModelO4MiniDeepResearch ResponsesModel = "o4-mini-deep-research"
    - const ResponsesModelO4MiniDeepResearch2025_06_26 ResponsesModel = "o4-mini-deep-research-2025-06-26"
    - const ResponsesModelComputerUsePreview ResponsesModel = "computer-use-preview"
    - const ResponsesModelComputerUsePreview2025_03_11 ResponsesModel = "computer-use-preview-2025-03-11"
    - const ResponsesModelGPT5Codex ResponsesModel = "gpt-5-codex"
    - const ResponsesModelGPT5Pro ResponsesModel = "gpt-5-pro"
    - const ResponsesModelGPT5Pro2025_10_06 ResponsesModel = "gpt-5-pro-2025-10-06"
    - const ResponsesModelGPT5_1CodexMax ResponsesModel = "gpt-5.1-codex-max"
- Moderation ResponsesClientEventModeration
  
  Configuration for running moderation on the input and output of this response.
  - Model string
    
    The moderation model to use for moderated completions, e.g. 'omni-moderation-latest'.
- ParallelToolCalls bool
  
  Whether to allow the model to run tool calls in parallel.
- PreviousResponseID string
  
  The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
- Prompt ResponsePrompt
  
  Reference to a prompt template and its variables. Learn more.
  - ID string
    
    The unique identifier of the prompt template to use.
  - Variables map[string, ResponsePromptVariableUnion]
    
    Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
    - string
    - type ResponseInputText struct{…}
      
      A text input to the model.
    - type ResponseInputImage struct{…}
      
      An image input to the model. Learn about image inputs.
    - type ResponseInputFile struct{…}
      
      A file input to the model.
  - Version string
    
    Optional version of the prompt template.
- PromptCacheKey string
  
  Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
- PromptCacheRetention ResponsesClientEventPromptCacheRetention
  
  The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.
  
  For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:
  - Organizations without ZDR enabled default to 24h.
  - Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.
  - const ResponsesClientEventPromptCacheRetentionInMemory ResponsesClientEventPromptCacheRetention = "in_memory"
  - const ResponsesClientEventPromptCacheRetention24h ResponsesClientEventPromptCacheRetention = "24h"
- Reasoning Reasoning
  
  gpt-5 and o-series models only
  
  Configuration options for reasoning models.
  - Context ReasoningContext
    
    Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
    - const ReasoningContextAuto ReasoningContext = "auto"
    - const ReasoningContextCurrentTurn ReasoningContext = "current_turn"
    - const ReasoningContextAllTurns ReasoningContext = "all_turns"
  - Effort ReasoningEffort
    
    Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
    - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
    - All models before gpt-5.1 default to medium reasoning effort, and do not support none.
    - The gpt-5-pro model defaults to (and only supports) high reasoning effort.
    - xhigh is supported for all models after gpt-5.1-codex-max.
    - const ReasoningEffortNone ReasoningEffort = "none"
    - const ReasoningEffortMinimal ReasoningEffort = "minimal"
    - const ReasoningEffortLow ReasoningEffort = "low"
    - const ReasoningEffortMedium ReasoningEffort = "medium"
    - const ReasoningEffortHigh ReasoningEffort = "high"
    - const ReasoningEffortXhigh ReasoningEffort = "xhigh"
  - GenerateSummary ReasoningGenerateSummary
    
    Deprecated: use summary instead.
    
    A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
    - const ReasoningGenerateSummaryAuto ReasoningGenerateSummary = "auto"
    - const ReasoningGenerateSummaryConcise ReasoningGenerateSummary = "concise"
    - const ReasoningGenerateSummaryDetailed ReasoningGenerateSummary = "detailed"
  - Summary ReasoningSummary
    
    A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
    
    concise is supported for computer-use-preview models and all reasoning models after gpt-5.
    - const ReasoningSummaryAuto ReasoningSummary = "auto"
    - const ReasoningSummaryConcise ReasoningSummary = "concise"
    - const ReasoningSummaryDetailed ReasoningSummary = "detailed"
- SafetyIdentifier string
  
  A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
- ServiceTier ResponsesClientEventServiceTier
  
  Specifies the processing type used for serving the request.
  - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
  - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
  - If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
  - When not set, the default behavior is 'auto'.
  When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
  - const ResponsesClientEventServiceTierAuto ResponsesClientEventServiceTier = "auto"
  - const ResponsesClientEventServiceTierDefault ResponsesClientEventServiceTier = "default"
  - const ResponsesClientEventServiceTierFlex ResponsesClientEventServiceTier = "flex"
  - const ResponsesClientEventServiceTierScale ResponsesClientEventServiceTier = "scale"
  - const ResponsesClientEventServiceTierPriority ResponsesClientEventServiceTier = "priority"
- Store bool
  
  Whether to store the generated model response for later retrieval via API.
- Stream bool
  
  If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section below for more information.
- StreamOptions ResponsesClientEventStreamOptions
  
  Options for streaming responses. Only set this when you set stream: true.
  - IncludeObfuscation bool
    
    When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an obfuscation field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set include_obfuscation to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API.
- Temperature float64
  
  What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
- Text ResponseTextConfig
  
  Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
  - Text inputs and outputs
  - Structured Outputs
  - Format ResponseFormatTextConfigUnion
    
    An object specifying the format that the model must output.
    
    Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
    
    The default format is { "type": "text" } with no additional options.
    
    Not recommended for gpt-4o and newer models:
    
    Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
    - type ResponseFormatText struct{…}
      
      Default response format. Used to generate text responses.
      - Type Text
        
        The type of response format being defined. Always text.
        
        const TextText Text = "text"
    - type ResponseFormatTextJSONSchemaConfig struct{…}
      
      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
      - Name string
        
        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
      - Schema map[string, any]
        
        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
      - Type JSONSchema
        
        The type of response format being defined. Always json_schema.
        
        const JSONSchemaJSONSchema JSONSchema = "json_schema"
      - Description string
        
        A description of what the response format is for, used by the model to determine how to respond in the format.
      - Strict bool
        
        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
    - type ResponseFormatJSONObject struct{…}
      
      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
      - Type JSONObject
        
        The type of response format being defined. Always json_object.
        
        const JSONObjectJSONObject JSONObject = "json_object"
  - Verbosity ResponseTextConfigVerbosity
    
    Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
    - const ResponseTextConfigVerbosityLow ResponseTextConfigVerbosity = "low"
    - const ResponseTextConfigVerbosityMedium ResponseTextConfigVerbosity = "medium"
    - const ResponseTextConfigVerbosityHigh ResponseTextConfigVerbosity = "high"
- ToolChoice ResponsesClientEventToolChoiceUnion
  
  How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.
  - type ToolChoiceOptions string
    
    Controls which (if any) tool is called by the model.
    
    none means the model will not call any tool and instead generates a message.
    
    auto means the model can pick between generating a message or calling one or more tools.
    
    required means the model must call one or more tools.
    - const ToolChoiceOptionsNone ToolChoiceOptions = "none"
    - const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
    - const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
  - type ToolChoiceAllowed struct{…}
    
    Constrains the tools available to the model to a pre-defined set.
    - Mode ToolChoiceAllowedMode
      
      Constrains the tools available to the model to a pre-defined set.
      
      auto allows the model to pick from among the allowed tools and generate a message.
      
      required requires the model to call one or more of the allowed tools.
      - const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
      - const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
    - Tools []map[string, any]
      
      A list of tool definitions that the model should be allowed to call.
      
      For the Responses API, the list of tool definitions might look like:
```
[
  { "type": "function", "name": "get_weather" },
  { "type": "mcp", "server_label": "deepwiki" },
  { "type": "image_generation" }
]
```
    - Type AllowedTools
      
      Allowed tool configuration type. Always allowed_tools.
      - const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
  - type ToolChoiceTypes struct{…}
    
    Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
    - Type ToolChoiceTypesType
      
      The type of hosted tool the model should to use. Learn more about built-in tools.
      
      Allowed values are:
      - file_search
      - web_search_preview
      - computer
      - computer_use_preview
      - computer_use
      - code_interpreter
      - image_generation
      - const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
      - const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
      - const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
      - const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
      - const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
      - const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
      - const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
      - const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
  - type ToolChoiceFunction struct{…}
    
    Use this option to force the model to call a specific function.
    - Name string
      
      The name of the function to call.
    - Type Function
      
      For function calling, the type is always function.
      - const FunctionFunction Function = "function"
  - type ToolChoiceMcp struct{…}
    
    Use this option to force the model to call a specific tool on a remote MCP server.
    - ServerLabel string
      
      The label of the MCP server to use.
    - Type Mcp
      
      For MCP tools, the type is always mcp.
      - const McpMcp Mcp = "mcp"
    - Name string
      
      The name of the tool to call on the server.
  - type ToolChoiceCustom struct{…}
    
    Use this option to force the model to call a specific custom tool.
    - Name string
      
      The name of the custom tool to call.
    - Type Custom
      
      For custom tool calling, the type is always custom.
      - const CustomCustom Custom = "custom"
  - type ToolChoiceApplyPatch struct{…}
    
    Forces the model to call the apply_patch tool when executing a tool call.
    - Type ApplyPatch
      
      The tool to call. Always apply_patch.
      - const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
  - type ToolChoiceShell struct{…}
    
    Forces the model to call the shell tool when a tool call is required.
    - Type Shell
      
      The tool to call. Always shell.
      - const ShellShell Shell = "shell"
- Tools []ToolUnion
  
  An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
  
  We support the following categories of tools:
  - Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
  - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
  - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
  - type FunctionTool struct{…}
    
    Defines a function in your own code the model can choose to call. Learn more about function calling.
  - type FileSearchTool struct{…}
    
    A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
  - type ComputerTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
  - type ComputerUsePreviewTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
  - type WebSearchTool struct{…}
    
    Search the Internet for sources related to the prompt. Learn more about the web search tool.
  - type ToolMcp struct{…}
    
    Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
  - type ToolCodeInterpreter struct{…}
    
    A tool that runs Python code to help generate a response to a prompt.
  - type ToolImageGeneration struct{…}
    
    A tool that generates images using the GPT image models.
  - type ToolLocalShell struct{…}
    
    A tool that allows the model to execute shell commands in a local environment.
  - type FunctionShellTool struct{…}
    
    A tool that allows the model to execute shell commands.
  - type CustomTool struct{…}
    
    A custom tool that processes input using a specified format. Learn more about custom tools
  - type NamespaceTool struct{…}
    
    Groups function/custom tools under a shared namespace.
  - type ToolSearchTool struct{…}
    
    Hosted or BYOT tool search configuration for deferred tools.
  - type WebSearchPreviewTool struct{…}
    
    This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
  - type ApplyPatchTool struct{…}
    
    Allows the assistant to create, delete, or update files using unified diffs.
- TopLogprobs int64
  
  An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
- TopP float64
  
  An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
  
  We generally recommend altering this or temperature but not both.
- Truncation ResponsesClientEventTruncation
  
  The truncation strategy to use for the model response.
  - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
  - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
  - const ResponsesClientEventTruncationAuto ResponsesClientEventTruncation = "auto"
  - const ResponsesClientEventTruncationDisabled ResponsesClientEventTruncation = "disabled"
- User string
  
  This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.

Responses Server Event

type ResponsesServerEventUnion interface{…}

Server events emitted by the Responses WebSocket server.
- type ResponseAudioDeltaEvent struct{…}
  
  Emitted when there is a partial audio response.
  - Delta string
    
    A chunk of Base64 encoded response audio bytes.
  - SequenceNumber int64
    
    A sequence number for this chunk of the stream response.
  - Type ResponseAudioDelta
    
    The type of the event. Always response.audio.delta.
    - const ResponseAudioDeltaResponseAudioDelta ResponseAudioDelta = "response.audio.delta"
- type ResponseAudioDoneEvent struct{…}
  
  Emitted when the audio response is complete.
  - SequenceNumber int64
    
    The sequence number of the delta.
  - Type ResponseAudioDone
    
    The type of the event. Always response.audio.done.
    - const ResponseAudioDoneResponseAudioDone ResponseAudioDone = "response.audio.done"
- type ResponseAudioTranscriptDeltaEvent struct{…}
  
  Emitted when there is a partial transcript of audio.
  - Delta string
    
    The partial transcript of the audio response.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseAudioTranscriptDelta
    
    The type of the event. Always response.audio.transcript.delta.
    - const ResponseAudioTranscriptDeltaResponseAudioTranscriptDelta ResponseAudioTranscriptDelta = "response.audio.transcript.delta"
- type ResponseAudioTranscriptDoneEvent struct{…}
  
  Emitted when the full audio transcript is completed.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseAudioTranscriptDone
    
    The type of the event. Always response.audio.transcript.done.
    - const ResponseAudioTranscriptDoneResponseAudioTranscriptDone ResponseAudioTranscriptDone = "response.audio.transcript.done"
- type ResponseCodeInterpreterCallCodeDeltaEvent struct{…}
  
  Emitted when a partial code snippet is streamed by the code interpreter.
  - Delta string
    
    The partial code snippet being streamed by the code interpreter.
  - ItemID string
    
    The unique identifier of the code interpreter tool call item.
  - OutputIndex int64
    
    The index of the output item in the response for which the code is being streamed.
  - SequenceNumber int64
    
    The sequence number of this event, used to order streaming events.
  - Type ResponseCodeInterpreterCallCodeDelta
    
    The type of the event. Always response.code_interpreter_call_code.delta.
    - const ResponseCodeInterpreterCallCodeDeltaResponseCodeInterpreterCallCodeDelta ResponseCodeInterpreterCallCodeDelta = "response.code_interpreter_call_code.delta"
- type ResponseCodeInterpreterCallCodeDoneEvent struct{…}
  
  Emitted when the code snippet is finalized by the code interpreter.
  - Code string
    
    The final code snippet output by the code interpreter.
  - ItemID string
    
    The unique identifier of the code interpreter tool call item.
  - OutputIndex int64
    
    The index of the output item in the response for which the code is finalized.
  - SequenceNumber int64
    
    The sequence number of this event, used to order streaming events.
  - Type ResponseCodeInterpreterCallCodeDone
    
    The type of the event. Always response.code_interpreter_call_code.done.
    - const ResponseCodeInterpreterCallCodeDoneResponseCodeInterpreterCallCodeDone ResponseCodeInterpreterCallCodeDone = "response.code_interpreter_call_code.done"
- type ResponseCodeInterpreterCallCompletedEvent struct{…}
  
  Emitted when the code interpreter call is completed.
  - ItemID string
    
    The unique identifier of the code interpreter tool call item.
  - OutputIndex int64
    
    The index of the output item in the response for which the code interpreter call is completed.
  - SequenceNumber int64
    
    The sequence number of this event, used to order streaming events.
  - Type ResponseCodeInterpreterCallCompleted
    
    The type of the event. Always response.code_interpreter_call.completed.
    - const ResponseCodeInterpreterCallCompletedResponseCodeInterpreterCallCompleted ResponseCodeInterpreterCallCompleted = "response.code_interpreter_call.completed"
- type ResponseCodeInterpreterCallInProgressEvent struct{…}
  
  Emitted when a code interpreter call is in progress.
  - ItemID string
    
    The unique identifier of the code interpreter tool call item.
  - OutputIndex int64
    
    The index of the output item in the response for which the code interpreter call is in progress.
  - SequenceNumber int64
    
    The sequence number of this event, used to order streaming events.
  - Type ResponseCodeInterpreterCallInProgress
    
    The type of the event. Always response.code_interpreter_call.in_progress.
    - const ResponseCodeInterpreterCallInProgressResponseCodeInterpreterCallInProgress ResponseCodeInterpreterCallInProgress = "response.code_interpreter_call.in_progress"
- type ResponseCodeInterpreterCallInterpretingEvent struct{…}
  
  Emitted when the code interpreter is actively interpreting the code snippet.
  - ItemID string
    
    The unique identifier of the code interpreter tool call item.
  - OutputIndex int64
    
    The index of the output item in the response for which the code interpreter is interpreting code.
  - SequenceNumber int64
    
    The sequence number of this event, used to order streaming events.
  - Type ResponseCodeInterpreterCallInterpreting
    
    The type of the event. Always response.code_interpreter_call.interpreting.
    - const ResponseCodeInterpreterCallInterpretingResponseCodeInterpreterCallInterpreting ResponseCodeInterpreterCallInterpreting = "response.code_interpreter_call.interpreting"
- type ResponseCompletedEvent struct{…}
  
  Emitted when the model response is complete.
  - Response Response
    
    Properties of the completed response.
    - ID string
      
      Unique identifier for this Response.
    - CreatedAt float64
      
      Unix timestamp (in seconds) of when this Response was created.
    - Error ResponseError
      
      An error object returned when the model fails to generate a Response.
      - Code ResponseErrorCode
        
        The error code for the response.
        
        const ResponseErrorCodeServerError ResponseErrorCode = "server_error"
        
        const ResponseErrorCodeRateLimitExceeded ResponseErrorCode = "rate_limit_exceeded"
        
        const ResponseErrorCodeInvalidPrompt ResponseErrorCode = "invalid_prompt"
        
        const ResponseErrorCodeVectorStoreTimeout ResponseErrorCode = "vector_store_timeout"
        
        const ResponseErrorCodeInvalidImage ResponseErrorCode = "invalid_image"
        
        const ResponseErrorCodeInvalidImageFormat ResponseErrorCode = "invalid_image_format"
        
        const ResponseErrorCodeInvalidBase64Image ResponseErrorCode = "invalid_base64_image"
        
        const ResponseErrorCodeInvalidImageURL ResponseErrorCode = "invalid_image_url"
        
        const ResponseErrorCodeImageTooLarge ResponseErrorCode = "image_too_large"
        
        const ResponseErrorCodeImageTooSmall ResponseErrorCode = "image_too_small"
        
        const ResponseErrorCodeImageParseError ResponseErrorCode = "image_parse_error"
        
        const ResponseErrorCodeImageContentPolicyViolation ResponseErrorCode = "image_content_policy_violation"
        
        const ResponseErrorCodeInvalidImageMode ResponseErrorCode = "invalid_image_mode"
        
        const ResponseErrorCodeImageFileTooLarge ResponseErrorCode = "image_file_too_large"
        
        const ResponseErrorCodeUnsupportedImageMediaType ResponseErrorCode = "unsupported_image_media_type"
        
        const ResponseErrorCodeEmptyImageFile ResponseErrorCode = "empty_image_file"
        
        const ResponseErrorCodeFailedToDownloadImage ResponseErrorCode = "failed_to_download_image"
        
        const ResponseErrorCodeImageFileNotFound ResponseErrorCode = "image_file_not_found"
      - Message string
        
        A human-readable description of the error.
    - IncompleteDetails ResponseIncompleteDetails
      
      Details about why the response is incomplete.
      - Reason string
        
        The reason why the response is incomplete.
        
        const ResponseIncompleteDetailsReasonMaxOutputTokens ResponseIncompleteDetailsReason = "max_output_tokens"
        
        const ResponseIncompleteDetailsReasonContentFilter ResponseIncompleteDetailsReason = "content_filter"
    - Instructions ResponseInstructionsUnion
      
      A system (or developer) message inserted into the model's context.
      
      When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
      - string
      - type ResponseInstructionsInputItemList []ResponseInputItemUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type EasyInputMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
        
        Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
        
        Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
        
        Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
        
        type ResponseInputItemMessage struct{…}
        
        A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
        
        Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
        
        Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
        
        Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
        
        Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
        
        type ResponseOutputMessage struct{…}
        
        An output message from the model.
        
        ID string
        
        The unique ID of the output message.
        
        Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
        
        Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
        
        Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
        
        Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
        
        Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
        
        type ResponseFileSearchToolCall struct{…}
        
        The results of a file search tool call. See the file search guide for more information.
        
        ID string
        
        The unique ID of the file search tool call.
        
        Queries []string
        
        The queries used to search for files.
        
        Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
        
        Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
        
        Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
        
        type ResponseComputerToolCall struct{…}
        
        A tool call to a computer use tool. See the computer use guide for more information.
        
        ID string
        
        The unique ID of the computer call.
        
        CallID string
        
        An identifier used when responding to the tool call with output.
        
        PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
        
        Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
        
        Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
        
        Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
        
        type ResponseInputItemComputerCallOutput struct{…}
        
        The output of a computer tool call.
        
        CallID string
        
        The ID of the computer tool call that produced the output.
        
        Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
        
        Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
        
        ID string
        
        The ID of the computer tool call output.
        
        AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
        
        type ResponseFunctionWebSearch struct{…}
        
        The results of a web search tool call. See the web search guide for more information.
        
        ID string
        
        The unique ID of the web search tool call.
        
        Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
        
        Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
        
        Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
        
        type ResponseFunctionToolCall struct{…}
        
        A tool call to run a function. See the function calling guide for more information.
        
        Arguments string
        
        A JSON string of the arguments to pass to the function.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Name string
        
        The name of the function to run.
        
        Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
        
        ID string
        
        The unique ID of the function tool call.
        
        Namespace string
        
        The namespace of the function to run.
        
        Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
        
        type ResponseInputItemFunctionCallOutput struct{…}
        
        The output of a function tool call.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
        
        Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
        
        ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
        
        type ResponseInputItemToolSearchCall struct{…}
        
        Arguments any
        
        The arguments supplied to the tool search call.
        
        Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
        
        ID string
        
        The unique ID of this tool search call.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
        
        Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
        
        type ResponseToolSearchOutputItemParamResp struct{…}
        
        Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
        
        Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
        
        ID string
        
        The unique ID of this tool search output.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
        
        Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
        
        type ResponseInputItemAdditionalTools struct{…}
        
        Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
        
        Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
        
        ID string
        
        The unique ID of this additional tools item.
        
        type ResponseReasoningItem struct{…}
        
        A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
        
        ID string
        
        The unique identifier of the reasoning content.
        
        Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
        
        Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
        
        Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
        
        EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
        
        Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
        
        type ResponseCompactionItemParamResp struct{…}
        
        A compaction item generated by the v1/responses/compact API.
        
        EncryptedContent string
        
        The encrypted content of the compaction summary.
        
        Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
        
        ID string
        
        The ID of the compaction item.
        
        type ResponseInputItemImageGenerationCall struct{…}
        
        An image generation request made by the model.
        
        ID string
        
        The unique ID of the image generation call.
        
        Result string
        
        The generated image encoded in base64.
        
        Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
        
        Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
        
        type ResponseCodeInterpreterToolCall struct{…}
        
        A tool call to run code.
        
        ID string
        
        The unique ID of the code interpreter tool call.
        
        Code string
        
        The code to run, or null if not available.
        
        ContainerID string
        
        The ID of the container used to run the code.
        
        Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
        
        Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
        
        Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
        
        type ResponseInputItemLocalShellCall struct{…}
        
        A tool call to run a command on the local shell.
        
        ID string
        
        The unique ID of the local shell call.
        
        Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
        
        CallID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
        
        Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
        
        type ResponseInputItemLocalShellCallOutput struct{…}
        
        The output of a local shell tool call.
        
        ID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Output string
        
        A JSON string of the output of the local shell tool call.
        
        Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
        
        type ResponseInputItemShellCall struct{…}
        
        A tool representing a request to execute one or more shell commands.
        
        Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
        
        ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
        
        Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
        
        Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
        
        type ResponseInputItemShellCallOutput struct{…}
        
        The streamed output items emitted by a shell tool call.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
        
        Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
        
        ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
        
        MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
        
        Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
        
        type ResponseInputItemApplyPatchCall struct{…}
        
        A tool call representing a request to create, delete, or update files using diff patches.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
        
        Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
        
        Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
        
        ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
        
        type ResponseInputItemApplyPatchCallOutput struct{…}
        
        The streamed output emitted by an apply patch tool call.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
        
        Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
        
        ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
        
        Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
        
        type ResponseInputItemMcpListTools struct{…}
        
        A list of tools available on an MCP server.
        
        ID string
        
        The unique ID of the list.
        
        ServerLabel string
        
        The label of the MCP server.
        
        Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
        
        Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
        
        Error string
        
        Error message if the server could not list tools.
        
        type ResponseInputItemMcpApprovalRequest struct{…}
        
        A request for human approval of a tool invocation.
        
        ID string
        
        The unique ID of the approval request.
        
        Arguments string
        
        A JSON string of arguments for the tool.
        
        Name string
        
        The name of the tool to run.
        
        ServerLabel string
        
        The label of the MCP server making the request.
        
        Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
        
        type ResponseInputItemMcpApprovalResponse struct{…}
        
        A response to an MCP approval request.
        
        ApprovalRequestID string
        
        The ID of the approval request being answered.
        
        Approve bool
        
        Whether the request was approved.
        
        Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
        
        ID string
        
        The unique ID of the approval response
        
        Reason string
        
        Optional reason for the decision.
        
        type ResponseInputItemMcpCall struct{…}
        
        An invocation of a tool on an MCP server.
        
        ID string
        
        The unique ID of the tool call.
        
        Arguments string
        
        A JSON string of the arguments passed to the tool.
        
        Name string
        
        The name of the tool that was run.
        
        ServerLabel string
        
        The label of the MCP server running the tool.
        
        Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
        
        ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
        
        Error string
        
        The error from the tool call, if any.
        
        Output string
        
        The output from the tool call.
        
        Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
        
        type ResponseCustomToolCallOutput struct{…}
        
        The output of a custom tool call from your code, being sent back to the model.
        
        CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
        
        Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
        
        ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
        
        type ResponseCustomToolCall struct{…}
        
        A call to a custom tool created by the model.
        
        CallID string
        
        An identifier used to map this custom tool call to a tool call output.
        
        Input string
        
        The input for the custom tool call generated by the model.
        
        Name string
        
        The name of the custom tool being called.
        
        Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
        
        ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
        
        Namespace string
        
        The namespace of the custom tool being called.
        
        type ResponseInputItemCompactionTrigger struct{…}
        
        Compacts the current context. Must be the final input item.
        
        Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
        
        type ResponseInputItemItemReference struct{…}
        
        An internal identifier for an item to reference.
        
        ID string
        
        The ID of the item to reference.
        
        Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
    - Metadata Metadata
      
      Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
      
      Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
    - Model ResponsesModel
      
      Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
      - string
      - type ChatModel string
        
        const ChatModelGPT5_4 ChatModel = "gpt-5.4"
        
        const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"
        
        const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"
        
        const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"
        
        const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"
        
        const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"
        
        const ChatModelGPT5_2 ChatModel = "gpt-5.2"
        
        const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"
        
        const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"
        
        const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"
        
        const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"
        
        const ChatModelGPT5_1 ChatModel = "gpt-5.1"
        
        const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"
        
        const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"
        
        const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"
        
        const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"
        
        const ChatModelGPT5 ChatModel = "gpt-5"
        
        const ChatModelGPT5Mini ChatModel = "gpt-5-mini"
        
        const ChatModelGPT5Nano ChatModel = "gpt-5-nano"
        
        const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"
        
        const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"
        
        const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"
        
        const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"
        
        const ChatModelGPT4_1 ChatModel = "gpt-4.1"
        
        const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"
        
        const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"
        
        const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"
        
        const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"
        
        const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"
        
        const ChatModelO4Mini ChatModel = "o4-mini"
        
        const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"
        
        const ChatModelO3 ChatModel = "o3"
        
        const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"
        
        const ChatModelO3Mini ChatModel = "o3-mini"
        
        const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"
        
        const ChatModelO1 ChatModel = "o1"
        
        const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"
        
        const ChatModelO1Preview ChatModel = "o1-preview"
        
        const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"
        
        const ChatModelO1Mini ChatModel = "o1-mini"
        
        const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"
        
        const ChatModelGPT4o ChatModel = "gpt-4o"
        
        const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"
        
        const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"
        
        const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"
        
        const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"
        
        const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"
        
        const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"
        
        const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"
        
        const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"
        
        const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"
        
        const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"
        
        const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"
        
        const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"
        
        const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"
        
        const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"
        
        const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"
        
        const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"
        
        const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"
        
        const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"
        
        const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"
        
        const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"
        
        const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"
        
        const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"
        
        const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"
        
        const ChatModelGPT4 ChatModel = "gpt-4"
        
        const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"
        
        const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"
        
        const ChatModelGPT4_32k ChatModel = "gpt-4-32k"
        
        const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"
        
        const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"
        
        const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"
        
        const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"
        
        const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"
        
        const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"
        
        const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"
        
        const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"
        
        const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"
      - type ResponsesModel string
        
        const ResponsesModelO1Pro ResponsesModel = "o1-pro"
        
        const ResponsesModelO1Pro2025_03_19 ResponsesModel = "o1-pro-2025-03-19"
        
        const ResponsesModelO3Pro ResponsesModel = "o3-pro"
        
        const ResponsesModelO3Pro2025_06_10 ResponsesModel = "o3-pro-2025-06-10"
        
        const ResponsesModelO3DeepResearch ResponsesModel = "o3-deep-research"
        
        const ResponsesModelO3DeepResearch2025_06_26 ResponsesModel = "o3-deep-research-2025-06-26"
        
        const ResponsesModelO4MiniDeepResearch ResponsesModel = "o4-mini-deep-research"
        
        const ResponsesModelO4MiniDeepResearch2025_06_26 ResponsesModel = "o4-mini-deep-research-2025-06-26"
        
        const ResponsesModelComputerUsePreview ResponsesModel = "computer-use-preview"
        
        const ResponsesModelComputerUsePreview2025_03_11 ResponsesModel = "computer-use-preview-2025-03-11"
        
        const ResponsesModelGPT5Codex ResponsesModel = "gpt-5-codex"
        
        const ResponsesModelGPT5Pro ResponsesModel = "gpt-5-pro"
        
        const ResponsesModelGPT5Pro2025_10_06 ResponsesModel = "gpt-5-pro-2025-10-06"
        
        const ResponsesModelGPT5_1CodexMax ResponsesModel = "gpt-5.1-codex-max"
    - Object Response
      
      The object type of this resource - always set to response.
      - const ResponseResponse Response = "response"
    - Output []ResponseOutputItemUnion
      
      An array of content items generated by the model.
      - The length and order of items in the output array is dependent on the model's response.
      - Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.
      - type ResponseOutputMessage struct{…}
        
        An output message from the model.
      - type ResponseFileSearchToolCall struct{…}
        
        The results of a file search tool call. See the file search guide for more information.
      - type ResponseFunctionToolCall struct{…}
        
        A tool call to run a function. See the function calling guide for more information.
      - type ResponseFunctionToolCallOutputItem struct{…}
        
        ID string
        
        The unique ID of the function call tool output.
        
        CallID string
        
        The unique ID of the function tool call generated by the model.
        
        Output ResponseFunctionToolCallOutputItemOutputUnion
        
        The output from the function call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Status ResponseFunctionToolCallOutputItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
        
        const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
        
        const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
        
        Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - type ResponseFunctionWebSearch struct{…}
        
        The results of a web search tool call. See the web search guide for more information.
      - type ResponseComputerToolCall struct{…}
        
        A tool call to a computer use tool. See the computer use guide for more information.
      - type ResponseComputerToolCallOutputItem struct{…}
        
        ID string
        
        The unique ID of the computer call tool output.
        
        CallID string
        
        The ID of the computer tool call that produced the output.
        
        Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Status ResponseComputerToolCallOutputItemStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
        
        const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
        
        const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
        
        const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
        
        Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
        
        AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - type ResponseReasoningItem struct{…}
        
        A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
      - type ResponseToolSearchCall struct{…}
        
        ID string
        
        The unique ID of the tool search call item.
        
        Arguments any
        
        Arguments used for the tool search call.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution ResponseToolSearchCallExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
        
        const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
        
        Status ResponseToolSearchCallStatus
        
        The status of the tool search call item that was recorded.
        
        const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
        
        const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
        
        const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
        
        Type ToolSearchCall
        
        The type of the item. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - type ResponseToolSearchOutputItem struct{…}
        
        ID string
        
        The unique ID of the tool search output item.
        
        CallID string
        
        The unique ID of the tool search call generated by the model.
        
        Execution ResponseToolSearchOutputItemExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
        
        const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
        
        Status ResponseToolSearchOutputItemStatus
        
        The status of the tool search output item that was recorded.
        
        const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
        
        const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
        
        const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
        
        Tools []ToolUnion
        
        The loaded tool definitions returned by tool search.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ToolSearchOutput
        
        The type of the item. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - type ResponseOutputItemAdditionalTools struct{…}
        
        ID string
        
        The unique ID of the additional tools item.
        
        Role string
        
        The role that provided the additional tools.
        
        const ResponseOutputItemAdditionalToolsRoleUnknown ResponseOutputItemAdditionalToolsRole = "unknown"
        
        const ResponseOutputItemAdditionalToolsRoleUser ResponseOutputItemAdditionalToolsRole = "user"
        
        const ResponseOutputItemAdditionalToolsRoleAssistant ResponseOutputItemAdditionalToolsRole = "assistant"
        
        const ResponseOutputItemAdditionalToolsRoleSystem ResponseOutputItemAdditionalToolsRole = "system"
        
        const ResponseOutputItemAdditionalToolsRoleCritic ResponseOutputItemAdditionalToolsRole = "critic"
        
        const ResponseOutputItemAdditionalToolsRoleDiscriminator ResponseOutputItemAdditionalToolsRole = "discriminator"
        
        const ResponseOutputItemAdditionalToolsRoleDeveloper ResponseOutputItemAdditionalToolsRole = "developer"
        
        const ResponseOutputItemAdditionalToolsRoleTool ResponseOutputItemAdditionalToolsRole = "tool"
        
        Tools []ToolUnion
        
        The additional tool definitions made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type AdditionalTools
        
        The type of the item. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
      - type ResponseCompactionItem struct{…}
        
        A compaction item generated by the v1/responses/compact API.
        
        ID string
        
        The unique ID of the compaction item.
        
        EncryptedContent string
        
        The encrypted content that was produced by compaction.
        
        Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - type ResponseOutputItemImageGenerationCall struct{…}
        
        An image generation request made by the model.
        
        ID string
        
        The unique ID of the image generation call.
        
        Result string
        
        The generated image encoded in base64.
        
        Status string
        
        The status of the image generation call.
        
        const ResponseOutputItemImageGenerationCallStatusInProgress ResponseOutputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseOutputItemImageGenerationCallStatusCompleted ResponseOutputItemImageGenerationCallStatus = "completed"
        
        const ResponseOutputItemImageGenerationCallStatusGenerating ResponseOutputItemImageGenerationCallStatus = "generating"
        
        const ResponseOutputItemImageGenerationCallStatusFailed ResponseOutputItemImageGenerationCallStatus = "failed"
        
        Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
      - type ResponseCodeInterpreterToolCall struct{…}
        
        A tool call to run code.
      - type ResponseOutputItemLocalShellCall struct{…}
        
        A tool call to run a command on the local shell.
        
        ID string
        
        The unique ID of the local shell call.
        
        Action ResponseOutputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
        
        CallID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Status string
        
        The status of the local shell call.
        
        const ResponseOutputItemLocalShellCallStatusInProgress ResponseOutputItemLocalShellCallStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallStatusCompleted ResponseOutputItemLocalShellCallStatus = "completed"
        
        const ResponseOutputItemLocalShellCallStatusIncomplete ResponseOutputItemLocalShellCallStatus = "incomplete"
        
        Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
      - type ResponseOutputItemLocalShellCallOutput struct{…}
        
        The output of a local shell tool call.
        
        ID string
        
        The unique ID of the local shell tool call generated by the model.
        
        Output string
        
        A JSON string of the output of the local shell tool call.
        
        Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseOutputItemLocalShellCallOutputStatusInProgress ResponseOutputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseOutputItemLocalShellCallOutputStatusCompleted ResponseOutputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseOutputItemLocalShellCallOutputStatusIncomplete ResponseOutputItemLocalShellCallOutputStatus = "incomplete"
      - type ResponseFunctionShellToolCall struct{…}
        
        A tool call that executes one or more shell commands in a managed environment.
        
        ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
        
        Action ResponseFunctionShellToolCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        Environment ResponseFunctionShellToolCallEnvironmentUnion
        
        Represents the use of a local environment to perform shell actions.
        
        type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
        
        type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        Status ResponseFunctionShellToolCallStatus
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
        
        const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
        
        const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
        
        Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
        
        CreatedBy string
        
        The ID of the entity that created this tool call.
      - type ResponseFunctionShellToolCallOutput struct{…}
        
        The output of a shell tool call that was emitted.
        
        ID string
        
        The unique ID of the shell call output. Populated when this item is returned via API.
        
        CallID string
        
        The unique ID of the shell tool call generated by the model.
        
        MaxOutputLength int64
        
        The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
        
        Output []ResponseFunctionShellToolCallOutputOutput
        
        An array of shell call output contents
        
        Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        The standard error output that was captured.
        
        Stdout string
        
        The standard output that was captured.
        
        CreatedBy string
        
        The identifier of the actor that created the item.
        
        Status ResponseFunctionShellToolCallOutputStatus
        
        The status of the shell call output. One of in_progress, completed, or incomplete.
        
        const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
        
        const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
        
        const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
        
        Type ShellCallOutput
        
        The type of the shell call output. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
        
        CreatedBy string
        
        The identifier of the actor that created the item.
      - type ResponseApplyPatchToolCall struct{…}
        
        A tool call that applies file diffs by creating, deleting, or updating files.
        
        ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Operation ResponseApplyPatchToolCallOperationUnion
        
        One of the create_file, delete_file, or update_file operations applied via apply_patch.
        
        type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
        
        Status ResponseApplyPatchToolCallStatus
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
        
        const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
        
        Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
        
        CreatedBy string
        
        The ID of the entity that created this tool call.
      - type ResponseApplyPatchToolCallOutput struct{…}
        
        The output emitted by an apply patch tool call.
        
        ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
        
        CallID string
        
        The unique ID of the apply patch tool call generated by the model.
        
        Status ResponseApplyPatchToolCallOutputStatus
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
        
        const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
        
        Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
        
        CreatedBy string
        
        The ID of the entity that created this tool call output.
        
        Output string
        
        Optional textual output returned by the apply patch tool.
      - type ResponseOutputItemMcpCall struct{…}
        
        An invocation of a tool on an MCP server.
        
        ID string
        
        The unique ID of the tool call.
        
        Arguments string
        
        A JSON string of the arguments passed to the tool.
        
        Name string
        
        The name of the tool that was run.
        
        ServerLabel string
        
        The label of the MCP server running the tool.
        
        Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
        
        ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
        
        Error string
        
        The error from the tool call, if any.
        
        Output string
        
        The output from the tool call.
        
        Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseOutputItemMcpCallStatusInProgress ResponseOutputItemMcpCallStatus = "in_progress"
        
        const ResponseOutputItemMcpCallStatusCompleted ResponseOutputItemMcpCallStatus = "completed"
        
        const ResponseOutputItemMcpCallStatusIncomplete ResponseOutputItemMcpCallStatus = "incomplete"
        
        const ResponseOutputItemMcpCallStatusCalling ResponseOutputItemMcpCallStatus = "calling"
        
        const ResponseOutputItemMcpCallStatusFailed ResponseOutputItemMcpCallStatus = "failed"
      - type ResponseOutputItemMcpListTools struct{…}
        
        A list of tools available on an MCP server.
        
        ID string
        
        The unique ID of the list.
        
        ServerLabel string
        
        The label of the MCP server.
        
        Tools []ResponseOutputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
        
        Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
        
        Error string
        
        Error message if the server could not list tools.
      - type ResponseOutputItemMcpApprovalRequest struct{…}
        
        A request for human approval of a tool invocation.
        
        ID string
        
        The unique ID of the approval request.
        
        Arguments string
        
        A JSON string of arguments for the tool.
        
        Name string
        
        The name of the tool to run.
        
        ServerLabel string
        
        The label of the MCP server making the request.
        
        Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
      - type ResponseOutputItemMcpApprovalResponse struct{…}
        
        A response to an MCP approval request.
        
        ID string
        
        The unique ID of the approval response
        
        ApprovalRequestID string
        
        The ID of the approval request being answered.
        
        Approve bool
        
        Whether the request was approved.
        
        Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
        
        Reason string
        
        Optional reason for the decision.
      - type ResponseCustomToolCall struct{…}
        
        A call to a custom tool created by the model.
      - type ResponseCustomToolCallOutputItem struct{…}
        
        The output of a custom tool call from your code, being sent back to the model.
        
        ID string
        
        The unique ID of the custom tool call output item.
        
        Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
        
        const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
        
        const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
        
        CreatedBy string
        
        The identifier of the actor that created the item.
    - ParallelToolCalls bool
      
      Whether to allow the model to run tool calls in parallel.
    - Temperature float64
      
      What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
    - ToolChoice ResponseToolChoiceUnion
      
      How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.
      - type ToolChoiceOptions string
        
        Controls which (if any) tool is called by the model.
        
        none means the model will not call any tool and instead generates a message.
        
        auto means the model can pick between generating a message or calling one or more tools.
        
        required means the model must call one or more tools.
        
        const ToolChoiceOptionsNone ToolChoiceOptions = "none"
        
        const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
        
        const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
      - type ToolChoiceAllowed struct{…}
        
        Constrains the tools available to the model to a pre-defined set.
        
        Mode ToolChoiceAllowedMode
        
        Constrains the tools available to the model to a pre-defined set.
        
        auto allows the model to pick from among the allowed tools and generate a message.
        
        required requires the model to call one or more of the allowed tools.
        
        const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
        
        const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
        
        Tools []map[string, any]
        
        A list of tool definitions that the model should be allowed to call.
        
        For the Responses API, the list of tool definitions might look like:
        
        [ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ]
        
        Type AllowedTools
        
        Allowed tool configuration type. Always allowed_tools.
        
        const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
      - type ToolChoiceTypes struct{…}
        
        Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
        
        Type ToolChoiceTypesType
        
        The type of hosted tool the model should to use. Learn more about built-in tools.
        
        Allowed values are:
        
        file_search
        
        web_search_preview
        
        computer
        
        computer_use_preview
        
        computer_use
        
        code_interpreter
        
        image_generation
        
        const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
        
        const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
        
        const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
        
        const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
        
        const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
        
        const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
        
        const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
        
        const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
      - type ToolChoiceFunction struct{…}
        
        Use this option to force the model to call a specific function.
        
        Name string
        
        The name of the function to call.
        
        Type Function
        
        For function calling, the type is always function.
        
        const FunctionFunction Function = "function"
      - type ToolChoiceMcp struct{…}
        
        Use this option to force the model to call a specific tool on a remote MCP server.
        
        ServerLabel string
        
        The label of the MCP server to use.
        
        Type Mcp
        
        For MCP tools, the type is always mcp.
        
        const McpMcp Mcp = "mcp"
        
        Name string
        
        The name of the tool to call on the server.
      - type ToolChoiceCustom struct{…}
        
        Use this option to force the model to call a specific custom tool.
        
        Name string
        
        The name of the custom tool to call.
        
        Type Custom
        
        For custom tool calling, the type is always custom.
        
        const CustomCustom Custom = "custom"
      - type ToolChoiceApplyPatch struct{…}
        
        Forces the model to call the apply_patch tool when executing a tool call.
        
        Type ApplyPatch
        
        The tool to call. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
      - type ToolChoiceShell struct{…}
        
        Forces the model to call the shell tool when a tool call is required.
        
        Type Shell
        
        The tool to call. Always shell.
        
        const ShellShell Shell = "shell"
    - Tools []ToolUnion
      
      An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
      
      We support the following categories of tools:
      - Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
      - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
      - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - TopP float64
      
      An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
      
      We generally recommend altering this or temperature but not both.
    - Background bool
      
      Whether to run the model response in the background. Learn more.
    - CompletedAt float64
      
      Unix timestamp (in seconds) of when this Response was completed. Only present when the status is completed.
    - Conversation ResponseConversation
      
      The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
      - ID string
        
        The unique ID of the conversation that this response was associated with.
    - MaxOutputTokens int64
      
      An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
    - MaxToolCalls int64
      
      The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
    - Moderation ResponseModeration
      
      Moderation results for the response input and output, if moderated completions were requested.
      - Input ResponseModerationInputUnion
        
        Moderation for the response input.
        
        type ResponseModerationInputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeText ResponseModerationInputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationInputModerationResultCategoryAppliedInputTypeImage ResponseModerationInputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
        
        type ResponseModerationInputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
      - Output ResponseModerationOutputUnion
        
        Moderation for the response output.
        
        type ResponseModerationOutputModerationResult struct{…}
        
        A moderation result produced for the response input or output.
        
        Categories map[string, bool]
        
        A dictionary of moderation categories to booleans, True if the input is flagged under this category.
        
        CategoryAppliedInputTypes map[string, []string]
        
        Which modalities of input are reflected by the score for each category.
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeText ResponseModerationOutputModerationResultCategoryAppliedInputType = "text"
        
        const ResponseModerationOutputModerationResultCategoryAppliedInputTypeImage ResponseModerationOutputModerationResultCategoryAppliedInputType = "image"
        
        CategoryScores map[string, float64]
        
        A dictionary of moderation categories to scores.
        
        Flagged bool
        
        A boolean indicating whether the content was flagged by any category.
        
        Model string
        
        The moderation model that produced this result.
        
        Type ModerationResult
        
        The object type, which was always moderation_result for successful moderation results.
        
        const ModerationResultModerationResult ModerationResult = "moderation_result"
        
        type ResponseModerationOutputError struct{…}
        
        An error produced while attempting moderation for the response input or output.
        
        Code string
        
        The error code.
        
        Message string
        
        The error message.
        
        Type Error
        
        The object type, which was always error for moderation failures.
        
        const ErrorError Error = "error"
    - PreviousResponseID string
      
      The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
    - Prompt ResponsePrompt
      
      Reference to a prompt template and its variables. Learn more.
      - ID string
        
        The unique identifier of the prompt template to use.
      - Variables map[string, ResponsePromptVariableUnion]
        
        Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
        
        string
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Version string
        
        Optional version of the prompt template.
    - PromptCacheKey string
      
      Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
    - PromptCacheRetention ResponsePromptCacheRetention
      
      The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.
      
      For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:
      - Organizations without ZDR enabled default to 24h.
      - Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.
      - const ResponsePromptCacheRetentionInMemory ResponsePromptCacheRetention = "in_memory"
      - const ResponsePromptCacheRetention24h ResponsePromptCacheRetention = "24h"
    - Reasoning Reasoning
      
      gpt-5 and o-series models only
      
      Configuration options for reasoning models.
      - Context ReasoningContext
        
        Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
        
        const ReasoningContextAuto ReasoningContext = "auto"
        
        const ReasoningContextCurrentTurn ReasoningContext = "current_turn"
        
        const ReasoningContextAllTurns ReasoningContext = "all_turns"
      - Effort ReasoningEffort
        
        Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
        
        gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
        
        All models before gpt-5.1 default to medium reasoning effort, and do not support none.
        
        The gpt-5-pro model defaults to (and only supports) high reasoning effort.
        
        xhigh is supported for all models after gpt-5.1-codex-max.
        
        const ReasoningEffortNone ReasoningEffort = "none"
        
        const ReasoningEffortMinimal ReasoningEffort = "minimal"
        
        const ReasoningEffortLow ReasoningEffort = "low"
        
        const ReasoningEffortMedium ReasoningEffort = "medium"
        
        const ReasoningEffortHigh ReasoningEffort = "high"
        
        const ReasoningEffortXhigh ReasoningEffort = "xhigh"
      - GenerateSummary ReasoningGenerateSummary
        
        Deprecated: use summary instead.
        
        A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
        
        const ReasoningGenerateSummaryAuto ReasoningGenerateSummary = "auto"
        
        const ReasoningGenerateSummaryConcise ReasoningGenerateSummary = "concise"
        
        const ReasoningGenerateSummaryDetailed ReasoningGenerateSummary = "detailed"
      - Summary ReasoningSummary
        
        A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.
        
        concise is supported for computer-use-preview models and all reasoning models after gpt-5.
        
        const ReasoningSummaryAuto ReasoningSummary = "auto"
        
        const ReasoningSummaryConcise ReasoningSummary = "concise"
        
        const ReasoningSummaryDetailed ReasoningSummary = "detailed"
    - SafetyIdentifier string
      
      A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
    - ServiceTier ResponseServiceTier
      
      Specifies the processing type used for serving the request.
      - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
      - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
      - If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
      - When not set, the default behavior is 'auto'.
      When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
      - const ResponseServiceTierAuto ResponseServiceTier = "auto"
      - const ResponseServiceTierDefault ResponseServiceTier = "default"
      - const ResponseServiceTierFlex ResponseServiceTier = "flex"
      - const ResponseServiceTierScale ResponseServiceTier = "scale"
      - const ResponseServiceTierPriority ResponseServiceTier = "priority"
    - Status ResponseStatus
      
      The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
      - const ResponseStatusCompleted ResponseStatus = "completed"
      - const ResponseStatusFailed ResponseStatus = "failed"
      - const ResponseStatusInProgress ResponseStatus = "in_progress"
      - const ResponseStatusCancelled ResponseStatus = "cancelled"
      - const ResponseStatusQueued ResponseStatus = "queued"
      - const ResponseStatusIncomplete ResponseStatus = "incomplete"
    - Text ResponseTextConfig
      
      Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
      - Text inputs and outputs
      - Structured Outputs
      - Format ResponseFormatTextConfigUnion
        
        An object specifying the format that the model must output.
        
        Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
        
        The default format is { "type": "text" } with no additional options.
        
        Not recommended for gpt-4o and newer models:
        
        Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
        
        type ResponseFormatText struct{…}
        
        Default response format. Used to generate text responses.
        
        Type Text
        
        The type of response format being defined. Always text.
        
        const TextText Text = "text"
        
        type ResponseFormatTextJSONSchemaConfig struct{…}
        
        JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
        
        Name string
        
        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
        
        Schema map[string, any]
        
        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
        
        Type JSONSchema
        
        The type of response format being defined. Always json_schema.
        
        const JSONSchemaJSONSchema JSONSchema = "json_schema"
        
        Description string
        
        A description of what the response format is for, used by the model to determine how to respond in the format.
        
        Strict bool
        
        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
        
        type ResponseFormatJSONObject struct{…}
        
        JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
        
        Type JSONObject
        
        The type of response format being defined. Always json_object.
        
        const JSONObjectJSONObject JSONObject = "json_object"
      - Verbosity ResponseTextConfigVerbosity
        
        Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
        
        const ResponseTextConfigVerbosityLow ResponseTextConfigVerbosity = "low"
        
        const ResponseTextConfigVerbosityMedium ResponseTextConfigVerbosity = "medium"
        
        const ResponseTextConfigVerbosityHigh ResponseTextConfigVerbosity = "high"
    - TopLogprobs int64
      
      An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
    - Truncation ResponseTruncation
      
      The truncation strategy to use for the model response.
      - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
      - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
      - const ResponseTruncationAuto ResponseTruncation = "auto"
      - const ResponseTruncationDisabled ResponseTruncation = "disabled"
    - Usage ResponseUsage
      
      Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
      - InputTokens int64
        
        The number of input tokens.
      - InputTokensDetails ResponseUsageInputTokensDetails
        
        A detailed breakdown of the input tokens.
        
        CachedTokens int64
        
        The number of tokens that were retrieved from the cache. More on prompt caching.
      - OutputTokens int64
        
        The number of output tokens.
      - OutputTokensDetails ResponseUsageOutputTokensDetails
        
        A detailed breakdown of the output tokens.
        
        ReasoningTokens int64
        
        The number of reasoning tokens.
      - TotalTokens int64
        
        The total number of tokens used.
    - User string
      
      This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
  - SequenceNumber int64
    
    The sequence number for this event.
  - Type ResponseCompleted
    
    The type of the event. Always response.completed.
    - const ResponseCompletedResponseCompleted ResponseCompleted = "response.completed"
- type ResponseContentPartAddedEvent struct{…}
  
  Emitted when a new content part is added.
  - ContentIndex int64
    
    The index of the content part that was added.
  - ItemID string
    
    The ID of the output item that the content part was added to.
  - OutputIndex int64
    
    The index of the output item that the content part was added to.
  - Part ResponseContentPartAddedEventPartUnion
    
    The content part that was added.
    - type ResponseOutputText struct{…}
      
      A text output from the model.
    - type ResponseOutputRefusal struct{…}
      
      A refusal from the model.
    - type ResponseContentPartAddedEventPartReasoningText struct{…}
      
      Reasoning text from the model.
      - Text string
        
        The reasoning text from the model.
      - Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseContentPartAdded
    
    The type of the event. Always response.content_part.added.
    - const ResponseContentPartAddedResponseContentPartAdded ResponseContentPartAdded = "response.content_part.added"
- type ResponseContentPartDoneEvent struct{…}
  
  Emitted when a content part is done.
  - ContentIndex int64
    
    The index of the content part that is done.
  - ItemID string
    
    The ID of the output item that the content part was added to.
  - OutputIndex int64
    
    The index of the output item that the content part was added to.
  - Part ResponseContentPartDoneEventPartUnion
    
    The content part that is done.
    - type ResponseOutputText struct{…}
      
      A text output from the model.
    - type ResponseOutputRefusal struct{…}
      
      A refusal from the model.
    - type ResponseContentPartDoneEventPartReasoningText struct{…}
      
      Reasoning text from the model.
      - Text string
        
        The reasoning text from the model.
      - Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseContentPartDone
    
    The type of the event. Always response.content_part.done.
    - const ResponseContentPartDoneResponseContentPartDone ResponseContentPartDone = "response.content_part.done"
- type ResponseCreatedEvent struct{…}
  
  An event that is emitted when a response is created.
  - Response Response
    
    The response that was created.
  - SequenceNumber int64
    
    The sequence number for this event.
  - Type ResponseCreated
    
    The type of the event. Always response.created.
    - const ResponseCreatedResponseCreated ResponseCreated = "response.created"
- type ResponseErrorEvent struct{…}
  
  Emitted when an error occurs.
  - Code string
    
    The error code.
  - Message string
    
    The error message.
  - Param string
    
    The error parameter.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type Error
    
    The type of the event. Always error.
    - const ErrorError Error = "error"
- type ResponseFileSearchCallCompletedEvent struct{…}
  
  Emitted when a file search call is completed (results found).
  - ItemID string
    
    The ID of the output item that the file search call is initiated.
  - OutputIndex int64
    
    The index of the output item that the file search call is initiated.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseFileSearchCallCompleted
    
    The type of the event. Always response.file_search_call.completed.
    - const ResponseFileSearchCallCompletedResponseFileSearchCallCompleted ResponseFileSearchCallCompleted = "response.file_search_call.completed"
- type ResponseFileSearchCallInProgressEvent struct{…}
  
  Emitted when a file search call is initiated.
  - ItemID string
    
    The ID of the output item that the file search call is initiated.
  - OutputIndex int64
    
    The index of the output item that the file search call is initiated.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseFileSearchCallInProgress
    
    The type of the event. Always response.file_search_call.in_progress.
    - const ResponseFileSearchCallInProgressResponseFileSearchCallInProgress ResponseFileSearchCallInProgress = "response.file_search_call.in_progress"
- type ResponseFileSearchCallSearchingEvent struct{…}
  
  Emitted when a file search is currently searching.
  - ItemID string
    
    The ID of the output item that the file search call is initiated.
  - OutputIndex int64
    
    The index of the output item that the file search call is searching.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseFileSearchCallSearching
    
    The type of the event. Always response.file_search_call.searching.
    - const ResponseFileSearchCallSearchingResponseFileSearchCallSearching ResponseFileSearchCallSearching = "response.file_search_call.searching"
- type ResponseFunctionCallArgumentsDeltaEvent struct{…}
  
  Emitted when there is a partial function-call arguments delta.
  - Delta string
    
    The function-call arguments delta that is added.
  - ItemID string
    
    The ID of the output item that the function-call arguments delta is added to.
  - OutputIndex int64
    
    The index of the output item that the function-call arguments delta is added to.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseFunctionCallArgumentsDelta
    
    The type of the event. Always response.function_call_arguments.delta.
    - const ResponseFunctionCallArgumentsDeltaResponseFunctionCallArgumentsDelta ResponseFunctionCallArgumentsDelta = "response.function_call_arguments.delta"
- type ResponseFunctionCallArgumentsDoneEvent struct{…}
  
  Emitted when function-call arguments are finalized.
  - Arguments string
    
    The function-call arguments.
  - ItemID string
    
    The ID of the item.
  - Name string
    
    The name of the function that was called.
  - OutputIndex int64
    
    The index of the output item.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseFunctionCallArgumentsDone
    - const ResponseFunctionCallArgumentsDoneResponseFunctionCallArgumentsDone ResponseFunctionCallArgumentsDone = "response.function_call_arguments.done"
- type ResponseInProgressEvent struct{…}
  
  Emitted when the response is in progress.
  - Response Response
    
    The response that is in progress.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseInProgress
    
    The type of the event. Always response.in_progress.
    - const ResponseInProgressResponseInProgress ResponseInProgress = "response.in_progress"
- type ResponseFailedEvent struct{…}
  
  An event that is emitted when a response fails.
  - Response Response
    
    The response that failed.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseFailed
    
    The type of the event. Always response.failed.
    - const ResponseFailedResponseFailed ResponseFailed = "response.failed"
- type ResponseIncompleteEvent struct{…}
  
  An event that is emitted when a response finishes as incomplete.
  - Response Response
    
    The response that was incomplete.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseIncomplete
    
    The type of the event. Always response.incomplete.
    - const ResponseIncompleteResponseIncomplete ResponseIncomplete = "response.incomplete"
- type ResponseOutputItemAddedEvent struct{…}
  
  Emitted when a new output item is added.
  - Item ResponseOutputItemUnion
    
    The output item that was added.
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
    - type ResponseFunctionToolCallOutputItem struct{…}
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
    - type ResponseComputerToolCallOutputItem struct{…}
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
    - type ResponseToolSearchCall struct{…}
    - type ResponseToolSearchOutputItem struct{…}
    - type ResponseOutputItemAdditionalTools struct{…}
    - type ResponseCompactionItem struct{…}
      
      A compaction item generated by the v1/responses/compact API.
    - type ResponseOutputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
    - type ResponseOutputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
    - type ResponseOutputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
    - type ResponseFunctionShellToolCall struct{…}
      
      A tool call that executes one or more shell commands in a managed environment.
    - type ResponseFunctionShellToolCallOutput struct{…}
      
      The output of a shell tool call that was emitted.
    - type ResponseApplyPatchToolCall struct{…}
      
      A tool call that applies file diffs by creating, deleting, or updating files.
    - type ResponseApplyPatchToolCallOutput struct{…}
      
      The output emitted by an apply patch tool call.
    - type ResponseOutputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
    - type ResponseOutputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
    - type ResponseOutputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
    - type ResponseOutputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
    - type ResponseCustomToolCallOutputItem struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
  - OutputIndex int64
    
    The index of the output item that was added.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseOutputItemAdded
    
    The type of the event. Always response.output_item.added.
    - const ResponseOutputItemAddedResponseOutputItemAdded ResponseOutputItemAdded = "response.output_item.added"
- type ResponseOutputItemDoneEvent struct{…}
  
  Emitted when an output item is marked done.
  - Item ResponseOutputItemUnion
    
    The output item that was marked done.
  - OutputIndex int64
    
    The index of the output item that was marked done.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseOutputItemDone
    
    The type of the event. Always response.output_item.done.
    - const ResponseOutputItemDoneResponseOutputItemDone ResponseOutputItemDone = "response.output_item.done"
- type ResponseReasoningSummaryPartAddedEvent struct{…}
  
  Emitted when a new reasoning summary part is added.
  - ItemID string
    
    The ID of the item this summary part is associated with.
  - OutputIndex int64
    
    The index of the output item this summary part is associated with.
  - Part ResponseReasoningSummaryPartAddedEventPart
    
    The summary part that was added.
    - Text string
      
      The text of the summary part.
    - Type SummaryText
      
      The type of the summary part. Always summary_text.
      - const SummaryTextSummaryText SummaryText = "summary_text"
  - SequenceNumber int64
    
    The sequence number of this event.
  - SummaryIndex int64
    
    The index of the summary part within the reasoning summary.
  - Type ResponseReasoningSummaryPartAdded
    
    The type of the event. Always response.reasoning_summary_part.added.
    - const ResponseReasoningSummaryPartAddedResponseReasoningSummaryPartAdded ResponseReasoningSummaryPartAdded = "response.reasoning_summary_part.added"
- type ResponseReasoningSummaryPartDoneEvent struct{…}
  
  Emitted when a reasoning summary part is completed.
  - ItemID string
    
    The ID of the item this summary part is associated with.
  - OutputIndex int64
    
    The index of the output item this summary part is associated with.
  - Part ResponseReasoningSummaryPartDoneEventPart
    
    The completed summary part.
    - Text string
      
      The text of the summary part.
    - Type SummaryText
      
      The type of the summary part. Always summary_text.
      - const SummaryTextSummaryText SummaryText = "summary_text"
  - SequenceNumber int64
    
    The sequence number of this event.
  - SummaryIndex int64
    
    The index of the summary part within the reasoning summary.
  - Type ResponseReasoningSummaryPartDone
    
    The type of the event. Always response.reasoning_summary_part.done.
    - const ResponseReasoningSummaryPartDoneResponseReasoningSummaryPartDone ResponseReasoningSummaryPartDone = "response.reasoning_summary_part.done"
- type ResponseReasoningSummaryTextDeltaEvent struct{…}
  
  Emitted when a delta is added to a reasoning summary text.
  - Delta string
    
    The text delta that was added to the summary.
  - ItemID string
    
    The ID of the item this summary text delta is associated with.
  - OutputIndex int64
    
    The index of the output item this summary text delta is associated with.
  - SequenceNumber int64
    
    The sequence number of this event.
  - SummaryIndex int64
    
    The index of the summary part within the reasoning summary.
  - Type ResponseReasoningSummaryTextDelta
    
    The type of the event. Always response.reasoning_summary_text.delta.
    - const ResponseReasoningSummaryTextDeltaResponseReasoningSummaryTextDelta ResponseReasoningSummaryTextDelta = "response.reasoning_summary_text.delta"
- type ResponseReasoningSummaryTextDoneEvent struct{…}
  
  Emitted when a reasoning summary text is completed.
  - ItemID string
    
    The ID of the item this summary text is associated with.
  - OutputIndex int64
    
    The index of the output item this summary text is associated with.
  - SequenceNumber int64
    
    The sequence number of this event.
  - SummaryIndex int64
    
    The index of the summary part within the reasoning summary.
  - Text string
    
    The full text of the completed reasoning summary.
  - Type ResponseReasoningSummaryTextDone
    
    The type of the event. Always response.reasoning_summary_text.done.
    - const ResponseReasoningSummaryTextDoneResponseReasoningSummaryTextDone ResponseReasoningSummaryTextDone = "response.reasoning_summary_text.done"
- type ResponseReasoningTextDeltaEvent struct{…}
  
  Emitted when a delta is added to a reasoning text.
  - ContentIndex int64
    
    The index of the reasoning content part this delta is associated with.
  - Delta string
    
    The text delta that was added to the reasoning content.
  - ItemID string
    
    The ID of the item this reasoning text delta is associated with.
  - OutputIndex int64
    
    The index of the output item this reasoning text delta is associated with.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseReasoningTextDelta
    
    The type of the event. Always response.reasoning_text.delta.
    - const ResponseReasoningTextDeltaResponseReasoningTextDelta ResponseReasoningTextDelta = "response.reasoning_text.delta"
- type ResponseReasoningTextDoneEvent struct{…}
  
  Emitted when a reasoning text is completed.
  - ContentIndex int64
    
    The index of the reasoning content part.
  - ItemID string
    
    The ID of the item this reasoning text is associated with.
  - OutputIndex int64
    
    The index of the output item this reasoning text is associated with.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Text string
    
    The full text of the completed reasoning content.
  - Type ResponseReasoningTextDone
    
    The type of the event. Always response.reasoning_text.done.
    - const ResponseReasoningTextDoneResponseReasoningTextDone ResponseReasoningTextDone = "response.reasoning_text.done"
- type ResponseRefusalDeltaEvent struct{…}
  
  Emitted when there is a partial refusal text.
  - ContentIndex int64
    
    The index of the content part that the refusal text is added to.
  - Delta string
    
    The refusal text that is added.
  - ItemID string
    
    The ID of the output item that the refusal text is added to.
  - OutputIndex int64
    
    The index of the output item that the refusal text is added to.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseRefusalDelta
    
    The type of the event. Always response.refusal.delta.
    - const ResponseRefusalDeltaResponseRefusalDelta ResponseRefusalDelta = "response.refusal.delta"
- type ResponseRefusalDoneEvent struct{…}
  
  Emitted when refusal text is finalized.
  - ContentIndex int64
    
    The index of the content part that the refusal text is finalized.
  - ItemID string
    
    The ID of the output item that the refusal text is finalized.
  - OutputIndex int64
    
    The index of the output item that the refusal text is finalized.
  - Refusal string
    
    The refusal text that is finalized.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseRefusalDone
    
    The type of the event. Always response.refusal.done.
    - const ResponseRefusalDoneResponseRefusalDone ResponseRefusalDone = "response.refusal.done"
- type ResponseTextDeltaEvent struct{…}
  
  Emitted when there is an additional text delta.
  - ContentIndex int64
    
    The index of the content part that the text delta was added to.
  - Delta string
    
    The text delta that was added.
  - ItemID string
    
    The ID of the output item that the text delta was added to.
  - Logprobs []ResponseTextDeltaEventLogprob
    
    The log probabilities of the tokens in the delta.
    - Token string
      
      A possible text token.
    - Logprob float64
      
      The log probability of this token.
    - TopLogprobs []ResponseTextDeltaEventLogprobTopLogprob
      
      The log probabilities of up to 20 of the most likely tokens.
      - Token string
        
        A possible text token.
      - Logprob float64
        
        The log probability of this token.
  - OutputIndex int64
    
    The index of the output item that the text delta was added to.
  - SequenceNumber int64
    
    The sequence number for this event.
  - Type ResponseOutputTextDelta
    
    The type of the event. Always response.output_text.delta.
    - const ResponseOutputTextDeltaResponseOutputTextDelta ResponseOutputTextDelta = "response.output_text.delta"
- type ResponseTextDoneEvent struct{…}
  
  Emitted when text content is finalized.
  - ContentIndex int64
    
    The index of the content part that the text content is finalized.
  - ItemID string
    
    The ID of the output item that the text content is finalized.
  - Logprobs []ResponseTextDoneEventLogprob
    
    The log probabilities of the tokens in the delta.
    - Token string
      
      A possible text token.
    - Logprob float64
      
      The log probability of this token.
    - TopLogprobs []ResponseTextDoneEventLogprobTopLogprob
      
      The log probabilities of up to 20 of the most likely tokens.
      - Token string
        
        A possible text token.
      - Logprob float64
        
        The log probability of this token.
  - OutputIndex int64
    
    The index of the output item that the text content is finalized.
  - SequenceNumber int64
    
    The sequence number for this event.
  - Text string
    
    The text content that is finalized.
  - Type ResponseOutputTextDone
    
    The type of the event. Always response.output_text.done.
    - const ResponseOutputTextDoneResponseOutputTextDone ResponseOutputTextDone = "response.output_text.done"
- type ResponseWebSearchCallCompletedEvent struct{…}
  
  Emitted when a web search call is completed.
  - ItemID string
    
    Unique ID for the output item associated with the web search call.
  - OutputIndex int64
    
    The index of the output item that the web search call is associated with.
  - SequenceNumber int64
    
    The sequence number of the web search call being processed.
  - Type ResponseWebSearchCallCompleted
    
    The type of the event. Always response.web_search_call.completed.
    - const ResponseWebSearchCallCompletedResponseWebSearchCallCompleted ResponseWebSearchCallCompleted = "response.web_search_call.completed"
- type ResponseWebSearchCallInProgressEvent struct{…}
  
  Emitted when a web search call is initiated.
  - ItemID string
    
    Unique ID for the output item associated with the web search call.
  - OutputIndex int64
    
    The index of the output item that the web search call is associated with.
  - SequenceNumber int64
    
    The sequence number of the web search call being processed.
  - Type ResponseWebSearchCallInProgress
    
    The type of the event. Always response.web_search_call.in_progress.
    - const ResponseWebSearchCallInProgressResponseWebSearchCallInProgress ResponseWebSearchCallInProgress = "response.web_search_call.in_progress"
- type ResponseWebSearchCallSearchingEvent struct{…}
  
  Emitted when a web search call is executing.
  - ItemID string
    
    Unique ID for the output item associated with the web search call.
  - OutputIndex int64
    
    The index of the output item that the web search call is associated with.
  - SequenceNumber int64
    
    The sequence number of the web search call being processed.
  - Type ResponseWebSearchCallSearching
    
    The type of the event. Always response.web_search_call.searching.
    - const ResponseWebSearchCallSearchingResponseWebSearchCallSearching ResponseWebSearchCallSearching = "response.web_search_call.searching"
- type ResponseImageGenCallCompletedEvent struct{…}
  
  Emitted when an image generation tool call has completed and the final image is available.
  - ItemID string
    
    The unique identifier of the image generation item being processed.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseImageGenerationCallCompleted
    
    The type of the event. Always 'response.image_generation_call.completed'.
    - const ResponseImageGenerationCallCompletedResponseImageGenerationCallCompleted ResponseImageGenerationCallCompleted = "response.image_generation_call.completed"
- type ResponseImageGenCallGeneratingEvent struct{…}
  
  Emitted when an image generation tool call is actively generating an image (intermediate state).
  - ItemID string
    
    The unique identifier of the image generation item being processed.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - SequenceNumber int64
    
    The sequence number of the image generation item being processed.
  - Type ResponseImageGenerationCallGenerating
    
    The type of the event. Always 'response.image_generation_call.generating'.
    - const ResponseImageGenerationCallGeneratingResponseImageGenerationCallGenerating ResponseImageGenerationCallGenerating = "response.image_generation_call.generating"
- type ResponseImageGenCallInProgressEvent struct{…}
  
  Emitted when an image generation tool call is in progress.
  - ItemID string
    
    The unique identifier of the image generation item being processed.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - SequenceNumber int64
    
    The sequence number of the image generation item being processed.
  - Type ResponseImageGenerationCallInProgress
    
    The type of the event. Always 'response.image_generation_call.in_progress'.
    - const ResponseImageGenerationCallInProgressResponseImageGenerationCallInProgress ResponseImageGenerationCallInProgress = "response.image_generation_call.in_progress"
- type ResponseImageGenCallPartialImageEvent struct{…}
  
  Emitted when a partial image is available during image generation streaming.
  - ItemID string
    
    The unique identifier of the image generation item being processed.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - PartialImageB64 string
    
    Base64-encoded partial image data, suitable for rendering as an image.
  - PartialImageIndex int64
    
    0-based index for the partial image (backend is 1-based, but this is 0-based for the user).
  - SequenceNumber int64
    
    The sequence number of the image generation item being processed.
  - Type ResponseImageGenerationCallPartialImage
    
    The type of the event. Always 'response.image_generation_call.partial_image'.
    - const ResponseImageGenerationCallPartialImageResponseImageGenerationCallPartialImage ResponseImageGenerationCallPartialImage = "response.image_generation_call.partial_image"
- type ResponseMcpCallArgumentsDeltaEvent struct{…}
  
  Emitted when there is a delta (partial update) to the arguments of an MCP tool call.
  - Delta string
    
    A JSON string containing the partial update to the arguments for the MCP tool call.
  - ItemID string
    
    The unique identifier of the MCP tool call item being processed.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpCallArgumentsDelta
    
    The type of the event. Always 'response.mcp_call_arguments.delta'.
    - const ResponseMcpCallArgumentsDeltaResponseMcpCallArgumentsDelta ResponseMcpCallArgumentsDelta = "response.mcp_call_arguments.delta"
- type ResponseMcpCallArgumentsDoneEvent struct{…}
  
  Emitted when the arguments for an MCP tool call are finalized.
  - Arguments string
    
    A JSON string containing the finalized arguments for the MCP tool call.
  - ItemID string
    
    The unique identifier of the MCP tool call item being processed.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpCallArgumentsDone
    
    The type of the event. Always 'response.mcp_call_arguments.done'.
    - const ResponseMcpCallArgumentsDoneResponseMcpCallArgumentsDone ResponseMcpCallArgumentsDone = "response.mcp_call_arguments.done"
- type ResponseMcpCallCompletedEvent struct{…}
  
  Emitted when an MCP tool call has completed successfully.
  - ItemID string
    
    The ID of the MCP tool call item that completed.
  - OutputIndex int64
    
    The index of the output item that completed.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpCallCompleted
    
    The type of the event. Always 'response.mcp_call.completed'.
    - const ResponseMcpCallCompletedResponseMcpCallCompleted ResponseMcpCallCompleted = "response.mcp_call.completed"
- type ResponseMcpCallFailedEvent struct{…}
  
  Emitted when an MCP tool call has failed.
  - ItemID string
    
    The ID of the MCP tool call item that failed.
  - OutputIndex int64
    
    The index of the output item that failed.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpCallFailed
    
    The type of the event. Always 'response.mcp_call.failed'.
    - const ResponseMcpCallFailedResponseMcpCallFailed ResponseMcpCallFailed = "response.mcp_call.failed"
- type ResponseMcpCallInProgressEvent struct{…}
  
  Emitted when an MCP tool call is in progress.
  - ItemID string
    
    The unique identifier of the MCP tool call item being processed.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpCallInProgress
    
    The type of the event. Always 'response.mcp_call.in_progress'.
    - const ResponseMcpCallInProgressResponseMcpCallInProgress ResponseMcpCallInProgress = "response.mcp_call.in_progress"
- type ResponseMcpListToolsCompletedEvent struct{…}
  
  Emitted when the list of available MCP tools has been successfully retrieved.
  - ItemID string
    
    The ID of the MCP tool call item that produced this output.
  - OutputIndex int64
    
    The index of the output item that was processed.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpListToolsCompleted
    
    The type of the event. Always 'response.mcp_list_tools.completed'.
    - const ResponseMcpListToolsCompletedResponseMcpListToolsCompleted ResponseMcpListToolsCompleted = "response.mcp_list_tools.completed"
- type ResponseMcpListToolsFailedEvent struct{…}
  
  Emitted when the attempt to list available MCP tools has failed.
  - ItemID string
    
    The ID of the MCP tool call item that failed.
  - OutputIndex int64
    
    The index of the output item that failed.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpListToolsFailed
    
    The type of the event. Always 'response.mcp_list_tools.failed'.
    - const ResponseMcpListToolsFailedResponseMcpListToolsFailed ResponseMcpListToolsFailed = "response.mcp_list_tools.failed"
- type ResponseMcpListToolsInProgressEvent struct{…}
  
  Emitted when the system is in the process of retrieving the list of available MCP tools.
  - ItemID string
    
    The ID of the MCP tool call item that is being processed.
  - OutputIndex int64
    
    The index of the output item that is being processed.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseMcpListToolsInProgress
    
    The type of the event. Always 'response.mcp_list_tools.in_progress'.
    - const ResponseMcpListToolsInProgressResponseMcpListToolsInProgress ResponseMcpListToolsInProgress = "response.mcp_list_tools.in_progress"
- type ResponseOutputTextAnnotationAddedEvent struct{…}
  
  Emitted when an annotation is added to output text content.
  - Annotation any
    
    The annotation object being added. (See annotation schema for details.)
  - AnnotationIndex int64
    
    The index of the annotation within the content part.
  - ContentIndex int64
    
    The index of the content part within the output item.
  - ItemID string
    
    The unique identifier of the item to which the annotation is being added.
  - OutputIndex int64
    
    The index of the output item in the response's output array.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseOutputTextAnnotationAdded
    
    The type of the event. Always 'response.output_text.annotation.added'.
    - const ResponseOutputTextAnnotationAddedResponseOutputTextAnnotationAdded ResponseOutputTextAnnotationAdded = "response.output_text.annotation.added"
- type ResponseQueuedEvent struct{…}
  
  Emitted when a response is queued and waiting to be processed.
  - Response Response
    
    The full response object that is queued.
  - SequenceNumber int64
    
    The sequence number for this event.
  - Type ResponseQueued
    
    The type of the event. Always 'response.queued'.
    - const ResponseQueuedResponseQueued ResponseQueued = "response.queued"
- type ResponseCustomToolCallInputDeltaEvent struct{…}
  
  Event representing a delta (partial update) to the input of a custom tool call.
  - Delta string
    
    The incremental input data (delta) for the custom tool call.
  - ItemID string
    
    Unique identifier for the API item associated with this event.
  - OutputIndex int64
    
    The index of the output this delta applies to.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseCustomToolCallInputDelta
    
    The event type identifier.
    - const ResponseCustomToolCallInputDeltaResponseCustomToolCallInputDelta ResponseCustomToolCallInputDelta = "response.custom_tool_call_input.delta"
- type ResponseCustomToolCallInputDoneEvent struct{…}
  
  Event indicating that input for a custom tool call is complete.
  - Input string
    
    The complete input data for the custom tool call.
  - ItemID string
    
    Unique identifier for the API item associated with this event.
  - OutputIndex int64
    
    The index of the output this event applies to.
  - SequenceNumber int64
    
    The sequence number of this event.
  - Type ResponseCustomToolCallInputDone
    
    The event type identifier.
    - const ResponseCustomToolCallInputDoneResponseCustomToolCallInputDone ResponseCustomToolCallInputDone = "response.custom_tool_call_input.done"

Skill Reference

type SkillReference struct{…}
- SkillID string
  
  The ID of the referenced skill.
- Type SkillReference
  
  References a skill created with the /v1/skills endpoint.
  - const SkillReferenceSkillReference SkillReference = "skill_reference"
- Version string
  
  Optional skill version. Use a positive integer or 'latest'. Omit for default.

Tool

type ToolUnion interface{…}

A tool that can be used to generate a response.
- type FunctionTool struct{…}
  
  Defines a function in your own code the model can choose to call. Learn more about function calling.
  - Name string
    
    The name of the function to call.
  - Parameters map[string, any]
    
    A JSON schema object describing the parameters of the function.
  - Strict bool
    
    Whether to enforce strict parameter validation. Default true.
  - Type Function
    
    The type of the function tool. Always function.
    - const FunctionFunction Function = "function"
  - DeferLoading bool
    
    Whether this function is deferred and loaded via tool search.
  - Description string
    
    A description of the function. Used by the model to determine whether or not to call the function.
- type FileSearchTool struct{…}
  
  A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
  - Type FileSearch
    
    The type of the file search tool. Always file_search.
    - const FileSearchFileSearch FileSearch = "file_search"
  - VectorStoreIDs []string
    
    The IDs of the vector stores to search.
  - Filters FileSearchToolFiltersUnion
    
    A filter to apply.
    - type ComparisonFilter struct{…}
      
      A filter used to compare a specified attribute key to a given value using a defined comparison operation.
      - Key string
        
        The key to compare against the value.
      - Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
      - Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
    - type CompoundFilter struct{…}
      
      Combine multiple filters using and or or.
      - Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
      - Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
  - MaxNumResults int64
    
    The maximum number of results to return. This number should be between 1 and 50 inclusive.
  - RankingOptions FileSearchToolRankingOptions
    
    Ranking options for search.
    - HybridSearch FileSearchToolRankingOptionsHybridSearch
      
      Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
      - EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
      - TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
    - Ranker string
      
      The ranker to use for the file search.
      - const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
      - const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
    - ScoreThreshold float64
      
      The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
- type ComputerTool struct{…}
  
  A tool that controls a virtual computer. Learn more about the computer tool.
  - Type Computer
    
    The type of the computer tool. Always computer.
    - const ComputerComputer Computer = "computer"
- type ComputerUsePreviewTool struct{…}
  
  A tool that controls a virtual computer. Learn more about the computer tool.
  - DisplayHeight int64
    
    The height of the computer display.
  - DisplayWidth int64
    
    The width of the computer display.
  - Environment ComputerUsePreviewToolEnvironment
    
    The type of computer environment to control.
    - const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
    - const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
    - const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
    - const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
    - const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
  - Type ComputerUsePreview
    
    The type of the computer use tool. Always computer_use_preview.
    - const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
- type WebSearchTool struct{…}
  
  Search the Internet for sources related to the prompt. Learn more about the web search tool.
  - Type WebSearchToolType
    
    The type of the web search tool. One of web_search or web_search_2025_08_26.
    - const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
    - const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
  - Filters WebSearchToolFilters
    
    Filters for the search.
    - AllowedDomains []string
      
      Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
      
      Example: ["pubmed.ncbi.nlm.nih.gov"]
  - SearchContextSize WebSearchToolSearchContextSize
    
    High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
    - const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
    - const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
    - const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
  - UserLocation WebSearchToolUserLocation
    
    The approximate location of the user.
    - City string
      
      Free text input for the city of the user, e.g. San Francisco.
    - Country string
      
      The two-letter ISO country code of the user, e.g. US.
    - Region string
      
      Free text input for the region of the user, e.g. California.
    - Timezone string
      
      The IANA timezone of the user, e.g. America/Los_Angeles.
    - Type string
      
      The type of location approximation. Always approximate.
      - const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
- type ToolMcp struct{…}
  
  Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
  - ServerLabel string
    
    A label for this MCP server, used to identify it in tool calls.
  - Type Mcp
    
    The type of the MCP tool. Always mcp.
    - const McpMcp Mcp = "mcp"
  - AllowedTools ToolMcpAllowedToolsUnion
    
    List of allowed tool names or a filter object.
    - type ToolMcpAllowedToolsMcpAllowedTools []string
      
      A string array of allowed tool names
    - type ToolMcpAllowedToolsMcpToolFilter struct{…}
      
      A filter object to specify which tools are allowed.
      - ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
      - ToolNames []string
        
        List of allowed tool names.
  - Authorization string
    
    An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
  - ConnectorID string
    
    Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
    
    Currently supported connector_id values are:
    - Dropbox: connector_dropbox
    - Gmail: connector_gmail
    - Google Calendar: connector_googlecalendar
    - Google Drive: connector_googledrive
    - Microsoft Teams: connector_microsoftteams
    - Outlook Calendar: connector_outlookcalendar
    - Outlook Email: connector_outlookemail
    - SharePoint: connector_sharepoint
    - const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
    - const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
    - const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
    - const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
    - const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
    - const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
    - const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
    - const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
  - DeferLoading bool
    
    Whether this MCP tool is deferred and discovered via tool search.
  - Headers map[string, string]
    
    Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
  - RequireApproval ToolMcpRequireApprovalUnion
    
    Specify which of the MCP server's tools require approval.
    - type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
      
      Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
      - Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
      - Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
    - type ToolMcpRequireApprovalMcpToolApprovalSetting string
      
      Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
      - const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
      - const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
  - ServerDescription string
    
    Optional description of the MCP server, used to provide more context.
  - ServerURL string
    
    The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
  - TunnelID string
    
    The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
- type ToolCodeInterpreter struct{…}
  
  A tool that runs Python code to help generate a response to a prompt.
  - Container ToolCodeInterpreterContainerUnion
    
    The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
    - string
    - type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
      
      Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
      - Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
      - FileIDs []string
        
        An optional list of uploaded files to make available to your code.
      - MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
      - NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
  - Type CodeInterpreter
    
    The type of the code interpreter tool. Always code_interpreter.
    - const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
- type ToolImageGeneration struct{…}
  
  A tool that generates images using the GPT image models.
  - Type ImageGeneration
    
    The type of the image generation tool. Always image_generation.
    - const ImageGenerationImageGeneration ImageGeneration = "image_generation"
  - Action string
    
    Whether to generate a new image or edit an existing image. Default: auto.
    - const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
    - const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
    - const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
  - Background string
    
    Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
    
    gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
    
    If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
    - const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
    - const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
    - const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
  - InputFidelity string
    
    Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
    - const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
    - const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
  - InputImageMask ToolImageGenerationInputImageMask
    
    Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
    - FileID string
      
      File ID for the mask image.
    - ImageURL string
      
      Base64-encoded mask image.
  - Model string
    
    The image generation model to use. Default: gpt-image-1.
    - string
    - string
      - const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
      - const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
      - const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
      - const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
      - const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
      - const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
  - Moderation string
    
    Moderation level for the generated image. Default: auto.
    - const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
    - const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
  - OutputCompression int64
    
    Compression level for the output image. Default: 100.
  - OutputFormat string
    
    The output format of the generated image. One of png, webp, or jpeg. Default: png.
    - const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
    - const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
    - const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
  - PartialImages int64
    
    Number of partial images to generate in streaming mode, from 0 (default value) to 3.
  - Quality string
    
    The quality of the generated image. One of low, medium, high, or auto. Default: auto.
    - const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
    - const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
    - const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
    - const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
  - Size string
    
    The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
    - string
    - string
      - const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
      - const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
      - const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
      - const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
- type ToolLocalShell struct{…}
  
  A tool that allows the model to execute shell commands in a local environment.
  - Type LocalShell
    
    The type of the local shell tool. Always local_shell.
    - const LocalShellLocalShell LocalShell = "local_shell"
- type FunctionShellTool struct{…}
  
  A tool that allows the model to execute shell commands.
  - Type Shell
    
    The type of the shell tool. Always shell.
    - const ShellShell Shell = "shell"
  - Environment FunctionShellToolEnvironmentUnion
    - type ContainerAuto struct{…}
      - Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
      - FileIDs []string
        
        An optional list of uploaded files to make available to your code.
      - MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
      - NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
      - Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
    - type LocalEnvironment struct{…}
      - Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
      - Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
    - type ContainerReference struct{…}
      - ContainerID string
        
        The ID of the referenced container.
      - Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
- type CustomTool struct{…}
  
  A custom tool that processes input using a specified format. Learn more about custom tools
  - Name string
    
    The name of the custom tool, used to identify it in tool calls.
  - Type Custom
    
    The type of the custom tool. Always custom.
    - const CustomCustom Custom = "custom"
  - DeferLoading bool
    
    Whether this tool should be deferred and discovered via tool search.
  - Description string
    
    Optional description of the custom tool, used to provide more context.
  - Format CustomToolInputFormatUnion
    
    The input format for the custom tool. Default is unconstrained text.
    - type CustomToolInputFormatText struct{…}
      
      Unconstrained free-form text.
      - Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
    - type CustomToolInputFormatGrammar struct{…}
      
      A grammar defined by the user.
      - Definition string
        
        The grammar definition.
      - Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
      - Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
- type NamespaceTool struct{…}
  
  Groups function/custom tools under a shared namespace.
  - Description string
    
    A description of the namespace shown to the model.
  - Name string
    
    The namespace name used in tool calls (for example, crm).
  - Tools []NamespaceToolToolUnion
    
    The function/custom tools available inside this namespace.
    - type NamespaceToolToolFunction struct{…}
      - Name string
      - Type Function
        
        const FunctionFunction Function = "function"
      - DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
      - Description string
      - Parameters any
      - Strict bool
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
  - Type Namespace
    
    The type of the tool. Always namespace.
    - const NamespaceNamespace Namespace = "namespace"
- type ToolSearchTool struct{…}
  
  Hosted or BYOT tool search configuration for deferred tools.
  - Type ToolSearch
    
    The type of the tool. Always tool_search.
    - const ToolSearchToolSearch ToolSearch = "tool_search"
  - Description string
    
    Description shown to the model for a client-executed tool search tool.
  - Execution ToolSearchToolExecution
    
    Whether tool search is executed by the server or by the client.
    - const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
    - const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
  - Parameters any
    
    Parameter schema for a client-executed tool search tool.
- type WebSearchPreviewTool struct{…}
  
  This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
  - Type WebSearchPreviewToolType
    
    The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
    - const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
    - const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
  - SearchContentTypes []string
    - const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
    - const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
  - SearchContextSize WebSearchPreviewToolSearchContextSize
    
    High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
    - const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
    - const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
    - const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
  - UserLocation WebSearchPreviewToolUserLocation
    
    The user's location.
    - Type Approximate
      
      The type of location approximation. Always approximate.
      - const ApproximateApproximate Approximate = "approximate"
    - City string
      
      Free text input for the city of the user, e.g. San Francisco.
    - Country string
      
      The two-letter ISO country code of the user, e.g. US.
    - Region string
      
      Free text input for the region of the user, e.g. California.
    - Timezone string
      
      The IANA timezone of the user, e.g. America/Los_Angeles.
- type ApplyPatchTool struct{…}
  
  Allows the assistant to create, delete, or update files using unified diffs.
  - Type ApplyPatch
    
    The type of the tool. Always apply_patch.
    - const ApplyPatchApplyPatch ApplyPatch = "apply_patch"

Tool Choice Allowed

type ToolChoiceAllowed struct{…}

Constrains the tools available to the model to a pre-defined set.
- Mode ToolChoiceAllowedMode
  
  Constrains the tools available to the model to a pre-defined set.
  
  auto allows the model to pick from among the allowed tools and generate a message.
  
  required requires the model to call one or more of the allowed tools.
  - const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
  - const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
- Tools []map[string, any]
  
  A list of tool definitions that the model should be allowed to call.
  
  For the Responses API, the list of tool definitions might look like:
```
[
  { "type": "function", "name": "get_weather" },
  { "type": "mcp", "server_label": "deepwiki" },
  { "type": "image_generation" }
]
```
- Type AllowedTools
  
  Allowed tool configuration type. Always allowed_tools.
  - const AllowedToolsAllowedTools AllowedTools = "allowed_tools"

Tool Choice Apply Patch

type ToolChoiceApplyPatch struct{…}

Forces the model to call the apply_patch tool when executing a tool call.
- Type ApplyPatch
  
  The tool to call. Always apply_patch.
  - const ApplyPatchApplyPatch ApplyPatch = "apply_patch"

Tool Choice Custom

type ToolChoiceCustom struct{…}

Use this option to force the model to call a specific custom tool.
- Name string
  
  The name of the custom tool to call.
- Type Custom
  
  For custom tool calling, the type is always custom.
  - const CustomCustom Custom = "custom"

Tool Choice Function

type ToolChoiceFunction struct{…}

Use this option to force the model to call a specific function.
- Name string
  
  The name of the function to call.
- Type Function
  
  For function calling, the type is always function.
  - const FunctionFunction Function = "function"

Tool Choice Mcp

type ToolChoiceMcp struct{…}

Use this option to force the model to call a specific tool on a remote MCP server.
- ServerLabel string
  
  The label of the MCP server to use.
- Type Mcp
  
  For MCP tools, the type is always mcp.
  - const McpMcp Mcp = "mcp"
- Name string
  
  The name of the tool to call on the server.

Tool Choice Options

type ToolChoiceOptions string

Controls which (if any) tool is called by the model.

none means the model will not call any tool and instead generates a message.

auto means the model can pick between generating a message or calling one or more tools.

required means the model must call one or more tools.
- const ToolChoiceOptionsNone ToolChoiceOptions = "none"
- const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
- const ToolChoiceOptionsRequired ToolChoiceOptions = "required"

Tool Choice Shell

type ToolChoiceShell struct{…}

Forces the model to call the shell tool when a tool call is required.
- Type Shell
  
  The tool to call. Always shell.
  - const ShellShell Shell = "shell"

Tool Choice Types

type ToolChoiceTypes struct{…}

Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
- Type ToolChoiceTypesType
  
  The type of hosted tool the model should to use. Learn more about built-in tools.
  
  Allowed values are:
  - file_search
  - web_search_preview
  - computer
  - computer_use_preview
  - computer_use
  - code_interpreter
  - image_generation
  - const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
  - const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
  - const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
  - const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
  - const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
  - const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
  - const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
  - const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"

Tool Search Tool

type ToolSearchTool struct{…}

Hosted or BYOT tool search configuration for deferred tools.
- Type ToolSearch
  
  The type of the tool. Always tool_search.
  - const ToolSearchToolSearch ToolSearch = "tool_search"
- Description string
  
  Description shown to the model for a client-executed tool search tool.
- Execution ToolSearchToolExecution
  
  Whether tool search is executed by the server or by the client.
  - const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
  - const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
- Parameters any
  
  Parameter schema for a client-executed tool search tool.

Web Search Preview Tool

type WebSearchPreviewTool struct{…}

This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
- Type WebSearchPreviewToolType
  
  The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
  - const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
  - const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
- SearchContentTypes []string
  - const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
  - const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
- SearchContextSize WebSearchPreviewToolSearchContextSize
  
  High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
  - const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
  - const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
  - const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
- UserLocation WebSearchPreviewToolUserLocation
  
  The user's location.
  - Type Approximate
    
    The type of location approximation. Always approximate.
    - const ApproximateApproximate Approximate = "approximate"
  - City string
    
    Free text input for the city of the user, e.g. San Francisco.
  - Country string
    
    The two-letter ISO country code of the user, e.g. US.
  - Region string
    
    Free text input for the region of the user, e.g. California.
  - Timezone string
    
    The IANA timezone of the user, e.g. America/Los_Angeles.

Web Search Tool

type WebSearchTool struct{…}

Search the Internet for sources related to the prompt. Learn more about the web search tool.
- Type WebSearchToolType
  
  The type of the web search tool. One of web_search or web_search_2025_08_26.
  - const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
  - const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
- Filters WebSearchToolFilters
  
  Filters for the search.
  - AllowedDomains []string
    
    Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
    
    Example: ["pubmed.ncbi.nlm.nih.gov"]
- SearchContextSize WebSearchToolSearchContextSize
  
  High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
  - const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
  - const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
  - const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
- UserLocation WebSearchToolUserLocation
  
  The approximate location of the user.
  - City string
    
    Free text input for the city of the user, e.g. San Francisco.
  - Country string
    
    The two-letter ISO country code of the user, e.g. US.
  - Region string
    
    Free text input for the region of the user, e.g. California.
  - Timezone string
    
    The IANA timezone of the user, e.g. America/Los_Angeles.
  - Type string
    
    The type of location approximation. Always approximate.
    - const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"

Input Items

List input items

client.Responses.InputItems.List(ctx, responseID, query) (*CursorPage[ResponseItemUnion], error)

get /responses/{response_id}/input_items

Returns a list of input items for a given response.

Parameters

responseID string
query InputItemListParams
- After param.Field[string]
  
  An item ID to list items after, used in pagination.
- Include param.Field[[]ResponseIncludable]
  
  Additional fields to include in the response. See the include parameter for Response creation above for more information.
  - const ResponseIncludableFileSearchCallResults ResponseIncludable = "file_search_call.results"
  - const ResponseIncludableWebSearchCallResults ResponseIncludable = "web_search_call.results"
  - const ResponseIncludableWebSearchCallActionSources ResponseIncludable = "web_search_call.action.sources"
  - const ResponseIncludableMessageInputImageImageURL ResponseIncludable = "message.input_image.image_url"
  - const ResponseIncludableComputerCallOutputOutputImageURL ResponseIncludable = "computer_call_output.output.image_url"
  - const ResponseIncludableCodeInterpreterCallOutputs ResponseIncludable = "code_interpreter_call.outputs"
  - const ResponseIncludableReasoningEncryptedContent ResponseIncludable = "reasoning.encrypted_content"
  - const ResponseIncludableMessageOutputTextLogprobs ResponseIncludable = "message.output_text.logprobs"
- Limit param.Field[int64]
  
  A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
- Order param.Field[InputItemListParamsOrder]
  
  The order to return the input items in. Default is desc.
  - asc: Return the input items in ascending order.
  - desc: Return the input items in descending order.
  - const InputItemListParamsOrderAsc InputItemListParamsOrder = "asc"
  - const InputItemListParamsOrderDesc InputItemListParamsOrder = "desc"

Returns

type ResponseItemUnion interface{…}

Content item used to generate a response.
- type ResponseInputMessageItem struct{…}
  - ID string
    
    The unique ID of the message input.
  - Content ResponseInputMessageContentList
    
    A list of one or many input items to the model, containing different content types.
    - type ResponseInputText struct{…}
      
      A text input to the model.
      - Text string
        
        The text input to the model.
      - Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
    - type ResponseInputImage struct{…}
      
      An image input to the model. Learn about image inputs.
      - Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
      - Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
      - FileID string
        
        The ID of the file to be sent to the model.
      - ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
    - type ResponseInputFile struct{…}
      
      A file input to the model.
      - Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
      - Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
      - FileData string
        
        The content of the file to be sent to the model.
      - FileID string
        
        The ID of the file to be sent to the model.
      - FileURL string
        
        The URL of the file to be sent to the model.
      - Filename string
        
        The name of the file to be sent to the model.
  - Role ResponseInputMessageItemRole
    
    The role of the message input. One of user, system, or developer.
    - const ResponseInputMessageItemRoleUser ResponseInputMessageItemRole = "user"
    - const ResponseInputMessageItemRoleSystem ResponseInputMessageItemRole = "system"
    - const ResponseInputMessageItemRoleDeveloper ResponseInputMessageItemRole = "developer"
  - Type Message
    
    The type of the message input. Always set to message.
    - const MessageMessage Message = "message"
  - Status ResponseInputMessageItemStatus
    
    The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseInputMessageItemStatusInProgress ResponseInputMessageItemStatus = "in_progress"
    - const ResponseInputMessageItemStatusCompleted ResponseInputMessageItemStatus = "completed"
    - const ResponseInputMessageItemStatusIncomplete ResponseInputMessageItemStatus = "incomplete"
- type ResponseOutputMessage struct{…}
  
  An output message from the model.
  - ID string
    
    The unique ID of the output message.
  - Content []ResponseOutputMessageContentUnion
    
    The content of the output message.
    - type ResponseOutputText struct{…}
      
      A text output from the model.
      - Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
      - Text string
        
        The text output from the model.
      - Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
      - Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
    - type ResponseOutputRefusal struct{…}
      
      A refusal from the model.
      - Refusal string
        
        The refusal explanation from the model.
      - Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
  - Role Assistant
    
    The role of the output message. Always assistant.
    - const AssistantAssistant Assistant = "assistant"
  - Status ResponseOutputMessageStatus
    
    The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
    - const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
    - const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
    - const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
  - Type Message
    
    The type of the output message. Always message.
    - const MessageMessage Message = "message"
  - Phase ResponseOutputMessagePhase
    
    Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
    - const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
    - const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
- type ResponseFileSearchToolCall struct{…}
  
  The results of a file search tool call. See the file search guide for more information.
  - ID string
    
    The unique ID of the file search tool call.
  - Queries []string
    
    The queries used to search for files.
  - Status ResponseFileSearchToolCallStatus
    
    The status of the file search tool call. One of in_progress, searching, incomplete or failed,
    - const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
    - const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
    - const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
    - const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
    - const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
  - Type FileSearchCall
    
    The type of the file search tool call. Always file_search_call.
    - const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
  - Results []ResponseFileSearchToolCallResult
    
    The results of the file search tool call.
    - Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
      
      Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
      - string
      - float64
      - bool
    - FileID string
      
      The unique ID of the file.
    - Filename string
      
      The name of the file.
    - Score float64
      
      The relevance score of the file - a value between 0 and 1.
    - Text string
      
      The text that was retrieved from the file.
- type ResponseComputerToolCall struct{…}
  
  A tool call to a computer use tool. See the computer use guide for more information.
  - ID string
    
    The unique ID of the computer call.
  - CallID string
    
    An identifier used when responding to the tool call with output.
  - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
    
    The pending safety checks for the computer call.
    - ID string
      
      The ID of the pending safety check.
    - Code string
      
      The type of the pending safety check.
    - Message string
      
      Details about the pending safety check.
  - Status ResponseComputerToolCallStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
    - const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
    - const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
  - Type ResponseComputerToolCallType
    
    The type of the computer call. Always computer_call.
    - const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
  - Action ResponseComputerToolCallActionUnion
    
    A click action.
    - type ResponseComputerToolCallActionClick struct{…}
      
      A click action.
      - Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
      - Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
      - X int64
        
        The x-coordinate where the click occurred.
      - Y int64
        
        The y-coordinate where the click occurred.
      - Keys []string
        
        The keys being held while clicking.
    - type ResponseComputerToolCallActionDoubleClick struct{…}
      
      A double click action.
      - Keys []string
        
        The keys being held while double-clicking.
      - Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
      - X int64
        
        The x-coordinate where the double click occurred.
      - Y int64
        
        The y-coordinate where the double click occurred.
    - type ResponseComputerToolCallActionDrag struct{…}
      
      A drag action.
      - Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
      - Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
      - Keys []string
        
        The keys being held while dragging the mouse.
    - type ResponseComputerToolCallActionKeypress struct{…}
      
      A collection of keypresses the model would like to perform.
      - Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
      - Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
    - type ResponseComputerToolCallActionMove struct{…}
      
      A mouse move action.
      - Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
      - X int64
        
        The x-coordinate to move to.
      - Y int64
        
        The y-coordinate to move to.
      - Keys []string
        
        The keys being held while moving the mouse.
    - type ResponseComputerToolCallActionScreenshot struct{…}
      
      A screenshot action.
      - Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
    - type ResponseComputerToolCallActionScroll struct{…}
      
      A scroll action.
      - ScrollX int64
        
        The horizontal scroll distance.
      - ScrollY int64
        
        The vertical scroll distance.
      - Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
      - X int64
        
        The x-coordinate where the scroll occurred.
      - Y int64
        
        The y-coordinate where the scroll occurred.
      - Keys []string
        
        The keys being held while scrolling.
    - type ResponseComputerToolCallActionType struct{…}
      
      An action to type in text.
      - Text string
        
        The text to type.
      - Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
    - type ResponseComputerToolCallActionWait struct{…}
      
      A wait action.
      - Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
  - Actions ComputerActionList
    
    Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
    - type ComputerActionClick struct{…}
      
      A click action.
      - Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
      - Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
      - X int64
        
        The x-coordinate where the click occurred.
      - Y int64
        
        The y-coordinate where the click occurred.
      - Keys []string
        
        The keys being held while clicking.
    - type ComputerActionDoubleClick struct{…}
      
      A double click action.
      - Keys []string
        
        The keys being held while double-clicking.
      - Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
      - X int64
        
        The x-coordinate where the double click occurred.
      - Y int64
        
        The y-coordinate where the double click occurred.
    - type ComputerActionDrag struct{…}
      
      A drag action.
      - Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
      - Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
      - Keys []string
        
        The keys being held while dragging the mouse.
    - type ComputerActionKeypress struct{…}
      
      A collection of keypresses the model would like to perform.
      - Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
      - Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
    - type ComputerActionMove struct{…}
      
      A mouse move action.
      - Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
      - X int64
        
        The x-coordinate to move to.
      - Y int64
        
        The y-coordinate to move to.
      - Keys []string
        
        The keys being held while moving the mouse.
    - type ComputerActionScreenshot struct{…}
      
      A screenshot action.
      - Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
    - type ComputerActionScroll struct{…}
      
      A scroll action.
      - ScrollX int64
        
        The horizontal scroll distance.
      - ScrollY int64
        
        The vertical scroll distance.
      - Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
      - X int64
        
        The x-coordinate where the scroll occurred.
      - Y int64
        
        The y-coordinate where the scroll occurred.
      - Keys []string
        
        The keys being held while scrolling.
    - type ComputerActionType struct{…}
      
      An action to type in text.
      - Text string
        
        The text to type.
      - Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
    - type ComputerActionWait struct{…}
      
      A wait action.
      - Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
- type ResponseComputerToolCallOutputItem struct{…}
  - ID string
    
    The unique ID of the computer call tool output.
  - CallID string
    
    The ID of the computer tool call that produced the output.
  - Output ResponseComputerToolCallOutputScreenshot
    
    A computer screenshot image used with the computer use tool.
    - Type ComputerScreenshot
      
      Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
      - const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
    - FileID string
      
      The identifier of an uploaded file that contains the screenshot.
    - ImageURL string
      
      The URL of the screenshot image.
  - Status ResponseComputerToolCallOutputItemStatus
    
    The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
    - const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
    - const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
    - const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
    - const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
  - Type ComputerCallOutput
    
    The type of the computer tool call output. Always computer_call_output.
    - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
  - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
    
    The safety checks reported by the API that have been acknowledged by the developer.
    - ID string
      
      The ID of the pending safety check.
    - Code string
      
      The type of the pending safety check.
    - Message string
      
      Details about the pending safety check.
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseFunctionWebSearch struct{…}
  
  The results of a web search tool call. See the web search guide for more information.
  - ID string
    
    The unique ID of the web search tool call.
  - Action ResponseFunctionWebSearchActionUnion
    
    An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
    - type ResponseFunctionWebSearchActionSearch struct{…}
      
      Action type "search" - Performs a web search query.
      - Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
      - Queries []string
        
        The search queries.
      - Query string
        
        The search query.
      - Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
    - type ResponseFunctionWebSearchActionOpenPage struct{…}
      
      Action type "open_page" - Opens a specific URL from search results.
      - Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
      - URL string
        
        The URL opened by the model.
    - type ResponseFunctionWebSearchActionFindInPage struct{…}
      
      Action type "find_in_page": Searches for a pattern within a loaded page.
      - Pattern string
        
        The pattern or text to search for within the page.
      - Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
      - URL string
        
        The URL of the page searched for the pattern.
  - Status ResponseFunctionWebSearchStatus
    
    The status of the web search tool call.
    - const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
    - const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
    - const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
    - const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
  - Type WebSearchCall
    
    The type of the web search tool call. Always web_search_call.
    - const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
- type ResponseFunctionToolCallItem struct{…}
  
  A tool call to run a function. See the function calling guide for more information.
  - ID string
    
    The unique ID of the function tool call.
  - Status string
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseFunctionToolCallItemStatusInProgress ResponseFunctionToolCallItemStatus = "in_progress"
    - const ResponseFunctionToolCallItemStatusCompleted ResponseFunctionToolCallItemStatus = "completed"
    - const ResponseFunctionToolCallItemStatusIncomplete ResponseFunctionToolCallItemStatus = "incomplete"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseFunctionToolCallOutputItem struct{…}
  - ID string
    
    The unique ID of the function call tool output.
  - CallID string
    
    The unique ID of the function tool call generated by the model.
  - Output ResponseFunctionToolCallOutputItemOutputUnion
    
    The output from the function call generated by your code. Can be a string or an list of output content.
    - string
    - type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
      
      Text, image, or file output of the function call.
      - type ResponseInputText struct{…}
        
        A text input to the model.
      - type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
      - type ResponseInputFile struct{…}
        
        A file input to the model.
  - Status ResponseFunctionToolCallOutputItemStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
    - const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
    - const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
  - Type FunctionCallOutput
    
    The type of the function tool call output. Always function_call_output.
    - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseToolSearchCall struct{…}
  - ID string
    
    The unique ID of the tool search call item.
  - Arguments any
    
    Arguments used for the tool search call.
  - CallID string
    
    The unique ID of the tool search call generated by the model.
  - Execution ResponseToolSearchCallExecution
    
    Whether tool search was executed by the server or by the client.
    - const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
    - const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
  - Status ResponseToolSearchCallStatus
    
    The status of the tool search call item that was recorded.
    - const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
    - const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
    - const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
  - Type ToolSearchCall
    
    The type of the item. Always tool_search_call.
    - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseToolSearchOutputItem struct{…}
  - ID string
    
    The unique ID of the tool search output item.
  - CallID string
    
    The unique ID of the tool search call generated by the model.
  - Execution ResponseToolSearchOutputItemExecution
    
    Whether tool search was executed by the server or by the client.
    - const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
    - const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
  - Status ResponseToolSearchOutputItemStatus
    
    The status of the tool search output item that was recorded.
    - const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
    - const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
    - const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
  - Tools []ToolUnion
    
    The loaded tool definitions returned by tool search.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
      - Name string
        
        The name of the function to call.
      - Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
      - Strict bool
        
        Whether to enforce strict parameter validation. Default true.
      - Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
      - DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
      - Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
      - VectorStoreIDs []string
        
        The IDs of the vector stores to search.
      - Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
      - MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
      - RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
      - Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
      - DisplayHeight int64
        
        The height of the computer display.
      - DisplayWidth int64
        
        The width of the computer display.
      - Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
      - Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
      - Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
      - SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
      - UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
      - Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
      - AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
      - Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
      - ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
      - DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
      - Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
      - RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
      - ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
      - ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
      - TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
      - Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
      - Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
      - Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
      - Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
      - Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
      - InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
      - InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
      - Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
      - Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
      - OutputCompression int64
        
        Compression level for the output image. Default: 100.
      - OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
      - PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
      - Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
      - Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
      - Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
      - Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
      - Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
      - Name string
        
        The name of the custom tool, used to identify it in tool calls.
      - Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
      - DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
      - Description string
        
        Optional description of the custom tool, used to provide more context.
      - Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
      - Description string
        
        A description of the namespace shown to the model.
      - Name string
        
        The namespace name used in tool calls (for example, crm).
      - Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
      - Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
      - Description string
        
        Description shown to the model for a client-executed tool search tool.
      - Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
      - Parameters any
        
        Parameter schema for a client-executed tool search tool.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
      - SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
      - SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
      - UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
      - Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
  - Type ToolSearchOutput
    
    The type of the item. Always tool_search_output.
    - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseItemAdditionalTools struct{…}
  - ID string
    
    The unique ID of the additional tools item.
  - Role string
    
    The role that provided the additional tools.
    - const ResponseItemAdditionalToolsRoleUnknown ResponseItemAdditionalToolsRole = "unknown"
    - const ResponseItemAdditionalToolsRoleUser ResponseItemAdditionalToolsRole = "user"
    - const ResponseItemAdditionalToolsRoleAssistant ResponseItemAdditionalToolsRole = "assistant"
    - const ResponseItemAdditionalToolsRoleSystem ResponseItemAdditionalToolsRole = "system"
    - const ResponseItemAdditionalToolsRoleCritic ResponseItemAdditionalToolsRole = "critic"
    - const ResponseItemAdditionalToolsRoleDiscriminator ResponseItemAdditionalToolsRole = "discriminator"
    - const ResponseItemAdditionalToolsRoleDeveloper ResponseItemAdditionalToolsRole = "developer"
    - const ResponseItemAdditionalToolsRoleTool ResponseItemAdditionalToolsRole = "tool"
  - Tools []ToolUnion
    
    The additional tool definitions made available at this item.
    - type FunctionTool struct{…}
      
      Defines a function in your own code the model can choose to call. Learn more about function calling.
    - type FileSearchTool struct{…}
      
      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
    - type ComputerTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type ComputerUsePreviewTool struct{…}
      
      A tool that controls a virtual computer. Learn more about the computer tool.
    - type WebSearchTool struct{…}
      
      Search the Internet for sources related to the prompt. Learn more about the web search tool.
    - type ToolMcp struct{…}
      
      Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
    - type ToolCodeInterpreter struct{…}
      
      A tool that runs Python code to help generate a response to a prompt.
    - type ToolImageGeneration struct{…}
      
      A tool that generates images using the GPT image models.
    - type ToolLocalShell struct{…}
      
      A tool that allows the model to execute shell commands in a local environment.
    - type FunctionShellTool struct{…}
      
      A tool that allows the model to execute shell commands.
    - type CustomTool struct{…}
      
      A custom tool that processes input using a specified format. Learn more about custom tools
    - type NamespaceTool struct{…}
      
      Groups function/custom tools under a shared namespace.
    - type ToolSearchTool struct{…}
      
      Hosted or BYOT tool search configuration for deferred tools.
    - type WebSearchPreviewTool struct{…}
      
      This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
    - type ApplyPatchTool struct{…}
      
      Allows the assistant to create, delete, or update files using unified diffs.
  - Type AdditionalTools
    
    The type of the item. Always additional_tools.
    - const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
- type ResponseReasoningItem struct{…}
  
  A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
  - ID string
    
    The unique identifier of the reasoning content.
  - Summary []ResponseReasoningItemSummary
    
    Reasoning summary content.
    - Text string
      
      A summary of the reasoning output from the model so far.
    - Type SummaryText
      
      The type of the object. Always summary_text.
      - const SummaryTextSummaryText SummaryText = "summary_text"
  - Type Reasoning
    
    The type of the object. Always reasoning.
    - const ReasoningReasoning Reasoning = "reasoning"
  - Content []ResponseReasoningItemContent
    
    Reasoning text content.
    - Text string
      
      The reasoning text from the model.
    - Type ReasoningText
      
      The type of the reasoning text. Always reasoning_text.
      - const ReasoningTextReasoningText ReasoningText = "reasoning_text"
  - EncryptedContent string
    
    The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
  - Status ResponseReasoningItemStatus
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
    - const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
    - const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
- type ResponseCompactionItem struct{…}
  
  A compaction item generated by the v1/responses/compact API.
  - ID string
    
    The unique ID of the compaction item.
  - EncryptedContent string
    
    The encrypted content that was produced by compaction.
  - Type Compaction
    
    The type of the item. Always compaction.
    - const CompactionCompaction Compaction = "compaction"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseItemImageGenerationCall struct{…}
  
  An image generation request made by the model.
  - ID string
    
    The unique ID of the image generation call.
  - Result string
    
    The generated image encoded in base64.
  - Status string
    
    The status of the image generation call.
    - const ResponseItemImageGenerationCallStatusInProgress ResponseItemImageGenerationCallStatus = "in_progress"
    - const ResponseItemImageGenerationCallStatusCompleted ResponseItemImageGenerationCallStatus = "completed"
    - const ResponseItemImageGenerationCallStatusGenerating ResponseItemImageGenerationCallStatus = "generating"
    - const ResponseItemImageGenerationCallStatusFailed ResponseItemImageGenerationCallStatus = "failed"
  - Type ImageGenerationCall
    
    The type of the image generation call. Always image_generation_call.
    - const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
- type ResponseCodeInterpreterToolCall struct{…}
  
  A tool call to run code.
  - ID string
    
    The unique ID of the code interpreter tool call.
  - Code string
    
    The code to run, or null if not available.
  - ContainerID string
    
    The ID of the container used to run the code.
  - Outputs []ResponseCodeInterpreterToolCallOutputUnion
    
    The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
    - type ResponseCodeInterpreterToolCallOutputLogs struct{…}
      
      The logs output from the code interpreter.
      - Logs string
        
        The logs output from the code interpreter.
      - Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
    - type ResponseCodeInterpreterToolCallOutputImage struct{…}
      
      The image output from the code interpreter.
      - Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
      - URL string
        
        The URL of the image output from the code interpreter.
  - Status ResponseCodeInterpreterToolCallStatus
    
    The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
    - const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
    - const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
    - const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
    - const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
    - const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
  - Type CodeInterpreterCall
    
    The type of the code interpreter tool call. Always code_interpreter_call.
    - const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
- type ResponseItemLocalShellCall struct{…}
  
  A tool call to run a command on the local shell.
  - ID string
    
    The unique ID of the local shell call.
  - Action ResponseItemLocalShellCallAction
    
    Execute a shell command on the server.
    - Command []string
      
      The command to run.
    - Env map[string, string]
      
      Environment variables to set for the command.
    - Type Exec
      
      The type of the local shell action. Always exec.
      - const ExecExec Exec = "exec"
    - TimeoutMs int64
      
      Optional timeout in milliseconds for the command.
    - User string
      
      Optional user to run the command as.
    - WorkingDirectory string
      
      Optional working directory to run the command in.
  - CallID string
    
    The unique ID of the local shell tool call generated by the model.
  - Status string
    
    The status of the local shell call.
    - const ResponseItemLocalShellCallStatusInProgress ResponseItemLocalShellCallStatus = "in_progress"
    - const ResponseItemLocalShellCallStatusCompleted ResponseItemLocalShellCallStatus = "completed"
    - const ResponseItemLocalShellCallStatusIncomplete ResponseItemLocalShellCallStatus = "incomplete"
  - Type LocalShellCall
    
    The type of the local shell call. Always local_shell_call.
    - const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
- type ResponseItemLocalShellCallOutput struct{…}
  
  The output of a local shell tool call.
  - ID string
    
    The unique ID of the local shell tool call generated by the model.
  - Output string
    
    A JSON string of the output of the local shell tool call.
  - Type LocalShellCallOutput
    
    The type of the local shell tool call output. Always local_shell_call_output.
    - const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
  - Status string
    
    The status of the item. One of in_progress, completed, or incomplete.
    - const ResponseItemLocalShellCallOutputStatusInProgress ResponseItemLocalShellCallOutputStatus = "in_progress"
    - const ResponseItemLocalShellCallOutputStatusCompleted ResponseItemLocalShellCallOutputStatus = "completed"
    - const ResponseItemLocalShellCallOutputStatusIncomplete ResponseItemLocalShellCallOutputStatus = "incomplete"
- type ResponseFunctionShellToolCall struct{…}
  
  A tool call that executes one or more shell commands in a managed environment.
  - ID string
    
    The unique ID of the shell tool call. Populated when this item is returned via API.
  - Action ResponseFunctionShellToolCallAction
    
    The shell commands and limits that describe how to run the tool call.
    - Commands []string
    - MaxOutputLength int64
      
      Optional maximum number of characters to return from each command.
    - TimeoutMs int64
      
      Optional timeout in milliseconds for the commands.
  - CallID string
    
    The unique ID of the shell tool call generated by the model.
  - Environment ResponseFunctionShellToolCallEnvironmentUnion
    
    Represents the use of a local environment to perform shell actions.
    - type ResponseLocalEnvironment struct{…}
      
      Represents the use of a local environment to perform shell actions.
      - Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
    - type ResponseContainerReference struct{…}
      
      Represents a container created with /v1/containers.
      - ContainerID string
      - Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
  - Status ResponseFunctionShellToolCallStatus
    
    The status of the shell call. One of in_progress, completed, or incomplete.
    - const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
    - const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
    - const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
  - Type ShellCall
    
    The type of the item. Always shell_call.
    - const ShellCallShellCall ShellCall = "shell_call"
  - CreatedBy string
    
    The ID of the entity that created this tool call.
- type ResponseFunctionShellToolCallOutput struct{…}
  
  The output of a shell tool call that was emitted.
  - ID string
    
    The unique ID of the shell call output. Populated when this item is returned via API.
  - CallID string
    
    The unique ID of the shell tool call generated by the model.
  - MaxOutputLength int64
    
    The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
  - Output []ResponseFunctionShellToolCallOutputOutput
    
    An array of shell call output contents
    - Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
      
      Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
      - type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
      - type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
    - Stderr string
      
      The standard error output that was captured.
    - Stdout string
      
      The standard output that was captured.
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - Status ResponseFunctionShellToolCallOutputStatus
    
    The status of the shell call output. One of in_progress, completed, or incomplete.
    - const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
    - const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
    - const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
  - Type ShellCallOutput
    
    The type of the shell call output. Always shell_call_output.
    - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseApplyPatchToolCall struct{…}
  
  A tool call that applies file diffs by creating, deleting, or updating files.
  - ID string
    
    The unique ID of the apply patch tool call. Populated when this item is returned via API.
  - CallID string
    
    The unique ID of the apply patch tool call generated by the model.
  - Operation ResponseApplyPatchToolCallOperationUnion
    
    One of the create_file, delete_file, or update_file operations applied via apply_patch.
    - type ResponseApplyPatchToolCallOperationCreateFile struct{…}
      
      Instruction describing how to create a file via the apply_patch tool.
      - Diff string
        
        Diff to apply.
      - Path string
        
        Path of the file to create.
      - Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
    - type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
      
      Instruction describing how to delete a file via the apply_patch tool.
      - Path string
        
        Path of the file to delete.
      - Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
    - type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
      
      Instruction describing how to update a file via the apply_patch tool.
      - Diff string
        
        Diff to apply.
      - Path string
        
        Path of the file to update.
      - Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
  - Status ResponseApplyPatchToolCallStatus
    
    The status of the apply patch tool call. One of in_progress or completed.
    - const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
    - const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
  - Type ApplyPatchCall
    
    The type of the item. Always apply_patch_call.
    - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
  - CreatedBy string
    
    The ID of the entity that created this tool call.
- type ResponseApplyPatchToolCallOutput struct{…}
  
  The output emitted by an apply patch tool call.
  - ID string
    
    The unique ID of the apply patch tool call output. Populated when this item is returned via API.
  - CallID string
    
    The unique ID of the apply patch tool call generated by the model.
  - Status ResponseApplyPatchToolCallOutputStatus
    
    The status of the apply patch tool call output. One of completed or failed.
    - const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
    - const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
  - Type ApplyPatchCallOutput
    
    The type of the item. Always apply_patch_call_output.
    - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
  - CreatedBy string
    
    The ID of the entity that created this tool call output.
  - Output string
    
    Optional textual output returned by the apply patch tool.
- type ResponseItemMcpListTools struct{…}
  
  A list of tools available on an MCP server.
  - ID string
    
    The unique ID of the list.
  - ServerLabel string
    
    The label of the MCP server.
  - Tools []ResponseItemMcpListToolsTool
    
    The tools available on the server.
    - InputSchema any
      
      The JSON schema describing the tool's input.
    - Name string
      
      The name of the tool.
    - Annotations any
      
      Additional annotations about the tool.
    - Description string
      
      The description of the tool.
  - Type McpListTools
    
    The type of the item. Always mcp_list_tools.
    - const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
  - Error string
    
    Error message if the server could not list tools.
- type ResponseItemMcpApprovalRequest struct{…}
  
  A request for human approval of a tool invocation.
  - ID string
    
    The unique ID of the approval request.
  - Arguments string
    
    A JSON string of arguments for the tool.
  - Name string
    
    The name of the tool to run.
  - ServerLabel string
    
    The label of the MCP server making the request.
  - Type McpApprovalRequest
    
    The type of the item. Always mcp_approval_request.
    - const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
- type ResponseItemMcpApprovalResponse struct{…}
  
  A response to an MCP approval request.
  - ID string
    
    The unique ID of the approval response
  - ApprovalRequestID string
    
    The ID of the approval request being answered.
  - Approve bool
    
    Whether the request was approved.
  - Type McpApprovalResponse
    
    The type of the item. Always mcp_approval_response.
    - const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
  - Reason string
    
    Optional reason for the decision.
- type ResponseItemMcpCall struct{…}
  
  An invocation of a tool on an MCP server.
  - ID string
    
    The unique ID of the tool call.
  - Arguments string
    
    A JSON string of the arguments passed to the tool.
  - Name string
    
    The name of the tool that was run.
  - ServerLabel string
    
    The label of the MCP server running the tool.
  - Type McpCall
    
    The type of the item. Always mcp_call.
    - const McpCallMcpCall McpCall = "mcp_call"
  - ApprovalRequestID string
    
    Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
  - Error string
    
    The error from the tool call, if any.
  - Output string
    
    The output from the tool call.
  - Status string
    
    The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
    - const ResponseItemMcpCallStatusInProgress ResponseItemMcpCallStatus = "in_progress"
    - const ResponseItemMcpCallStatusCompleted ResponseItemMcpCallStatus = "completed"
    - const ResponseItemMcpCallStatusIncomplete ResponseItemMcpCallStatus = "incomplete"
    - const ResponseItemMcpCallStatusCalling ResponseItemMcpCallStatus = "calling"
    - const ResponseItemMcpCallStatusFailed ResponseItemMcpCallStatus = "failed"
- type ResponseCustomToolCallItem struct{…}
  
  A call to a custom tool created by the model.
  - ID string
    
    The unique ID of the custom tool call item.
  - Status string
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseCustomToolCallItemStatusInProgress ResponseCustomToolCallItemStatus = "in_progress"
    - const ResponseCustomToolCallItemStatusCompleted ResponseCustomToolCallItemStatus = "completed"
    - const ResponseCustomToolCallItemStatusIncomplete ResponseCustomToolCallItemStatus = "incomplete"
  - CreatedBy string
    
    The identifier of the actor that created the item.
- type ResponseCustomToolCallOutputItem struct{…}
  
  The output of a custom tool call from your code, being sent back to the model.
  - ID string
    
    The unique ID of the custom tool call output item.
  - Status string
    
    The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
    - const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
    - const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
    - const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
  - CreatedBy string
    
    The identifier of the actor that created the item.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
  "github.com/openai/openai-go/responses"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  page, err := client.Responses.InputItems.List(
    context.TODO(),
    "response_id",
    responses.InputItemListParams{

    },
  )
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", page)
}

Response

{
  "data": [
    {
      "id": "id",
      "content": [
        {
          "text": "text",
          "type": "input_text"
        }
      ],
      "role": "user",
      "type": "message",
      "status": "in_progress"
    }
  ],
  "first_id": "first_id",
  "has_more": true,
  "last_id": "last_id",
  "object": "list"
}

Domain Types

Response Item List

type ResponseItemList struct{…}

A list of Response items.
- Data []ResponseItemUnion
  
  A list of items used to generate this response.
  - type ResponseInputMessageItem struct{…}
    - ID string
      
      The unique ID of the message input.
    - Content ResponseInputMessageContentList
      
      A list of one or many input items to the model, containing different content types.
      - type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
      - type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
      - type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
    - Role ResponseInputMessageItemRole
      
      The role of the message input. One of user, system, or developer.
      - const ResponseInputMessageItemRoleUser ResponseInputMessageItemRole = "user"
      - const ResponseInputMessageItemRoleSystem ResponseInputMessageItemRole = "system"
      - const ResponseInputMessageItemRoleDeveloper ResponseInputMessageItemRole = "developer"
    - Type Message
      
      The type of the message input. Always set to message.
      - const MessageMessage Message = "message"
    - Status ResponseInputMessageItemStatus
      
      The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseInputMessageItemStatusInProgress ResponseInputMessageItemStatus = "in_progress"
      - const ResponseInputMessageItemStatusCompleted ResponseInputMessageItemStatus = "completed"
      - const ResponseInputMessageItemStatusIncomplete ResponseInputMessageItemStatus = "incomplete"
  - type ResponseOutputMessage struct{…}
    
    An output message from the model.
    - ID string
      
      The unique ID of the output message.
    - Content []ResponseOutputMessageContentUnion
      
      The content of the output message.
      - type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
      - type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
    - Role Assistant
      
      The role of the output message. Always assistant.
      - const AssistantAssistant Assistant = "assistant"
    - Status ResponseOutputMessageStatus
      
      The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
      - const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
      - const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
      - const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
    - Type Message
      
      The type of the output message. Always message.
      - const MessageMessage Message = "message"
    - Phase ResponseOutputMessagePhase
      
      Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
      - const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
      - const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
  - type ResponseFileSearchToolCall struct{…}
    
    The results of a file search tool call. See the file search guide for more information.
    - ID string
      
      The unique ID of the file search tool call.
    - Queries []string
      
      The queries used to search for files.
    - Status ResponseFileSearchToolCallStatus
      
      The status of the file search tool call. One of in_progress, searching, incomplete or failed,
      - const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
      - const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
      - const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
      - const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
      - const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
    - Type FileSearchCall
      
      The type of the file search tool call. Always file_search_call.
      - const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
    - Results []ResponseFileSearchToolCallResult
      
      The results of the file search tool call.
      - Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
      - FileID string
        
        The unique ID of the file.
      - Filename string
        
        The name of the file.
      - Score float64
        
        The relevance score of the file - a value between 0 and 1.
      - Text string
        
        The text that was retrieved from the file.
  - type ResponseComputerToolCall struct{…}
    
    A tool call to a computer use tool. See the computer use guide for more information.
    - ID string
      
      The unique ID of the computer call.
    - CallID string
      
      An identifier used when responding to the tool call with output.
    - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
      
      The pending safety checks for the computer call.
      - ID string
        
        The ID of the pending safety check.
      - Code string
        
        The type of the pending safety check.
      - Message string
        
        Details about the pending safety check.
    - Status ResponseComputerToolCallStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
      - const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
      - const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
    - Type ResponseComputerToolCallType
      
      The type of the computer call. Always computer_call.
      - const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
    - Action ResponseComputerToolCallActionUnion
      
      A click action.
      - type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
      - type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
      - type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
      - type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
      - type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
      - type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
      - type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
      - type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
      - type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
    - Actions ComputerActionList
      
      Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
      - type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
      - type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
      - type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
      - type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
      - type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
      - type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
      - type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
      - type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
      - type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
  - type ResponseComputerToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the computer call tool output.
    - CallID string
      
      The ID of the computer tool call that produced the output.
    - Output ResponseComputerToolCallOutputScreenshot
      
      A computer screenshot image used with the computer use tool.
      - Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
      - FileID string
        
        The identifier of an uploaded file that contains the screenshot.
      - ImageURL string
        
        The URL of the screenshot image.
    - Status ResponseComputerToolCallOutputItemStatus
      
      The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
      - const ResponseComputerToolCallOutputItemStatusCompleted ResponseComputerToolCallOutputItemStatus = "completed"
      - const ResponseComputerToolCallOutputItemStatusIncomplete ResponseComputerToolCallOutputItemStatus = "incomplete"
      - const ResponseComputerToolCallOutputItemStatusFailed ResponseComputerToolCallOutputItemStatus = "failed"
      - const ResponseComputerToolCallOutputItemStatusInProgress ResponseComputerToolCallOutputItemStatus = "in_progress"
    - Type ComputerCallOutput
      
      The type of the computer tool call output. Always computer_call_output.
      - const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
    - AcknowledgedSafetyChecks []ResponseComputerToolCallOutputItemAcknowledgedSafetyCheck
      
      The safety checks reported by the API that have been acknowledged by the developer.
      - ID string
        
        The ID of the pending safety check.
      - Code string
        
        The type of the pending safety check.
      - Message string
        
        Details about the pending safety check.
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseFunctionWebSearch struct{…}
    
    The results of a web search tool call. See the web search guide for more information.
    - ID string
      
      The unique ID of the web search tool call.
    - Action ResponseFunctionWebSearchActionUnion
      
      An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
      - type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
      - type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
      - type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
    - Status ResponseFunctionWebSearchStatus
      
      The status of the web search tool call.
      - const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
      - const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
      - const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
      - const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
    - Type WebSearchCall
      
      The type of the web search tool call. Always web_search_call.
      - const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
  - type ResponseFunctionToolCallItem struct{…}
    
    A tool call to run a function. See the function calling guide for more information.
    - ID string
      
      The unique ID of the function tool call.
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseFunctionToolCallItemStatusInProgress ResponseFunctionToolCallItemStatus = "in_progress"
      - const ResponseFunctionToolCallItemStatusCompleted ResponseFunctionToolCallItemStatus = "completed"
      - const ResponseFunctionToolCallItemStatusIncomplete ResponseFunctionToolCallItemStatus = "incomplete"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseFunctionToolCallOutputItem struct{…}
    - ID string
      
      The unique ID of the function call tool output.
    - CallID string
      
      The unique ID of the function tool call generated by the model.
    - Output ResponseFunctionToolCallOutputItemOutputUnion
      
      The output from the function call generated by your code. Can be a string or an list of output content.
      - string
      - type ResponseFunctionToolCallOutputItemOutputOutputContentList []ResponseFunctionToolCallOutputItemOutputOutputContentListItemUnion
        
        Text, image, or file output of the function call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
    - Status ResponseFunctionToolCallOutputItemStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseFunctionToolCallOutputItemStatusInProgress ResponseFunctionToolCallOutputItemStatus = "in_progress"
      - const ResponseFunctionToolCallOutputItemStatusCompleted ResponseFunctionToolCallOutputItemStatus = "completed"
      - const ResponseFunctionToolCallOutputItemStatusIncomplete ResponseFunctionToolCallOutputItemStatus = "incomplete"
    - Type FunctionCallOutput
      
      The type of the function tool call output. Always function_call_output.
      - const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseToolSearchCall struct{…}
    - ID string
      
      The unique ID of the tool search call item.
    - Arguments any
      
      Arguments used for the tool search call.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchCallExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchCallExecutionServer ResponseToolSearchCallExecution = "server"
      - const ResponseToolSearchCallExecutionClient ResponseToolSearchCallExecution = "client"
    - Status ResponseToolSearchCallStatus
      
      The status of the tool search call item that was recorded.
      - const ResponseToolSearchCallStatusInProgress ResponseToolSearchCallStatus = "in_progress"
      - const ResponseToolSearchCallStatusCompleted ResponseToolSearchCallStatus = "completed"
      - const ResponseToolSearchCallStatusIncomplete ResponseToolSearchCallStatus = "incomplete"
    - Type ToolSearchCall
      
      The type of the item. Always tool_search_call.
      - const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseToolSearchOutputItem struct{…}
    - ID string
      
      The unique ID of the tool search output item.
    - CallID string
      
      The unique ID of the tool search call generated by the model.
    - Execution ResponseToolSearchOutputItemExecution
      
      Whether tool search was executed by the server or by the client.
      - const ResponseToolSearchOutputItemExecutionServer ResponseToolSearchOutputItemExecution = "server"
      - const ResponseToolSearchOutputItemExecutionClient ResponseToolSearchOutputItemExecution = "client"
    - Status ResponseToolSearchOutputItemStatus
      
      The status of the tool search output item that was recorded.
      - const ResponseToolSearchOutputItemStatusInProgress ResponseToolSearchOutputItemStatus = "in_progress"
      - const ResponseToolSearchOutputItemStatusCompleted ResponseToolSearchOutputItemStatus = "completed"
      - const ResponseToolSearchOutputItemStatusIncomplete ResponseToolSearchOutputItemStatus = "incomplete"
    - Tools []ToolUnion
      
      The loaded tool definitions returned by tool search.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
    - Type ToolSearchOutput
      
      The type of the item. Always tool_search_output.
      - const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseItemAdditionalTools struct{…}
    - ID string
      
      The unique ID of the additional tools item.
    - Role string
      
      The role that provided the additional tools.
      - const ResponseItemAdditionalToolsRoleUnknown ResponseItemAdditionalToolsRole = "unknown"
      - const ResponseItemAdditionalToolsRoleUser ResponseItemAdditionalToolsRole = "user"
      - const ResponseItemAdditionalToolsRoleAssistant ResponseItemAdditionalToolsRole = "assistant"
      - const ResponseItemAdditionalToolsRoleSystem ResponseItemAdditionalToolsRole = "system"
      - const ResponseItemAdditionalToolsRoleCritic ResponseItemAdditionalToolsRole = "critic"
      - const ResponseItemAdditionalToolsRoleDiscriminator ResponseItemAdditionalToolsRole = "discriminator"
      - const ResponseItemAdditionalToolsRoleDeveloper ResponseItemAdditionalToolsRole = "developer"
      - const ResponseItemAdditionalToolsRoleTool ResponseItemAdditionalToolsRole = "tool"
    - Tools []ToolUnion
      
      The additional tool definitions made available at this item.
      - type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
      - type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
      - type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
      - type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
      - type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
      - type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
      - type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
      - type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
      - type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
      - type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
      - type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
      - type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
      - type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
      - type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
    - Type AdditionalTools
      
      The type of the item. Always additional_tools.
      - const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
  - type ResponseReasoningItem struct{…}
    
    A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
    - ID string
      
      The unique identifier of the reasoning content.
    - Summary []ResponseReasoningItemSummary
      
      Reasoning summary content.
      - Text string
        
        A summary of the reasoning output from the model so far.
      - Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
    - Type Reasoning
      
      The type of the object. Always reasoning.
      - const ReasoningReasoning Reasoning = "reasoning"
    - Content []ResponseReasoningItemContent
      
      Reasoning text content.
      - Text string
        
        The reasoning text from the model.
      - Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
    - EncryptedContent string
      
      The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
    - Status ResponseReasoningItemStatus
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
      - const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
      - const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
  - type ResponseCompactionItem struct{…}
    
    A compaction item generated by the v1/responses/compact API.
    - ID string
      
      The unique ID of the compaction item.
    - EncryptedContent string
      
      The encrypted content that was produced by compaction.
    - Type Compaction
      
      The type of the item. Always compaction.
      - const CompactionCompaction Compaction = "compaction"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseItemImageGenerationCall struct{…}
    
    An image generation request made by the model.
    - ID string
      
      The unique ID of the image generation call.
    - Result string
      
      The generated image encoded in base64.
    - Status string
      
      The status of the image generation call.
      - const ResponseItemImageGenerationCallStatusInProgress ResponseItemImageGenerationCallStatus = "in_progress"
      - const ResponseItemImageGenerationCallStatusCompleted ResponseItemImageGenerationCallStatus = "completed"
      - const ResponseItemImageGenerationCallStatusGenerating ResponseItemImageGenerationCallStatus = "generating"
      - const ResponseItemImageGenerationCallStatusFailed ResponseItemImageGenerationCallStatus = "failed"
    - Type ImageGenerationCall
      
      The type of the image generation call. Always image_generation_call.
      - const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
  - type ResponseCodeInterpreterToolCall struct{…}
    
    A tool call to run code.
    - ID string
      
      The unique ID of the code interpreter tool call.
    - Code string
      
      The code to run, or null if not available.
    - ContainerID string
      
      The ID of the container used to run the code.
    - Outputs []ResponseCodeInterpreterToolCallOutputUnion
      
      The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
      - type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
      - type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
    - Status ResponseCodeInterpreterToolCallStatus
      
      The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
      - const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
      - const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
      - const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
      - const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
      - const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
    - Type CodeInterpreterCall
      
      The type of the code interpreter tool call. Always code_interpreter_call.
      - const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
  - type ResponseItemLocalShellCall struct{…}
    
    A tool call to run a command on the local shell.
    - ID string
      
      The unique ID of the local shell call.
    - Action ResponseItemLocalShellCallAction
      
      Execute a shell command on the server.
      - Command []string
        
        The command to run.
      - Env map[string, string]
        
        Environment variables to set for the command.
      - Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
      - User string
        
        Optional user to run the command as.
      - WorkingDirectory string
        
        Optional working directory to run the command in.
    - CallID string
      
      The unique ID of the local shell tool call generated by the model.
    - Status string
      
      The status of the local shell call.
      - const ResponseItemLocalShellCallStatusInProgress ResponseItemLocalShellCallStatus = "in_progress"
      - const ResponseItemLocalShellCallStatusCompleted ResponseItemLocalShellCallStatus = "completed"
      - const ResponseItemLocalShellCallStatusIncomplete ResponseItemLocalShellCallStatus = "incomplete"
    - Type LocalShellCall
      
      The type of the local shell call. Always local_shell_call.
      - const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
  - type ResponseItemLocalShellCallOutput struct{…}
    
    The output of a local shell tool call.
    - ID string
      
      The unique ID of the local shell tool call generated by the model.
    - Output string
      
      A JSON string of the output of the local shell tool call.
    - Type LocalShellCallOutput
      
      The type of the local shell tool call output. Always local_shell_call_output.
      - const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete.
      - const ResponseItemLocalShellCallOutputStatusInProgress ResponseItemLocalShellCallOutputStatus = "in_progress"
      - const ResponseItemLocalShellCallOutputStatusCompleted ResponseItemLocalShellCallOutputStatus = "completed"
      - const ResponseItemLocalShellCallOutputStatusIncomplete ResponseItemLocalShellCallOutputStatus = "incomplete"
  - type ResponseFunctionShellToolCall struct{…}
    
    A tool call that executes one or more shell commands in a managed environment.
    - ID string
      
      The unique ID of the shell tool call. Populated when this item is returned via API.
    - Action ResponseFunctionShellToolCallAction
      
      The shell commands and limits that describe how to run the tool call.
      - Commands []string
      - MaxOutputLength int64
        
        Optional maximum number of characters to return from each command.
      - TimeoutMs int64
        
        Optional timeout in milliseconds for the commands.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - Environment ResponseFunctionShellToolCallEnvironmentUnion
      
      Represents the use of a local environment to perform shell actions.
      - type ResponseLocalEnvironment struct{…}
        
        Represents the use of a local environment to perform shell actions.
        
        Type Local
        
        The environment type. Always local.
        
        const LocalLocal Local = "local"
      - type ResponseContainerReference struct{…}
        
        Represents a container created with /v1/containers.
        
        ContainerID string
        
        Type ContainerReference
        
        The environment type. Always container_reference.
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
    - Status ResponseFunctionShellToolCallStatus
      
      The status of the shell call. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallStatusInProgress ResponseFunctionShellToolCallStatus = "in_progress"
      - const ResponseFunctionShellToolCallStatusCompleted ResponseFunctionShellToolCallStatus = "completed"
      - const ResponseFunctionShellToolCallStatusIncomplete ResponseFunctionShellToolCallStatus = "incomplete"
    - Type ShellCall
      
      The type of the item. Always shell_call.
      - const ShellCallShellCall ShellCall = "shell_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseFunctionShellToolCallOutput struct{…}
    
    The output of a shell tool call that was emitted.
    - ID string
      
      The unique ID of the shell call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the shell tool call generated by the model.
    - MaxOutputLength int64
      
      The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
    - Output []ResponseFunctionShellToolCallOutputOutput
      
      An array of shell call output contents
      - Outcome ResponseFunctionShellToolCallOutputOutputOutcomeUnion
        
        Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellToolCallOutputOutputOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        Exit code from the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
      - Stderr string
        
        The standard error output that was captured.
      - Stdout string
        
        The standard output that was captured.
      - CreatedBy string
        
        The identifier of the actor that created the item.
    - Status ResponseFunctionShellToolCallOutputStatus
      
      The status of the shell call output. One of in_progress, completed, or incomplete.
      - const ResponseFunctionShellToolCallOutputStatusInProgress ResponseFunctionShellToolCallOutputStatus = "in_progress"
      - const ResponseFunctionShellToolCallOutputStatusCompleted ResponseFunctionShellToolCallOutputStatus = "completed"
      - const ResponseFunctionShellToolCallOutputStatusIncomplete ResponseFunctionShellToolCallOutputStatus = "incomplete"
    - Type ShellCallOutput
      
      The type of the shell call output. Always shell_call_output.
      - const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseApplyPatchToolCall struct{…}
    
    A tool call that applies file diffs by creating, deleting, or updating files.
    - ID string
      
      The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Operation ResponseApplyPatchToolCallOperationUnion
      
      One of the create_file, delete_file, or update_file operations applied via apply_patch.
      - type ResponseApplyPatchToolCallOperationCreateFile struct{…}
        
        Instruction describing how to create a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to create.
        
        Type CreateFile
        
        Create a new file with the provided diff.
        
        const CreateFileCreateFile CreateFile = "create_file"
      - type ResponseApplyPatchToolCallOperationDeleteFile struct{…}
        
        Instruction describing how to delete a file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete.
        
        Type DeleteFile
        
        Delete the specified file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
      - type ResponseApplyPatchToolCallOperationUpdateFile struct{…}
        
        Instruction describing how to update a file via the apply_patch tool.
        
        Diff string
        
        Diff to apply.
        
        Path string
        
        Path of the file to update.
        
        Type UpdateFile
        
        Update an existing file with the provided diff.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
    - Status ResponseApplyPatchToolCallStatus
      
      The status of the apply patch tool call. One of in_progress or completed.
      - const ResponseApplyPatchToolCallStatusInProgress ResponseApplyPatchToolCallStatus = "in_progress"
      - const ResponseApplyPatchToolCallStatusCompleted ResponseApplyPatchToolCallStatus = "completed"
    - Type ApplyPatchCall
      
      The type of the item. Always apply_patch_call.
      - const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
    - CreatedBy string
      
      The ID of the entity that created this tool call.
  - type ResponseApplyPatchToolCallOutput struct{…}
    
    The output emitted by an apply patch tool call.
    - ID string
      
      The unique ID of the apply patch tool call output. Populated when this item is returned via API.
    - CallID string
      
      The unique ID of the apply patch tool call generated by the model.
    - Status ResponseApplyPatchToolCallOutputStatus
      
      The status of the apply patch tool call output. One of completed or failed.
      - const ResponseApplyPatchToolCallOutputStatusCompleted ResponseApplyPatchToolCallOutputStatus = "completed"
      - const ResponseApplyPatchToolCallOutputStatusFailed ResponseApplyPatchToolCallOutputStatus = "failed"
    - Type ApplyPatchCallOutput
      
      The type of the item. Always apply_patch_call_output.
      - const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
    - CreatedBy string
      
      The ID of the entity that created this tool call output.
    - Output string
      
      Optional textual output returned by the apply patch tool.
  - type ResponseItemMcpListTools struct{…}
    
    A list of tools available on an MCP server.
    - ID string
      
      The unique ID of the list.
    - ServerLabel string
      
      The label of the MCP server.
    - Tools []ResponseItemMcpListToolsTool
      
      The tools available on the server.
      - InputSchema any
        
        The JSON schema describing the tool's input.
      - Name string
        
        The name of the tool.
      - Annotations any
        
        Additional annotations about the tool.
      - Description string
        
        The description of the tool.
    - Type McpListTools
      
      The type of the item. Always mcp_list_tools.
      - const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
    - Error string
      
      Error message if the server could not list tools.
  - type ResponseItemMcpApprovalRequest struct{…}
    
    A request for human approval of a tool invocation.
    - ID string
      
      The unique ID of the approval request.
    - Arguments string
      
      A JSON string of arguments for the tool.
    - Name string
      
      The name of the tool to run.
    - ServerLabel string
      
      The label of the MCP server making the request.
    - Type McpApprovalRequest
      
      The type of the item. Always mcp_approval_request.
      - const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
  - type ResponseItemMcpApprovalResponse struct{…}
    
    A response to an MCP approval request.
    - ID string
      
      The unique ID of the approval response
    - ApprovalRequestID string
      
      The ID of the approval request being answered.
    - Approve bool
      
      Whether the request was approved.
    - Type McpApprovalResponse
      
      The type of the item. Always mcp_approval_response.
      - const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
    - Reason string
      
      Optional reason for the decision.
  - type ResponseItemMcpCall struct{…}
    
    An invocation of a tool on an MCP server.
    - ID string
      
      The unique ID of the tool call.
    - Arguments string
      
      A JSON string of the arguments passed to the tool.
    - Name string
      
      The name of the tool that was run.
    - ServerLabel string
      
      The label of the MCP server running the tool.
    - Type McpCall
      
      The type of the item. Always mcp_call.
      - const McpCallMcpCall McpCall = "mcp_call"
    - ApprovalRequestID string
      
      Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
    - Error string
      
      The error from the tool call, if any.
    - Output string
      
      The output from the tool call.
    - Status string
      
      The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
      - const ResponseItemMcpCallStatusInProgress ResponseItemMcpCallStatus = "in_progress"
      - const ResponseItemMcpCallStatusCompleted ResponseItemMcpCallStatus = "completed"
      - const ResponseItemMcpCallStatusIncomplete ResponseItemMcpCallStatus = "incomplete"
      - const ResponseItemMcpCallStatusCalling ResponseItemMcpCallStatus = "calling"
      - const ResponseItemMcpCallStatusFailed ResponseItemMcpCallStatus = "failed"
  - type ResponseCustomToolCallItem struct{…}
    
    A call to a custom tool created by the model.
    - ID string
      
      The unique ID of the custom tool call item.
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseCustomToolCallItemStatusInProgress ResponseCustomToolCallItemStatus = "in_progress"
      - const ResponseCustomToolCallItemStatusCompleted ResponseCustomToolCallItemStatus = "completed"
      - const ResponseCustomToolCallItemStatusIncomplete ResponseCustomToolCallItemStatus = "incomplete"
    - CreatedBy string
      
      The identifier of the actor that created the item.
  - type ResponseCustomToolCallOutputItem struct{…}
    
    The output of a custom tool call from your code, being sent back to the model.
    - ID string
      
      The unique ID of the custom tool call output item.
    - Status string
      
      The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
      - const ResponseCustomToolCallOutputItemStatusInProgress ResponseCustomToolCallOutputItemStatus = "in_progress"
      - const ResponseCustomToolCallOutputItemStatusCompleted ResponseCustomToolCallOutputItemStatus = "completed"
      - const ResponseCustomToolCallOutputItemStatusIncomplete ResponseCustomToolCallOutputItemStatus = "incomplete"
    - CreatedBy string
      
      The identifier of the actor that created the item.
- FirstID string
  
  The ID of the first item in the list.
- HasMore bool
  
  Whether there are more items available.
- LastID string
  
  The ID of the last item in the list.
- Object List
  
  The type of object returned, must be list.
  - const ListList List = "list"

Input Tokens

Get input token counts

client.Responses.InputTokens.Count(ctx, body) (*InputTokenCountResponse, error)

post /responses/input_tokens

Returns input token counts of the request.

Returns an object with object set to response.input_tokens and an input_tokens count.

Parameters

body InputTokenCountParams
- Conversation param.Field[InputTokenCountParamsConversationUnion]
  
  The conversation that this response belongs to. Items from this conversation are prepended to input_items for this response request. Input items and output items from this response are automatically added to this conversation after this response completes.
  - string
  - type ResponseConversationParamResp struct{…}
    
    The conversation that this response belongs to.
    - ID string
      
      The unique ID of the conversation.
- Input param.Field[InputTokenCountParamsInputUnion]
  
  Text, image, or file inputs to the model, used to generate a response
  - string
  - type InputTokenCountParamsInputArray []ResponseInputItemUnion
    
    A list of one or many input items to the model, containing different content types.
    - type EasyInputMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.
      - Content EasyInputMessageContentUnion
        
        Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
        
        string
        
        type ResponseInputMessageContentList []ResponseInputContentUnion
        
        A list of one or many input items to the model, containing different content types.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        Detail ResponseInputImageDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageDetailLow ResponseInputImageDetail = "low"
        
        const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"
        
        const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"
        
        const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileDetailLow ResponseInputFileDetail = "low"
        
        const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"
        
        FileData string
        
        The content of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Role EasyInputMessageRole
        
        The role of the message input. One of user, assistant, system, or developer.
        
        const EasyInputMessageRoleUser EasyInputMessageRole = "user"
        
        const EasyInputMessageRoleAssistant EasyInputMessageRole = "assistant"
        
        const EasyInputMessageRoleSystem EasyInputMessageRole = "system"
        
        const EasyInputMessageRoleDeveloper EasyInputMessageRole = "developer"
      - Phase EasyInputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const EasyInputMessagePhaseCommentary EasyInputMessagePhase = "commentary"
        
        const EasyInputMessagePhaseFinalAnswer EasyInputMessagePhase = "final_answer"
      - Type EasyInputMessageType
        
        The type of the message input. Always message.
        
        const EasyInputMessageTypeMessage EasyInputMessageType = "message"
    - type ResponseInputItemMessage struct{…}
      
      A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.
      - Content ResponseInputMessageContentList
        
        A list of one or many input items to the model, containing different content types.
      - Role string
        
        The role of the message input. One of user, system, or developer.
        
        const ResponseInputItemMessageRoleUser ResponseInputItemMessageRole = "user"
        
        const ResponseInputItemMessageRoleSystem ResponseInputItemMessageRole = "system"
        
        const ResponseInputItemMessageRoleDeveloper ResponseInputItemMessageRole = "developer"
      - Status string
        
        The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemMessageStatusInProgress ResponseInputItemMessageStatus = "in_progress"
        
        const ResponseInputItemMessageStatusCompleted ResponseInputItemMessageStatus = "completed"
        
        const ResponseInputItemMessageStatusIncomplete ResponseInputItemMessageStatus = "incomplete"
      - Type string
        
        The type of the message input. Always set to message.
        
        const ResponseInputItemMessageTypeMessage ResponseInputItemMessageType = "message"
    - type ResponseOutputMessage struct{…}
      
      An output message from the model.
      - ID string
        
        The unique ID of the output message.
      - Content []ResponseOutputMessageContentUnion
        
        The content of the output message.
        
        type ResponseOutputText struct{…}
        
        A text output from the model.
        
        Annotations []ResponseOutputTextAnnotationUnion
        
        The annotations of the text output.
        
        type ResponseOutputTextAnnotationFileCitation struct{…}
        
        A citation to a file.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the file cited.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FileCitation
        
        The type of the file citation. Always file_citation.
        
        const FileCitationFileCitation FileCitation = "file_citation"
        
        type ResponseOutputTextAnnotationURLCitation struct{…}
        
        A citation for a web resource used to generate a model response.
        
        EndIndex int64
        
        The index of the last character of the URL citation in the message.
        
        StartIndex int64
        
        The index of the first character of the URL citation in the message.
        
        Title string
        
        The title of the web resource.
        
        Type URLCitation
        
        The type of the URL citation. Always url_citation.
        
        const URLCitationURLCitation URLCitation = "url_citation"
        
        URL string
        
        The URL of the web resource.
        
        type ResponseOutputTextAnnotationContainerFileCitation struct{…}
        
        A citation for a container file used to generate a model response.
        
        ContainerID string
        
        The ID of the container file.
        
        EndIndex int64
        
        The index of the last character of the container file citation in the message.
        
        FileID string
        
        The ID of the file.
        
        Filename string
        
        The filename of the container file cited.
        
        StartIndex int64
        
        The index of the first character of the container file citation in the message.
        
        Type ContainerFileCitation
        
        The type of the container file citation. Always container_file_citation.
        
        const ContainerFileCitationContainerFileCitation ContainerFileCitation = "container_file_citation"
        
        type ResponseOutputTextAnnotationFilePath struct{…}
        
        A path to a file.
        
        FileID string
        
        The ID of the file.
        
        Index int64
        
        The index of the file in the list of files.
        
        Type FilePath
        
        The type of the file path. Always file_path.
        
        const FilePathFilePath FilePath = "file_path"
        
        Text string
        
        The text output from the model.
        
        Type OutputText
        
        The type of the output text. Always output_text.
        
        const OutputTextOutputText OutputText = "output_text"
        
        Logprobs []ResponseOutputTextLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        TopLogprobs []ResponseOutputTextLogprobTopLogprob
        
        Token string
        
        Bytes []int64
        
        Logprob float64
        
        type ResponseOutputRefusal struct{…}
        
        A refusal from the model.
        
        Refusal string
        
        The refusal explanation from the model.
        
        Type Refusal
        
        The type of the refusal. Always refusal.
        
        const RefusalRefusal Refusal = "refusal"
      - Role Assistant
        
        The role of the output message. Always assistant.
        
        const AssistantAssistant Assistant = "assistant"
      - Status ResponseOutputMessageStatus
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseOutputMessageStatusInProgress ResponseOutputMessageStatus = "in_progress"
        
        const ResponseOutputMessageStatusCompleted ResponseOutputMessageStatus = "completed"
        
        const ResponseOutputMessageStatusIncomplete ResponseOutputMessageStatus = "incomplete"
      - Type Message
        
        The type of the output message. Always message.
        
        const MessageMessage Message = "message"
      - Phase ResponseOutputMessagePhase
        
        Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
        
        const ResponseOutputMessagePhaseCommentary ResponseOutputMessagePhase = "commentary"
        
        const ResponseOutputMessagePhaseFinalAnswer ResponseOutputMessagePhase = "final_answer"
    - type ResponseFileSearchToolCall struct{…}
      
      The results of a file search tool call. See the file search guide for more information.
      - ID string
        
        The unique ID of the file search tool call.
      - Queries []string
        
        The queries used to search for files.
      - Status ResponseFileSearchToolCallStatus
        
        The status of the file search tool call. One of in_progress, searching, incomplete or failed,
        
        const ResponseFileSearchToolCallStatusInProgress ResponseFileSearchToolCallStatus = "in_progress"
        
        const ResponseFileSearchToolCallStatusSearching ResponseFileSearchToolCallStatus = "searching"
        
        const ResponseFileSearchToolCallStatusCompleted ResponseFileSearchToolCallStatus = "completed"
        
        const ResponseFileSearchToolCallStatusIncomplete ResponseFileSearchToolCallStatus = "incomplete"
        
        const ResponseFileSearchToolCallStatusFailed ResponseFileSearchToolCallStatus = "failed"
      - Type FileSearchCall
        
        The type of the file search tool call. Always file_search_call.
        
        const FileSearchCallFileSearchCall FileSearchCall = "file_search_call"
      - Results []ResponseFileSearchToolCallResult
        
        The results of the file search tool call.
        
        Attributes map[string, ResponseFileSearchToolCallResultAttributeUnion]
        
        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
        
        string
        
        float64
        
        bool
        
        FileID string
        
        The unique ID of the file.
        
        Filename string
        
        The name of the file.
        
        Score float64
        
        The relevance score of the file - a value between 0 and 1.
        
        Text string
        
        The text that was retrieved from the file.
    - type ResponseComputerToolCall struct{…}
      
      A tool call to a computer use tool. See the computer use guide for more information.
      - ID string
        
        The unique ID of the computer call.
      - CallID string
        
        An identifier used when responding to the tool call with output.
      - PendingSafetyChecks []ResponseComputerToolCallPendingSafetyCheck
        
        The pending safety checks for the computer call.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status ResponseComputerToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseComputerToolCallStatusInProgress ResponseComputerToolCallStatus = "in_progress"
        
        const ResponseComputerToolCallStatusCompleted ResponseComputerToolCallStatus = "completed"
        
        const ResponseComputerToolCallStatusIncomplete ResponseComputerToolCallStatus = "incomplete"
      - Type ResponseComputerToolCallType
        
        The type of the computer call. Always computer_call.
        
        const ResponseComputerToolCallTypeComputerCall ResponseComputerToolCallType = "computer_call"
      - Action ResponseComputerToolCallActionUnion
        
        A click action.
        
        type ResponseComputerToolCallActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ResponseComputerToolCallActionClickButtonLeft ResponseComputerToolCallActionClickButton = "left"
        
        const ResponseComputerToolCallActionClickButtonRight ResponseComputerToolCallActionClickButton = "right"
        
        const ResponseComputerToolCallActionClickButtonWheel ResponseComputerToolCallActionClickButton = "wheel"
        
        const ResponseComputerToolCallActionClickButtonBack ResponseComputerToolCallActionClickButton = "back"
        
        const ResponseComputerToolCallActionClickButtonForward ResponseComputerToolCallActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ResponseComputerToolCallActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ResponseComputerToolCallActionDrag struct{…}
        
        A drag action.
        
        Path []ResponseComputerToolCallActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ResponseComputerToolCallActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ResponseComputerToolCallActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ResponseComputerToolCallActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ResponseComputerToolCallActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ResponseComputerToolCallActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ResponseComputerToolCallActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
      - Actions ComputerActionList
        
        Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.
        
        type ComputerActionClick struct{…}
        
        A click action.
        
        Button string
        
        Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
        
        const ComputerActionClickButtonLeft ComputerActionClickButton = "left"
        
        const ComputerActionClickButtonRight ComputerActionClickButton = "right"
        
        const ComputerActionClickButtonWheel ComputerActionClickButton = "wheel"
        
        const ComputerActionClickButtonBack ComputerActionClickButton = "back"
        
        const ComputerActionClickButtonForward ComputerActionClickButton = "forward"
        
        Type Click
        
        Specifies the event type. For a click action, this property is always click.
        
        const ClickClick Click = "click"
        
        X int64
        
        The x-coordinate where the click occurred.
        
        Y int64
        
        The y-coordinate where the click occurred.
        
        Keys []string
        
        The keys being held while clicking.
        
        type ComputerActionDoubleClick struct{…}
        
        A double click action.
        
        Keys []string
        
        The keys being held while double-clicking.
        
        Type DoubleClick
        
        Specifies the event type. For a double click action, this property is always set to double_click.
        
        const DoubleClickDoubleClick DoubleClick = "double_click"
        
        X int64
        
        The x-coordinate where the double click occurred.
        
        Y int64
        
        The y-coordinate where the double click occurred.
        
        type ComputerActionDrag struct{…}
        
        A drag action.
        
        Path []ComputerActionDragPath
        
        An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
        
        [ { x: 100, y: 200 }, { x: 200, y: 300 } ]
        
        X int64
        
        The x-coordinate.
        
        Y int64
        
        The y-coordinate.
        
        Type Drag
        
        Specifies the event type. For a drag action, this property is always set to drag.
        
        const DragDrag Drag = "drag"
        
        Keys []string
        
        The keys being held while dragging the mouse.
        
        type ComputerActionKeypress struct{…}
        
        A collection of keypresses the model would like to perform.
        
        Keys []string
        
        The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
        
        Type Keypress
        
        Specifies the event type. For a keypress action, this property is always set to keypress.
        
        const KeypressKeypress Keypress = "keypress"
        
        type ComputerActionMove struct{…}
        
        A mouse move action.
        
        Type Move
        
        Specifies the event type. For a move action, this property is always set to move.
        
        const MoveMove Move = "move"
        
        X int64
        
        The x-coordinate to move to.
        
        Y int64
        
        The y-coordinate to move to.
        
        Keys []string
        
        The keys being held while moving the mouse.
        
        type ComputerActionScreenshot struct{…}
        
        A screenshot action.
        
        Type Screenshot
        
        Specifies the event type. For a screenshot action, this property is always set to screenshot.
        
        const ScreenshotScreenshot Screenshot = "screenshot"
        
        type ComputerActionScroll struct{…}
        
        A scroll action.
        
        ScrollX int64
        
        The horizontal scroll distance.
        
        ScrollY int64
        
        The vertical scroll distance.
        
        Type Scroll
        
        Specifies the event type. For a scroll action, this property is always set to scroll.
        
        const ScrollScroll Scroll = "scroll"
        
        X int64
        
        The x-coordinate where the scroll occurred.
        
        Y int64
        
        The y-coordinate where the scroll occurred.
        
        Keys []string
        
        The keys being held while scrolling.
        
        type ComputerActionType struct{…}
        
        An action to type in text.
        
        Text string
        
        The text to type.
        
        Type Type
        
        Specifies the event type. For a type action, this property is always set to type.
        
        const TypeType Type = "type"
        
        type ComputerActionWait struct{…}
        
        A wait action.
        
        Type Wait
        
        Specifies the event type. For a wait action, this property is always set to wait.
        
        const WaitWait Wait = "wait"
    - type ResponseInputItemComputerCallOutput struct{…}
      
      The output of a computer tool call.
      - CallID string
        
        The ID of the computer tool call that produced the output.
      - Output ResponseComputerToolCallOutputScreenshot
        
        A computer screenshot image used with the computer use tool.
        
        Type ComputerScreenshot
        
        Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.
        
        const ComputerScreenshotComputerScreenshot ComputerScreenshot = "computer_screenshot"
        
        FileID string
        
        The identifier of an uploaded file that contains the screenshot.
        
        ImageURL string
        
        The URL of the screenshot image.
      - Type ComputerCallOutput
        
        The type of the computer tool call output. Always computer_call_output.
        
        const ComputerCallOutputComputerCallOutput ComputerCallOutput = "computer_call_output"
      - ID string
        
        The ID of the computer tool call output.
      - AcknowledgedSafetyChecks []ResponseInputItemComputerCallOutputAcknowledgedSafetyCheck
        
        The safety checks reported by the API that have been acknowledged by the developer.
        
        ID string
        
        The ID of the pending safety check.
        
        Code string
        
        The type of the pending safety check.
        
        Message string
        
        Details about the pending safety check.
      - Status string
        
        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
        
        const ResponseInputItemComputerCallOutputStatusInProgress ResponseInputItemComputerCallOutputStatus = "in_progress"
        
        const ResponseInputItemComputerCallOutputStatusCompleted ResponseInputItemComputerCallOutputStatus = "completed"
        
        const ResponseInputItemComputerCallOutputStatusIncomplete ResponseInputItemComputerCallOutputStatus = "incomplete"
    - type ResponseFunctionWebSearch struct{…}
      
      The results of a web search tool call. See the web search guide for more information.
      - ID string
        
        The unique ID of the web search tool call.
      - Action ResponseFunctionWebSearchActionUnion
        
        An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
        
        type ResponseFunctionWebSearchActionSearch struct{…}
        
        Action type "search" - Performs a web search query.
        
        Type Search
        
        The action type.
        
        const SearchSearch Search = "search"
        
        Queries []string
        
        The search queries.
        
        Query string
        
        The search query.
        
        Sources []ResponseFunctionWebSearchActionSearchSource
        
        The sources used in the search.
        
        Type URL
        
        The type of source. Always url.
        
        const URLURL URL = "url"
        
        URL string
        
        The URL of the source.
        
        type ResponseFunctionWebSearchActionOpenPage struct{…}
        
        Action type "open_page" - Opens a specific URL from search results.
        
        Type OpenPage
        
        The action type.
        
        const OpenPageOpenPage OpenPage = "open_page"
        
        URL string
        
        The URL opened by the model.
        
        type ResponseFunctionWebSearchActionFindInPage struct{…}
        
        Action type "find_in_page": Searches for a pattern within a loaded page.
        
        Pattern string
        
        The pattern or text to search for within the page.
        
        Type FindInPage
        
        The action type.
        
        const FindInPageFindInPage FindInPage = "find_in_page"
        
        URL string
        
        The URL of the page searched for the pattern.
      - Status ResponseFunctionWebSearchStatus
        
        The status of the web search tool call.
        
        const ResponseFunctionWebSearchStatusInProgress ResponseFunctionWebSearchStatus = "in_progress"
        
        const ResponseFunctionWebSearchStatusSearching ResponseFunctionWebSearchStatus = "searching"
        
        const ResponseFunctionWebSearchStatusCompleted ResponseFunctionWebSearchStatus = "completed"
        
        const ResponseFunctionWebSearchStatusFailed ResponseFunctionWebSearchStatus = "failed"
      - Type WebSearchCall
        
        The type of the web search tool call. Always web_search_call.
        
        const WebSearchCallWebSearchCall WebSearchCall = "web_search_call"
    - type ResponseFunctionToolCall struct{…}
      
      A tool call to run a function. See the function calling guide for more information.
      - Arguments string
        
        A JSON string of the arguments to pass to the function.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Name string
        
        The name of the function to run.
      - Type FunctionCall
        
        The type of the function tool call. Always function_call.
        
        const FunctionCallFunctionCall FunctionCall = "function_call"
      - ID string
        
        The unique ID of the function tool call.
      - Namespace string
        
        The namespace of the function to run.
      - Status ResponseFunctionToolCallStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseFunctionToolCallStatusInProgress ResponseFunctionToolCallStatus = "in_progress"
        
        const ResponseFunctionToolCallStatusCompleted ResponseFunctionToolCallStatus = "completed"
        
        const ResponseFunctionToolCallStatusIncomplete ResponseFunctionToolCallStatus = "incomplete"
    - type ResponseInputItemFunctionCallOutput struct{…}
      
      The output of a function tool call.
      - CallID string
        
        The unique ID of the function tool call generated by the model.
      - Output ResponseInputItemFunctionCallOutputOutputUnion
        
        Text, image, or file output of the function tool call.
        
        string
        
        type ResponseFunctionCallOutputItemList []ResponseFunctionCallOutputItemUnion
        
        An array of content outputs (text, image, file) for the function tool call.
        
        type ResponseInputTextContent struct{…}
        
        A text input to the model.
        
        Text string
        
        The text input to the model.
        
        Type InputText
        
        The type of the input item. Always input_text.
        
        const InputTextInputText InputText = "input_text"
        
        type ResponseInputImageContent struct{…}
        
        An image input to the model. Learn about image inputs
        
        Type InputImage
        
        The type of the input item. Always input_image.
        
        const InputImageInputImage InputImage = "input_image"
        
        Detail ResponseInputImageContentDetail
        
        The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
        
        const ResponseInputImageContentDetailLow ResponseInputImageContentDetail = "low"
        
        const ResponseInputImageContentDetailHigh ResponseInputImageContentDetail = "high"
        
        const ResponseInputImageContentDetailAuto ResponseInputImageContentDetail = "auto"
        
        const ResponseInputImageContentDetailOriginal ResponseInputImageContentDetail = "original"
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        ImageURL string
        
        The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
        
        type ResponseInputFileContent struct{…}
        
        A file input to the model.
        
        Type InputFile
        
        The type of the input item. Always input_file.
        
        const InputFileInputFile InputFile = "input_file"
        
        Detail ResponseInputFileContentDetail
        
        The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.
        
        const ResponseInputFileContentDetailLow ResponseInputFileContentDetail = "low"
        
        const ResponseInputFileContentDetailHigh ResponseInputFileContentDetail = "high"
        
        FileData string
        
        The base64-encoded data of the file to be sent to the model.
        
        FileID string
        
        The ID of the file to be sent to the model.
        
        FileURL string
        
        The URL of the file to be sent to the model.
        
        Filename string
        
        The name of the file to be sent to the model.
      - Type FunctionCallOutput
        
        The type of the function tool call output. Always function_call_output.
        
        const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"
      - ID string
        
        The unique ID of the function tool call output. Populated when this item is returned via API.
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseInputItemFunctionCallOutputStatusInProgress ResponseInputItemFunctionCallOutputStatus = "in_progress"
        
        const ResponseInputItemFunctionCallOutputStatusCompleted ResponseInputItemFunctionCallOutputStatus = "completed"
        
        const ResponseInputItemFunctionCallOutputStatusIncomplete ResponseInputItemFunctionCallOutputStatus = "incomplete"
    - type ResponseInputItemToolSearchCall struct{…}
      - Arguments any
        
        The arguments supplied to the tool search call.
      - Type ToolSearchCall
        
        The item type. Always tool_search_call.
        
        const ToolSearchCallToolSearchCall ToolSearchCall = "tool_search_call"
      - ID string
        
        The unique ID of this tool search call.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution string
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseInputItemToolSearchCallExecutionServer ResponseInputItemToolSearchCallExecution = "server"
        
        const ResponseInputItemToolSearchCallExecutionClient ResponseInputItemToolSearchCallExecution = "client"
      - Status string
        
        The status of the tool search call.
        
        const ResponseInputItemToolSearchCallStatusInProgress ResponseInputItemToolSearchCallStatus = "in_progress"
        
        const ResponseInputItemToolSearchCallStatusCompleted ResponseInputItemToolSearchCallStatus = "completed"
        
        const ResponseInputItemToolSearchCallStatusIncomplete ResponseInputItemToolSearchCallStatus = "incomplete"
    - type ResponseToolSearchOutputItemParamResp struct{…}
      - Tools []ToolUnion
        
        The loaded tool definitions returned by the tool search output.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        Name string
        
        The name of the function to call.
        
        Parameters map[string, any]
        
        A JSON schema object describing the parameters of the function.
        
        Strict bool
        
        Whether to enforce strict parameter validation. Default true.
        
        Type Function
        
        The type of the function tool. Always function.
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function is deferred and loaded via tool search.
        
        Description string
        
        A description of the function. Used by the model to determine whether or not to call the function.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        Type FileSearch
        
        The type of the file search tool. Always file_search.
        
        const FileSearchFileSearch FileSearch = "file_search"
        
        VectorStoreIDs []string
        
        The IDs of the vector stores to search.
        
        Filters FileSearchToolFiltersUnion
        
        A filter to apply.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Key string
        
        The key to compare against the value.
        
        Type ComparisonFilterType
        
        Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
        
        eq: equals
        
        ne: not equal
        
        gt: greater than
        
        gte: greater than or equal
        
        lt: less than
        
        lte: less than or equal
        
        in: in
        
        nin: not in
        
        const ComparisonFilterTypeEq ComparisonFilterType = "eq"
        
        const ComparisonFilterTypeNe ComparisonFilterType = "ne"
        
        const ComparisonFilterTypeGt ComparisonFilterType = "gt"
        
        const ComparisonFilterTypeGte ComparisonFilterType = "gte"
        
        const ComparisonFilterTypeLt ComparisonFilterType = "lt"
        
        const ComparisonFilterTypeLte ComparisonFilterType = "lte"
        
        const ComparisonFilterTypeIn ComparisonFilterType = "in"
        
        const ComparisonFilterTypeNin ComparisonFilterType = "nin"
        
        Value ComparisonFilterValueUnion
        
        The value to compare against the attribute key; supports string, number, or boolean types.
        
        string
        
        float64
        
        bool
        
        type ComparisonFilterValueArray []ComparisonFilterValueArrayItemUnion
        
        string
        
        float64
        
        type CompoundFilter struct{…}
        
        Combine multiple filters using and or or.
        
        Filters []ComparisonFilter
        
        Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
        
        type ComparisonFilter struct{…}
        
        A filter used to compare a specified attribute key to a given value using a defined comparison operation.
        
        Type CompoundFilterType
        
        Type of operation: and or or.
        
        const CompoundFilterTypeAnd CompoundFilterType = "and"
        
        const CompoundFilterTypeOr CompoundFilterType = "or"
        
        MaxNumResults int64
        
        The maximum number of results to return. This number should be between 1 and 50 inclusive.
        
        RankingOptions FileSearchToolRankingOptions
        
        Ranking options for search.
        
        HybridSearch FileSearchToolRankingOptionsHybridSearch
        
        Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
        
        EmbeddingWeight float64
        
        The weight of the embedding in the reciprocal ranking fusion.
        
        TextWeight float64
        
        The weight of the text in the reciprocal ranking fusion.
        
        Ranker string
        
        The ranker to use for the file search.
        
        const FileSearchToolRankingOptionsRankerAuto FileSearchToolRankingOptionsRanker = "auto"
        
        const FileSearchToolRankingOptionsRankerDefault2024_11_15 FileSearchToolRankingOptionsRanker = "default-2024-11-15"
        
        ScoreThreshold float64
        
        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        Type Computer
        
        The type of the computer tool. Always computer.
        
        const ComputerComputer Computer = "computer"
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        DisplayHeight int64
        
        The height of the computer display.
        
        DisplayWidth int64
        
        The width of the computer display.
        
        Environment ComputerUsePreviewToolEnvironment
        
        The type of computer environment to control.
        
        const ComputerUsePreviewToolEnvironmentWindows ComputerUsePreviewToolEnvironment = "windows"
        
        const ComputerUsePreviewToolEnvironmentMac ComputerUsePreviewToolEnvironment = "mac"
        
        const ComputerUsePreviewToolEnvironmentLinux ComputerUsePreviewToolEnvironment = "linux"
        
        const ComputerUsePreviewToolEnvironmentUbuntu ComputerUsePreviewToolEnvironment = "ubuntu"
        
        const ComputerUsePreviewToolEnvironmentBrowser ComputerUsePreviewToolEnvironment = "browser"
        
        Type ComputerUsePreview
        
        The type of the computer use tool. Always computer_use_preview.
        
        const ComputerUsePreviewComputerUsePreview ComputerUsePreview = "computer_use_preview"
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        Type WebSearchToolType
        
        The type of the web search tool. One of web_search or web_search_2025_08_26.
        
        const WebSearchToolTypeWebSearch WebSearchToolType = "web_search"
        
        const WebSearchToolTypeWebSearch2025_08_26 WebSearchToolType = "web_search_2025_08_26"
        
        Filters WebSearchToolFilters
        
        Filters for the search.
        
        AllowedDomains []string
        
        Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
        
        Example: ["pubmed.ncbi.nlm.nih.gov"]
        
        SearchContextSize WebSearchToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchToolSearchContextSizeLow WebSearchToolSearchContextSize = "low"
        
        const WebSearchToolSearchContextSizeMedium WebSearchToolSearchContextSize = "medium"
        
        const WebSearchToolSearchContextSizeHigh WebSearchToolSearchContextSize = "high"
        
        UserLocation WebSearchToolUserLocation
        
        The approximate location of the user.
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        Type string
        
        The type of location approximation. Always approximate.
        
        const WebSearchToolUserLocationTypeApproximate WebSearchToolUserLocationType = "approximate"
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        ServerLabel string
        
        A label for this MCP server, used to identify it in tool calls.
        
        Type Mcp
        
        The type of the MCP tool. Always mcp.
        
        const McpMcp Mcp = "mcp"
        
        AllowedTools ToolMcpAllowedToolsUnion
        
        List of allowed tool names or a filter object.
        
        type ToolMcpAllowedToolsMcpAllowedTools []string
        
        A string array of allowed tool names
        
        type ToolMcpAllowedToolsMcpToolFilter struct{…}
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Authorization string
        
        An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
        
        ConnectorID string
        
        Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.
        
        Currently supported connector_id values are:
        
        Dropbox: connector_dropbox
        
        Gmail: connector_gmail
        
        Google Calendar: connector_googlecalendar
        
        Google Drive: connector_googledrive
        
        Microsoft Teams: connector_microsoftteams
        
        Outlook Calendar: connector_outlookcalendar
        
        Outlook Email: connector_outlookemail
        
        SharePoint: connector_sharepoint
        
        const ToolMcpConnectorIDConnectorDropbox ToolMcpConnectorID = "connector_dropbox"
        
        const ToolMcpConnectorIDConnectorGmail ToolMcpConnectorID = "connector_gmail"
        
        const ToolMcpConnectorIDConnectorGooglecalendar ToolMcpConnectorID = "connector_googlecalendar"
        
        const ToolMcpConnectorIDConnectorGoogledrive ToolMcpConnectorID = "connector_googledrive"
        
        const ToolMcpConnectorIDConnectorMicrosoftteams ToolMcpConnectorID = "connector_microsoftteams"
        
        const ToolMcpConnectorIDConnectorOutlookcalendar ToolMcpConnectorID = "connector_outlookcalendar"
        
        const ToolMcpConnectorIDConnectorOutlookemail ToolMcpConnectorID = "connector_outlookemail"
        
        const ToolMcpConnectorIDConnectorSharepoint ToolMcpConnectorID = "connector_sharepoint"
        
        DeferLoading bool
        
        Whether this MCP tool is deferred and discovered via tool search.
        
        Headers map[string, string]
        
        Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
        
        RequireApproval ToolMcpRequireApprovalUnion
        
        Specify which of the MCP server's tools require approval.
        
        type ToolMcpRequireApprovalMcpToolApprovalFilter struct{…}
        
        Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.
        
        Always ToolMcpRequireApprovalMcpToolApprovalFilterAlways
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        Never ToolMcpRequireApprovalMcpToolApprovalFilterNever
        
        A filter object to specify which tools are allowed.
        
        ReadOnly bool
        
        Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.
        
        ToolNames []string
        
        List of allowed tool names.
        
        type ToolMcpRequireApprovalMcpToolApprovalSetting string
        
        Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingAlways ToolMcpRequireApprovalMcpToolApprovalSetting = "always"
        
        const ToolMcpRequireApprovalMcpToolApprovalSettingNever ToolMcpRequireApprovalMcpToolApprovalSetting = "never"
        
        ServerDescription string
        
        Optional description of the MCP server, used to provide more context.
        
        ServerURL string
        
        The URL for the MCP server. One of server_url, connector_id, or tunnel_id must be provided.
        
        TunnelID string
        
        The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        Container ToolCodeInterpreterContainerUnion
        
        The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.
        
        string
        
        type ToolCodeInterpreterContainerCodeInterpreterContainerAuto struct{…}
        
        Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
        
        Type Auto
        
        Always auto.
        
        const AutoAuto Auto = "auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit string
        
        The memory limit for the code interpreter container.
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit1g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "1g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit4g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "4g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit16g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "16g"
        
        const ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit64g ToolCodeInterpreterContainerCodeInterpreterToolAutoMemoryLimit = "64g"
        
        NetworkPolicy ToolCodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        Type Disabled
        
        Disable outbound network access. Always disabled.
        
        const DisabledDisabled Disabled = "disabled"
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        AllowedDomains []string
        
        A list of allowed domains when type is allowlist.
        
        Type Allowlist
        
        Allow outbound network access only to specified domains. Always allowlist.
        
        const AllowlistAllowlist Allowlist = "allowlist"
        
        DomainSecrets []ContainerNetworkPolicyDomainSecret
        
        Optional domain-scoped secrets for allowlisted domains.
        
        Domain string
        
        The domain associated with the secret.
        
        Name string
        
        The name of the secret to inject for the domain.
        
        Value string
        
        The secret value to inject for the domain.
        
        Type CodeInterpreter
        
        The type of the code interpreter tool. Always code_interpreter.
        
        const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        Type ImageGeneration
        
        The type of the image generation tool. Always image_generation.
        
        const ImageGenerationImageGeneration ImageGeneration = "image_generation"
        
        Action string
        
        Whether to generate a new image or edit an existing image. Default: auto.
        
        const ToolImageGenerationActionGenerate ToolImageGenerationAction = "generate"
        
        const ToolImageGenerationActionEdit ToolImageGenerationAction = "edit"
        
        const ToolImageGenerationActionAuto ToolImageGenerationAction = "auto"
        
        Background string
        
        Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
        
        gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
        
        If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
        
        const ToolImageGenerationBackgroundTransparent ToolImageGenerationBackground = "transparent"
        
        const ToolImageGenerationBackgroundOpaque ToolImageGenerationBackground = "opaque"
        
        const ToolImageGenerationBackgroundAuto ToolImageGenerationBackground = "auto"
        
        InputFidelity string
        
        Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
        
        const ToolImageGenerationInputFidelityHigh ToolImageGenerationInputFidelity = "high"
        
        const ToolImageGenerationInputFidelityLow ToolImageGenerationInputFidelity = "low"
        
        InputImageMask ToolImageGenerationInputImageMask
        
        Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
        
        FileID string
        
        File ID for the mask image.
        
        ImageURL string
        
        Base64-encoded mask image.
        
        Model string
        
        The image generation model to use. Default: gpt-image-1.
        
        string
        
        string
        
        const ToolImageGenerationModelGPTImage1 ToolImageGenerationModel = "gpt-image-1"
        
        const ToolImageGenerationModelGPTImage1Mini ToolImageGenerationModel = "gpt-image-1-mini"
        
        const ToolImageGenerationModelGPTImage2 ToolImageGenerationModel = "gpt-image-2"
        
        const ToolImageGenerationModelGPTImage2_2026_04_21 ToolImageGenerationModel = "gpt-image-2-2026-04-21"
        
        const ToolImageGenerationModelGPTImage1_5 ToolImageGenerationModel = "gpt-image-1.5"
        
        const ToolImageGenerationModelChatgptImageLatest ToolImageGenerationModel = "chatgpt-image-latest"
        
        Moderation string
        
        Moderation level for the generated image. Default: auto.
        
        const ToolImageGenerationModerationAuto ToolImageGenerationModeration = "auto"
        
        const ToolImageGenerationModerationLow ToolImageGenerationModeration = "low"
        
        OutputCompression int64
        
        Compression level for the output image. Default: 100.
        
        OutputFormat string
        
        The output format of the generated image. One of png, webp, or jpeg. Default: png.
        
        const ToolImageGenerationOutputFormatPNG ToolImageGenerationOutputFormat = "png"
        
        const ToolImageGenerationOutputFormatWebP ToolImageGenerationOutputFormat = "webp"
        
        const ToolImageGenerationOutputFormatJPEG ToolImageGenerationOutputFormat = "jpeg"
        
        PartialImages int64
        
        Number of partial images to generate in streaming mode, from 0 (default value) to 3.
        
        Quality string
        
        The quality of the generated image. One of low, medium, high, or auto. Default: auto.
        
        const ToolImageGenerationQualityLow ToolImageGenerationQuality = "low"
        
        const ToolImageGenerationQualityMedium ToolImageGenerationQuality = "medium"
        
        const ToolImageGenerationQualityHigh ToolImageGenerationQuality = "high"
        
        const ToolImageGenerationQualityAuto ToolImageGenerationQuality = "auto"
        
        Size string
        
        The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
        
        string
        
        string
        
        const ToolImageGenerationSize1024x1024 ToolImageGenerationSize = "1024x1024"
        
        const ToolImageGenerationSize1024x1536 ToolImageGenerationSize = "1024x1536"
        
        const ToolImageGenerationSize1536x1024 ToolImageGenerationSize = "1536x1024"
        
        const ToolImageGenerationSizeAuto ToolImageGenerationSize = "auto"
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        Type LocalShell
        
        The type of the local shell tool. Always local_shell.
        
        const LocalShellLocalShell LocalShell = "local_shell"
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        Type Shell
        
        The type of the shell tool. Always shell.
        
        const ShellShell Shell = "shell"
        
        Environment FunctionShellToolEnvironmentUnion
        
        type ContainerAuto struct{…}
        
        Type ContainerAuto
        
        Automatically creates a container for this request
        
        const ContainerAutoContainerAuto ContainerAuto = "container_auto"
        
        FileIDs []string
        
        An optional list of uploaded files to make available to your code.
        
        MemoryLimit ContainerAutoMemoryLimit
        
        The memory limit for the container.
        
        const ContainerAutoMemoryLimit1g ContainerAutoMemoryLimit = "1g"
        
        const ContainerAutoMemoryLimit4g ContainerAutoMemoryLimit = "4g"
        
        const ContainerAutoMemoryLimit16g ContainerAutoMemoryLimit = "16g"
        
        const ContainerAutoMemoryLimit64g ContainerAutoMemoryLimit = "64g"
        
        NetworkPolicy ContainerAutoNetworkPolicyUnion
        
        Network access policy for the container.
        
        type ContainerNetworkPolicyDisabled struct{…}
        
        type ContainerNetworkPolicyAllowlist struct{…}
        
        Skills []ContainerAutoSkillUnion
        
        An optional list of skills referenced by id or inline data.
        
        type SkillReference struct{…}
        
        SkillID string
        
        The ID of the referenced skill.
        
        Type SkillReference
        
        References a skill created with the /v1/skills endpoint.
        
        const SkillReferenceSkillReference SkillReference = "skill_reference"
        
        Version string
        
        Optional skill version. Use a positive integer or 'latest'. Omit for default.
        
        type InlineSkill struct{…}
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Source InlineSkillSource
        
        Inline skill payload
        
        Data string
        
        Base64-encoded skill zip bundle.
        
        MediaType ApplicationZip
        
        The media type of the inline skill payload. Must be application/zip.
        
        const ApplicationZipApplicationZip ApplicationZip = "application/zip"
        
        Type Base64
        
        The type of the inline skill source. Must be base64.
        
        const Base64Base64 Base64 = "base64"
        
        Type Inline
        
        Defines an inline skill for this request.
        
        const InlineInline Inline = "inline"
        
        type LocalEnvironment struct{…}
        
        Type Local
        
        Use a local computer environment.
        
        const LocalLocal Local = "local"
        
        Skills []LocalSkill
        
        An optional list of skills.
        
        Description string
        
        The description of the skill.
        
        Name string
        
        The name of the skill.
        
        Path string
        
        The path to the directory containing the skill.
        
        type ContainerReference struct{…}
        
        ContainerID string
        
        The ID of the referenced container.
        
        Type ContainerReference
        
        References a container created with the /v1/containers endpoint
        
        const ContainerReferenceContainerReference ContainerReference = "container_reference"
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Name string
        
        The name of the custom tool, used to identify it in tool calls.
        
        Type Custom
        
        The type of the custom tool. Always custom.
        
        const CustomCustom Custom = "custom"
        
        DeferLoading bool
        
        Whether this tool should be deferred and discovered via tool search.
        
        Description string
        
        Optional description of the custom tool, used to provide more context.
        
        Format CustomToolInputFormatUnion
        
        The input format for the custom tool. Default is unconstrained text.
        
        type CustomToolInputFormatText struct{…}
        
        Unconstrained free-form text.
        
        Type Text
        
        Unconstrained text format. Always text.
        
        const TextText Text = "text"
        
        type CustomToolInputFormatGrammar struct{…}
        
        A grammar defined by the user.
        
        Definition string
        
        The grammar definition.
        
        Syntax string
        
        The syntax of the grammar definition. One of lark or regex.
        
        const CustomToolInputFormatGrammarSyntaxLark CustomToolInputFormatGrammarSyntax = "lark"
        
        const CustomToolInputFormatGrammarSyntaxRegex CustomToolInputFormatGrammarSyntax = "regex"
        
        Type Grammar
        
        Grammar format. Always grammar.
        
        const GrammarGrammar Grammar = "grammar"
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        Description string
        
        A description of the namespace shown to the model.
        
        Name string
        
        The namespace name used in tool calls (for example, crm).
        
        Tools []NamespaceToolToolUnion
        
        The function/custom tools available inside this namespace.
        
        type NamespaceToolToolFunction struct{…}
        
        Name string
        
        Type Function
        
        const FunctionFunction Function = "function"
        
        DeferLoading bool
        
        Whether this function should be deferred and discovered via tool search.
        
        Description string
        
        Parameters any
        
        Strict bool
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        Type Namespace
        
        The type of the tool. Always namespace.
        
        const NamespaceNamespace Namespace = "namespace"
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        Type ToolSearch
        
        The type of the tool. Always tool_search.
        
        const ToolSearchToolSearch ToolSearch = "tool_search"
        
        Description string
        
        Description shown to the model for a client-executed tool search tool.
        
        Execution ToolSearchToolExecution
        
        Whether tool search is executed by the server or by the client.
        
        const ToolSearchToolExecutionServer ToolSearchToolExecution = "server"
        
        const ToolSearchToolExecutionClient ToolSearchToolExecution = "client"
        
        Parameters any
        
        Parameter schema for a client-executed tool search tool.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        Type WebSearchPreviewToolType
        
        The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
        
        const WebSearchPreviewToolTypeWebSearchPreview WebSearchPreviewToolType = "web_search_preview"
        
        const WebSearchPreviewToolTypeWebSearchPreview2025_03_11 WebSearchPreviewToolType = "web_search_preview_2025_03_11"
        
        SearchContentTypes []string
        
        const WebSearchPreviewToolSearchContentTypeText WebSearchPreviewToolSearchContentType = "text"
        
        const WebSearchPreviewToolSearchContentTypeImage WebSearchPreviewToolSearchContentType = "image"
        
        SearchContextSize WebSearchPreviewToolSearchContextSize
        
        High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
        
        const WebSearchPreviewToolSearchContextSizeLow WebSearchPreviewToolSearchContextSize = "low"
        
        const WebSearchPreviewToolSearchContextSizeMedium WebSearchPreviewToolSearchContextSize = "medium"
        
        const WebSearchPreviewToolSearchContextSizeHigh WebSearchPreviewToolSearchContextSize = "high"
        
        UserLocation WebSearchPreviewToolUserLocation
        
        The user's location.
        
        Type Approximate
        
        The type of location approximation. Always approximate.
        
        const ApproximateApproximate Approximate = "approximate"
        
        City string
        
        Free text input for the city of the user, e.g. San Francisco.
        
        Country string
        
        The two-letter ISO country code of the user, e.g. US.
        
        Region string
        
        Free text input for the region of the user, e.g. California.
        
        Timezone string
        
        The IANA timezone of the user, e.g. America/Los_Angeles.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
        
        Type ApplyPatch
        
        The type of the tool. Always apply_patch.
        
        const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
      - Type ToolSearchOutput
        
        The item type. Always tool_search_output.
        
        const ToolSearchOutputToolSearchOutput ToolSearchOutput = "tool_search_output"
      - ID string
        
        The unique ID of this tool search output.
      - CallID string
        
        The unique ID of the tool search call generated by the model.
      - Execution ResponseToolSearchOutputItemParamExecution
        
        Whether tool search was executed by the server or by the client.
        
        const ResponseToolSearchOutputItemParamExecutionServer ResponseToolSearchOutputItemParamExecution = "server"
        
        const ResponseToolSearchOutputItemParamExecutionClient ResponseToolSearchOutputItemParamExecution = "client"
      - Status ResponseToolSearchOutputItemParamStatus
        
        The status of the tool search output.
        
        const ResponseToolSearchOutputItemParamStatusInProgress ResponseToolSearchOutputItemParamStatus = "in_progress"
        
        const ResponseToolSearchOutputItemParamStatusCompleted ResponseToolSearchOutputItemParamStatus = "completed"
        
        const ResponseToolSearchOutputItemParamStatusIncomplete ResponseToolSearchOutputItemParamStatus = "incomplete"
    - type ResponseInputItemAdditionalTools struct{…}
      - Role Developer
        
        The role that provided the additional tools. Only developer is supported.
        
        const DeveloperDeveloper Developer = "developer"
      - Tools []ToolUnion
        
        A list of additional tools made available at this item.
        
        type FunctionTool struct{…}
        
        Defines a function in your own code the model can choose to call. Learn more about function calling.
        
        type FileSearchTool struct{…}
        
        A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
        
        type ComputerTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type ComputerUsePreviewTool struct{…}
        
        A tool that controls a virtual computer. Learn more about the computer tool.
        
        type WebSearchTool struct{…}
        
        Search the Internet for sources related to the prompt. Learn more about the web search tool.
        
        type ToolMcp struct{…}
        
        Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
        
        type ToolCodeInterpreter struct{…}
        
        A tool that runs Python code to help generate a response to a prompt.
        
        type ToolImageGeneration struct{…}
        
        A tool that generates images using the GPT image models.
        
        type ToolLocalShell struct{…}
        
        A tool that allows the model to execute shell commands in a local environment.
        
        type FunctionShellTool struct{…}
        
        A tool that allows the model to execute shell commands.
        
        type CustomTool struct{…}
        
        A custom tool that processes input using a specified format. Learn more about custom tools
        
        type NamespaceTool struct{…}
        
        Groups function/custom tools under a shared namespace.
        
        type ToolSearchTool struct{…}
        
        Hosted or BYOT tool search configuration for deferred tools.
        
        type WebSearchPreviewTool struct{…}
        
        This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
        
        type ApplyPatchTool struct{…}
        
        Allows the assistant to create, delete, or update files using unified diffs.
      - Type AdditionalTools
        
        The item type. Always additional_tools.
        
        const AdditionalToolsAdditionalTools AdditionalTools = "additional_tools"
      - ID string
        
        The unique ID of this additional tools item.
    - type ResponseReasoningItem struct{…}
      
      A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.
      - ID string
        
        The unique identifier of the reasoning content.
      - Summary []ResponseReasoningItemSummary
        
        Reasoning summary content.
        
        Text string
        
        A summary of the reasoning output from the model so far.
        
        Type SummaryText
        
        The type of the object. Always summary_text.
        
        const SummaryTextSummaryText SummaryText = "summary_text"
      - Type Reasoning
        
        The type of the object. Always reasoning.
        
        const ReasoningReasoning Reasoning = "reasoning"
      - Content []ResponseReasoningItemContent
        
        Reasoning text content.
        
        Text string
        
        The reasoning text from the model.
        
        Type ReasoningText
        
        The type of the reasoning text. Always reasoning_text.
        
        const ReasoningTextReasoningText ReasoningText = "reasoning_text"
      - EncryptedContent string
        
        The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
      - Status ResponseReasoningItemStatus
        
        The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
        
        const ResponseReasoningItemStatusInProgress ResponseReasoningItemStatus = "in_progress"
        
        const ResponseReasoningItemStatusCompleted ResponseReasoningItemStatus = "completed"
        
        const ResponseReasoningItemStatusIncomplete ResponseReasoningItemStatus = "incomplete"
    - type ResponseCompactionItemParamResp struct{…}
      
      A compaction item generated by the v1/responses/compact API.
      - EncryptedContent string
        
        The encrypted content of the compaction summary.
      - Type Compaction
        
        The type of the item. Always compaction.
        
        const CompactionCompaction Compaction = "compaction"
      - ID string
        
        The ID of the compaction item.
    - type ResponseInputItemImageGenerationCall struct{…}
      
      An image generation request made by the model.
      - ID string
        
        The unique ID of the image generation call.
      - Result string
        
        The generated image encoded in base64.
      - Status string
        
        The status of the image generation call.
        
        const ResponseInputItemImageGenerationCallStatusInProgress ResponseInputItemImageGenerationCallStatus = "in_progress"
        
        const ResponseInputItemImageGenerationCallStatusCompleted ResponseInputItemImageGenerationCallStatus = "completed"
        
        const ResponseInputItemImageGenerationCallStatusGenerating ResponseInputItemImageGenerationCallStatus = "generating"
        
        const ResponseInputItemImageGenerationCallStatusFailed ResponseInputItemImageGenerationCallStatus = "failed"
      - Type ImageGenerationCall
        
        The type of the image generation call. Always image_generation_call.
        
        const ImageGenerationCallImageGenerationCall ImageGenerationCall = "image_generation_call"
    - type ResponseCodeInterpreterToolCall struct{…}
      
      A tool call to run code.
      - ID string
        
        The unique ID of the code interpreter tool call.
      - Code string
        
        The code to run, or null if not available.
      - ContainerID string
        
        The ID of the container used to run the code.
      - Outputs []ResponseCodeInterpreterToolCallOutputUnion
        
        The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
        
        type ResponseCodeInterpreterToolCallOutputLogs struct{…}
        
        The logs output from the code interpreter.
        
        Logs string
        
        The logs output from the code interpreter.
        
        Type Logs
        
        The type of the output. Always logs.
        
        const LogsLogs Logs = "logs"
        
        type ResponseCodeInterpreterToolCallOutputImage struct{…}
        
        The image output from the code interpreter.
        
        Type Image
        
        The type of the output. Always image.
        
        const ImageImage Image = "image"
        
        URL string
        
        The URL of the image output from the code interpreter.
      - Status ResponseCodeInterpreterToolCallStatus
        
        The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
        
        const ResponseCodeInterpreterToolCallStatusInProgress ResponseCodeInterpreterToolCallStatus = "in_progress"
        
        const ResponseCodeInterpreterToolCallStatusCompleted ResponseCodeInterpreterToolCallStatus = "completed"
        
        const ResponseCodeInterpreterToolCallStatusIncomplete ResponseCodeInterpreterToolCallStatus = "incomplete"
        
        const ResponseCodeInterpreterToolCallStatusInterpreting ResponseCodeInterpreterToolCallStatus = "interpreting"
        
        const ResponseCodeInterpreterToolCallStatusFailed ResponseCodeInterpreterToolCallStatus = "failed"
      - Type CodeInterpreterCall
        
        The type of the code interpreter tool call. Always code_interpreter_call.
        
        const CodeInterpreterCallCodeInterpreterCall CodeInterpreterCall = "code_interpreter_call"
    - type ResponseInputItemLocalShellCall struct{…}
      
      A tool call to run a command on the local shell.
      - ID string
        
        The unique ID of the local shell call.
      - Action ResponseInputItemLocalShellCallAction
        
        Execute a shell command on the server.
        
        Command []string
        
        The command to run.
        
        Env map[string, string]
        
        Environment variables to set for the command.
        
        Type Exec
        
        The type of the local shell action. Always exec.
        
        const ExecExec Exec = "exec"
        
        TimeoutMs int64
        
        Optional timeout in milliseconds for the command.
        
        User string
        
        Optional user to run the command as.
        
        WorkingDirectory string
        
        Optional working directory to run the command in.
      - CallID string
        
        The unique ID of the local shell tool call generated by the model.
      - Status string
        
        The status of the local shell call.
        
        const ResponseInputItemLocalShellCallStatusInProgress ResponseInputItemLocalShellCallStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallStatusCompleted ResponseInputItemLocalShellCallStatus = "completed"
        
        const ResponseInputItemLocalShellCallStatusIncomplete ResponseInputItemLocalShellCallStatus = "incomplete"
      - Type LocalShellCall
        
        The type of the local shell call. Always local_shell_call.
        
        const LocalShellCallLocalShellCall LocalShellCall = "local_shell_call"
    - type ResponseInputItemLocalShellCallOutput struct{…}
      
      The output of a local shell tool call.
      - ID string
        
        The unique ID of the local shell tool call generated by the model.
      - Output string
        
        A JSON string of the output of the local shell tool call.
      - Type LocalShellCallOutput
        
        The type of the local shell tool call output. Always local_shell_call_output.
        
        const LocalShellCallOutputLocalShellCallOutput LocalShellCallOutput = "local_shell_call_output"
      - Status string
        
        The status of the item. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemLocalShellCallOutputStatusInProgress ResponseInputItemLocalShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemLocalShellCallOutputStatusCompleted ResponseInputItemLocalShellCallOutputStatus = "completed"
        
        const ResponseInputItemLocalShellCallOutputStatusIncomplete ResponseInputItemLocalShellCallOutputStatus = "incomplete"
    - type ResponseInputItemShellCall struct{…}
      
      A tool representing a request to execute one or more shell commands.
      - Action ResponseInputItemShellCallAction
        
        The shell commands and limits that describe how to run the tool call.
        
        Commands []string
        
        Ordered shell commands for the execution environment to run.
        
        MaxOutputLength int64
        
        Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
        
        TimeoutMs int64
        
        Maximum wall-clock time in milliseconds to allow the shell commands to run.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Type ShellCall
        
        The type of the item. Always shell_call.
        
        const ShellCallShellCall ShellCall = "shell_call"
      - ID string
        
        The unique ID of the shell tool call. Populated when this item is returned via API.
      - Environment ResponseInputItemShellCallEnvironmentUnion
        
        The environment to execute the shell commands in.
        
        type LocalEnvironment struct{…}
        
        type ContainerReference struct{…}
      - Status string
        
        The status of the shell call. One of in_progress, completed, or incomplete.
        
        const ResponseInputItemShellCallStatusInProgress ResponseInputItemShellCallStatus = "in_progress"
        
        const ResponseInputItemShellCallStatusCompleted ResponseInputItemShellCallStatus = "completed"
        
        const ResponseInputItemShellCallStatusIncomplete ResponseInputItemShellCallStatus = "incomplete"
    - type ResponseInputItemShellCallOutput struct{…}
      
      The streamed output items emitted by a shell tool call.
      - CallID string
        
        The unique ID of the shell tool call generated by the model.
      - Output []ResponseFunctionShellCallOutputContent
        
        Captured chunks of stdout and stderr output, along with their associated outcomes.
        
        Outcome ResponseFunctionShellCallOutputContentOutcomeUnion
        
        The exit or timeout outcome associated with this shell call.
        
        type ResponseFunctionShellCallOutputContentOutcomeTimeout struct{…}
        
        Indicates that the shell call exceeded its configured time limit.
        
        Type Timeout
        
        The outcome type. Always timeout.
        
        const TimeoutTimeout Timeout = "timeout"
        
        type ResponseFunctionShellCallOutputContentOutcomeExit struct{…}
        
        Indicates that the shell commands finished and returned an exit code.
        
        ExitCode int64
        
        The exit code returned by the shell process.
        
        Type Exit
        
        The outcome type. Always exit.
        
        const ExitExit Exit = "exit"
        
        Stderr string
        
        Captured stderr output for the shell call.
        
        Stdout string
        
        Captured stdout output for the shell call.
      - Type ShellCallOutput
        
        The type of the item. Always shell_call_output.
        
        const ShellCallOutputShellCallOutput ShellCallOutput = "shell_call_output"
      - ID string
        
        The unique ID of the shell tool call output. Populated when this item is returned via API.
      - MaxOutputLength int64
        
        The maximum number of UTF-8 characters captured for this shell call's combined output.
      - Status string
        
        The status of the shell call output.
        
        const ResponseInputItemShellCallOutputStatusInProgress ResponseInputItemShellCallOutputStatus = "in_progress"
        
        const ResponseInputItemShellCallOutputStatusCompleted ResponseInputItemShellCallOutputStatus = "completed"
        
        const ResponseInputItemShellCallOutputStatusIncomplete ResponseInputItemShellCallOutputStatus = "incomplete"
    - type ResponseInputItemApplyPatchCall struct{…}
      
      A tool call representing a request to create, delete, or update files using diff patches.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Operation ResponseInputItemApplyPatchCallOperationUnion
        
        The specific create, delete, or update instruction for the apply_patch tool call.
        
        type ResponseInputItemApplyPatchCallOperationCreateFile struct{…}
        
        Instruction for creating a new file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply when creating the file.
        
        Path string
        
        Path of the file to create relative to the workspace root.
        
        Type CreateFile
        
        The operation type. Always create_file.
        
        const CreateFileCreateFile CreateFile = "create_file"
        
        type ResponseInputItemApplyPatchCallOperationDeleteFile struct{…}
        
        Instruction for deleting an existing file via the apply_patch tool.
        
        Path string
        
        Path of the file to delete relative to the workspace root.
        
        Type DeleteFile
        
        The operation type. Always delete_file.
        
        const DeleteFileDeleteFile DeleteFile = "delete_file"
        
        type ResponseInputItemApplyPatchCallOperationUpdateFile struct{…}
        
        Instruction for updating an existing file via the apply_patch tool.
        
        Diff string
        
        Unified diff content to apply to the existing file.
        
        Path string
        
        Path of the file to update relative to the workspace root.
        
        Type UpdateFile
        
        The operation type. Always update_file.
        
        const UpdateFileUpdateFile UpdateFile = "update_file"
      - Status string
        
        The status of the apply patch tool call. One of in_progress or completed.
        
        const ResponseInputItemApplyPatchCallStatusInProgress ResponseInputItemApplyPatchCallStatus = "in_progress"
        
        const ResponseInputItemApplyPatchCallStatusCompleted ResponseInputItemApplyPatchCallStatus = "completed"
      - Type ApplyPatchCall
        
        The type of the item. Always apply_patch_call.
        
        const ApplyPatchCallApplyPatchCall ApplyPatchCall = "apply_patch_call"
      - ID string
        
        The unique ID of the apply patch tool call. Populated when this item is returned via API.
    - type ResponseInputItemApplyPatchCallOutput struct{…}
      
      The streamed output emitted by an apply patch tool call.
      - CallID string
        
        The unique ID of the apply patch tool call generated by the model.
      - Status string
        
        The status of the apply patch tool call output. One of completed or failed.
        
        const ResponseInputItemApplyPatchCallOutputStatusCompleted ResponseInputItemApplyPatchCallOutputStatus = "completed"
        
        const ResponseInputItemApplyPatchCallOutputStatusFailed ResponseInputItemApplyPatchCallOutputStatus = "failed"
      - Type ApplyPatchCallOutput
        
        The type of the item. Always apply_patch_call_output.
        
        const ApplyPatchCallOutputApplyPatchCallOutput ApplyPatchCallOutput = "apply_patch_call_output"
      - ID string
        
        The unique ID of the apply patch tool call output. Populated when this item is returned via API.
      - Output string
        
        Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
    - type ResponseInputItemMcpListTools struct{…}
      
      A list of tools available on an MCP server.
      - ID string
        
        The unique ID of the list.
      - ServerLabel string
        
        The label of the MCP server.
      - Tools []ResponseInputItemMcpListToolsTool
        
        The tools available on the server.
        
        InputSchema any
        
        The JSON schema describing the tool's input.
        
        Name string
        
        The name of the tool.
        
        Annotations any
        
        Additional annotations about the tool.
        
        Description string
        
        The description of the tool.
      - Type McpListTools
        
        The type of the item. Always mcp_list_tools.
        
        const McpListToolsMcpListTools McpListTools = "mcp_list_tools"
      - Error string
        
        Error message if the server could not list tools.
    - type ResponseInputItemMcpApprovalRequest struct{…}
      
      A request for human approval of a tool invocation.
      - ID string
        
        The unique ID of the approval request.
      - Arguments string
        
        A JSON string of arguments for the tool.
      - Name string
        
        The name of the tool to run.
      - ServerLabel string
        
        The label of the MCP server making the request.
      - Type McpApprovalRequest
        
        The type of the item. Always mcp_approval_request.
        
        const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"
    - type ResponseInputItemMcpApprovalResponse struct{…}
      
      A response to an MCP approval request.
      - ApprovalRequestID string
        
        The ID of the approval request being answered.
      - Approve bool
        
        Whether the request was approved.
      - Type McpApprovalResponse
        
        The type of the item. Always mcp_approval_response.
        
        const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"
      - ID string
        
        The unique ID of the approval response
      - Reason string
        
        Optional reason for the decision.
    - type ResponseInputItemMcpCall struct{…}
      
      An invocation of a tool on an MCP server.
      - ID string
        
        The unique ID of the tool call.
      - Arguments string
        
        A JSON string of the arguments passed to the tool.
      - Name string
        
        The name of the tool that was run.
      - ServerLabel string
        
        The label of the MCP server running the tool.
      - Type McpCall
        
        The type of the item. Always mcp_call.
        
        const McpCallMcpCall McpCall = "mcp_call"
      - ApprovalRequestID string
        
        Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
      - Error string
        
        The error from the tool call, if any.
      - Output string
        
        The output from the tool call.
      - Status string
        
        The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
        
        const ResponseInputItemMcpCallStatusInProgress ResponseInputItemMcpCallStatus = "in_progress"
        
        const ResponseInputItemMcpCallStatusCompleted ResponseInputItemMcpCallStatus = "completed"
        
        const ResponseInputItemMcpCallStatusIncomplete ResponseInputItemMcpCallStatus = "incomplete"
        
        const ResponseInputItemMcpCallStatusCalling ResponseInputItemMcpCallStatus = "calling"
        
        const ResponseInputItemMcpCallStatusFailed ResponseInputItemMcpCallStatus = "failed"
    - type ResponseCustomToolCallOutput struct{…}
      
      The output of a custom tool call from your code, being sent back to the model.
      - CallID string
        
        The call ID, used to map this custom tool call output to a custom tool call.
      - Output ResponseCustomToolCallOutputOutputUnion
        
        The output from the custom tool call generated by your code. Can be a string or an list of output content.
        
        string
        
        type ResponseCustomToolCallOutputOutputOutputContentList []ResponseCustomToolCallOutputOutputOutputContentListItemUnion
        
        Text, image, or file output of the custom tool call.
        
        type ResponseInputText struct{…}
        
        A text input to the model.
        
        type ResponseInputImage struct{…}
        
        An image input to the model. Learn about image inputs.
        
        type ResponseInputFile struct{…}
        
        A file input to the model.
      - Type CustomToolCallOutput
        
        The type of the custom tool call output. Always custom_tool_call_output.
        
        const CustomToolCallOutputCustomToolCallOutput CustomToolCallOutput = "custom_tool_call_output"
      - ID string
        
        The unique ID of the custom tool call output in the OpenAI platform.
    - type ResponseCustomToolCall struct{…}
      
      A call to a custom tool created by the model.
      - CallID string
        
        An identifier used to map this custom tool call to a tool call output.
      - Input string
        
        The input for the custom tool call generated by the model.
      - Name string
        
        The name of the custom tool being called.
      - Type CustomToolCall
        
        The type of the custom tool call. Always custom_tool_call.
        
        const CustomToolCallCustomToolCall CustomToolCall = "custom_tool_call"
      - ID string
        
        The unique ID of the custom tool call in the OpenAI platform.
      - Namespace string
        
        The namespace of the custom tool being called.
    - type ResponseInputItemCompactionTrigger struct{…}
      
      Compacts the current context. Must be the final input item.
      - Type CompactionTrigger
        
        The type of the item. Always compaction_trigger.
        
        const CompactionTriggerCompactionTrigger CompactionTrigger = "compaction_trigger"
    - type ResponseInputItemItemReference struct{…}
      
      An internal identifier for an item to reference.
      - ID string
        
        The ID of the item to reference.
      - Type string
        
        The type of item to reference. Always item_reference.
        
        const ResponseInputItemItemReferenceTypeItemReference ResponseInputItemItemReferenceType = "item_reference"
- Instructions param.Field[string]
  
  A system (or developer) message inserted into the model's context. When used along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
- Model param.Field[string]
  
  Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
- ParallelToolCalls param.Field[bool]
  
  Whether to allow the model to run tool calls in parallel.
- Personality param.Field[InputTokenCountParamsPersonality]
  
  A model-owned style preset to apply to this request. Omit this parameter to use the model's default style. Supported values may expand over time. Values must be at most 64 characters.
  - string
  - type InputTokenCountParamsPersonality string
    
    A model-owned style preset to apply to this request. Omit this parameter to use the model's default style. Supported values may expand over time. Values must be at most 64 characters.
    - const InputTokenCountParamsPersonalityFriendly InputTokenCountParamsPersonality = "friendly"
    - const InputTokenCountParamsPersonalityPragmatic InputTokenCountParamsPersonality = "pragmatic"
- PreviousResponseID param.Field[string]
  
  The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
- Reasoning param.Field[Reasoning]
  
  gpt-5 and o-series models only Configuration options for reasoning models.
- Text param.Field[InputTokenCountParamsText]
  
  Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
  - Text inputs and outputs
  - Structured Outputs
  - Format ResponseFormatTextConfigUnion
    
    An object specifying the format that the model must output.
    
    Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
    
    The default format is { "type": "text" } with no additional options.
    
    Not recommended for gpt-4o and newer models:
    
    Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
    - type ResponseFormatText struct{…}
      
      Default response format. Used to generate text responses.
      - Type Text
        
        The type of response format being defined. Always text.
        
        const TextText Text = "text"
    - type ResponseFormatTextJSONSchemaConfig struct{…}
      
      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
      - Name string
        
        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
      - Schema map[string, any]
        
        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
      - Type JSONSchema
        
        The type of response format being defined. Always json_schema.
        
        const JSONSchemaJSONSchema JSONSchema = "json_schema"
      - Description string
        
        A description of what the response format is for, used by the model to determine how to respond in the format.
      - Strict bool
        
        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.
    - type ResponseFormatJSONObject struct{…}
      
      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
      - Type JSONObject
        
        The type of response format being defined. Always json_object.
        
        const JSONObjectJSONObject JSONObject = "json_object"
  - Verbosity string
    
    Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
    - const InputTokenCountParamsTextVerbosityLow InputTokenCountParamsTextVerbosity = "low"
    - const InputTokenCountParamsTextVerbosityMedium InputTokenCountParamsTextVerbosity = "medium"
    - const InputTokenCountParamsTextVerbosityHigh InputTokenCountParamsTextVerbosity = "high"
- ToolChoice param.Field[InputTokenCountParamsToolChoiceUnion]
  
  Controls which tool the model should use, if any.
  - type ToolChoiceOptions string
    
    Controls which (if any) tool is called by the model.
    
    none means the model will not call any tool and instead generates a message.
    
    auto means the model can pick between generating a message or calling one or more tools.
    
    required means the model must call one or more tools.
    - const ToolChoiceOptionsNone ToolChoiceOptions = "none"
    - const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
    - const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
  - type ToolChoiceAllowed struct{…}
    
    Constrains the tools available to the model to a pre-defined set.
    - Mode ToolChoiceAllowedMode
      
      Constrains the tools available to the model to a pre-defined set.
      
      auto allows the model to pick from among the allowed tools and generate a message.
      
      required requires the model to call one or more of the allowed tools.
      - const ToolChoiceAllowedModeAuto ToolChoiceAllowedMode = "auto"
      - const ToolChoiceAllowedModeRequired ToolChoiceAllowedMode = "required"
    - Tools []map[string, any]
      
      A list of tool definitions that the model should be allowed to call.
      
      For the Responses API, the list of tool definitions might look like:
```
[
  { "type": "function", "name": "get_weather" },
  { "type": "mcp", "server_label": "deepwiki" },
  { "type": "image_generation" }
]
```
    - Type AllowedTools
      
      Allowed tool configuration type. Always allowed_tools.
      - const AllowedToolsAllowedTools AllowedTools = "allowed_tools"
  - type ToolChoiceTypes struct{…}
    
    Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
    - Type ToolChoiceTypesType
      
      The type of hosted tool the model should to use. Learn more about built-in tools.
      
      Allowed values are:
      - file_search
      - web_search_preview
      - computer
      - computer_use_preview
      - computer_use
      - code_interpreter
      - image_generation
      - const ToolChoiceTypesTypeFileSearch ToolChoiceTypesType = "file_search"
      - const ToolChoiceTypesTypeWebSearchPreview ToolChoiceTypesType = "web_search_preview"
      - const ToolChoiceTypesTypeComputer ToolChoiceTypesType = "computer"
      - const ToolChoiceTypesTypeComputerUsePreview ToolChoiceTypesType = "computer_use_preview"
      - const ToolChoiceTypesTypeComputerUse ToolChoiceTypesType = "computer_use"
      - const ToolChoiceTypesTypeWebSearchPreview2025_03_11 ToolChoiceTypesType = "web_search_preview_2025_03_11"
      - const ToolChoiceTypesTypeImageGeneration ToolChoiceTypesType = "image_generation"
      - const ToolChoiceTypesTypeCodeInterpreter ToolChoiceTypesType = "code_interpreter"
  - type ToolChoiceFunction struct{…}
    
    Use this option to force the model to call a specific function.
    - Name string
      
      The name of the function to call.
    - Type Function
      
      For function calling, the type is always function.
      - const FunctionFunction Function = "function"
  - type ToolChoiceMcp struct{…}
    
    Use this option to force the model to call a specific tool on a remote MCP server.
    - ServerLabel string
      
      The label of the MCP server to use.
    - Type Mcp
      
      For MCP tools, the type is always mcp.
      - const McpMcp Mcp = "mcp"
    - Name string
      
      The name of the tool to call on the server.
  - type ToolChoiceCustom struct{…}
    
    Use this option to force the model to call a specific custom tool.
    - Name string
      
      The name of the custom tool to call.
    - Type Custom
      
      For custom tool calling, the type is always custom.
      - const CustomCustom Custom = "custom"
  - type ToolChoiceApplyPatch struct{…}
    
    Forces the model to call the apply_patch tool when executing a tool call.
    - Type ApplyPatch
      
      The tool to call. Always apply_patch.
      - const ApplyPatchApplyPatch ApplyPatch = "apply_patch"
  - type ToolChoiceShell struct{…}
    
    Forces the model to call the shell tool when a tool call is required.
    - Type Shell
      
      The tool to call. Always shell.
      - const ShellShell Shell = "shell"
- Tools param.Field[[]ToolUnion]
  
  An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.
  - type FunctionTool struct{…}
    
    Defines a function in your own code the model can choose to call. Learn more about function calling.
  - type FileSearchTool struct{…}
    
    A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
  - type ComputerTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
  - type ComputerUsePreviewTool struct{…}
    
    A tool that controls a virtual computer. Learn more about the computer tool.
  - type WebSearchTool struct{…}
    
    Search the Internet for sources related to the prompt. Learn more about the web search tool.
  - type ToolMcp struct{…}
    
    Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
  - type ToolCodeInterpreter struct{…}
    
    A tool that runs Python code to help generate a response to a prompt.
  - type ToolImageGeneration struct{…}
    
    A tool that generates images using the GPT image models.
  - type ToolLocalShell struct{…}
    
    A tool that allows the model to execute shell commands in a local environment.
  - type FunctionShellTool struct{…}
    
    A tool that allows the model to execute shell commands.
  - type CustomTool struct{…}
    
    A custom tool that processes input using a specified format. Learn more about custom tools
  - type NamespaceTool struct{…}
    
    Groups function/custom tools under a shared namespace.
  - type ToolSearchTool struct{…}
    
    Hosted or BYOT tool search configuration for deferred tools.
  - type WebSearchPreviewTool struct{…}
    
    This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
  - type ApplyPatchTool struct{…}
    
    Allows the assistant to create, delete, or update files using unified diffs.
- Truncation param.Field[InputTokenCountParamsTruncation]
  
  The truncation strategy to use for the model response. - auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. - disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.
  - const InputTokenCountParamsTruncationAuto InputTokenCountParamsTruncation = "auto"
  - const InputTokenCountParamsTruncationDisabled InputTokenCountParamsTruncation = "disabled"

Returns

type InputTokenCountResponse struct{…}
- InputTokens int64
- Object ResponseInputTokens
  - const ResponseInputTokensResponseInputTokens ResponseInputTokens = "response.input_tokens"

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
  "github.com/openai/openai-go/responses"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  response, err := client.Responses.InputTokens.Count(context.TODO(), responses.InputTokenCountParams{

  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", response.InputTokens)
}

Response

{
  "input_tokens": 123,
  "object": "response.input_tokens"
}

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/responses"
)

func main() {
  client := openai.NewClient()
  response, err := client.Responses.InputTokens.Count(context.TODO(), responses.InputTokenCountParams{
    Model: "gpt-5",
    Input: "Tell me a joke.",
  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", response.InputTokens)
}

Response

{
  "object": "response.input_tokens",
  "input_tokens": 11
}

go/resources/responses/index.md +261 −116

1618 - `ConnectorID string`1618 - `ConnectorID string`

1619 1619

1620 Identifier for service connectors, like those available in ChatGPT. One of1620 Identifier for service connectors, like those available in ChatGPT. One of

1621 `server_url` or `connector_id` must be provided. Learn more about service1621 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

1622 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).1622 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

1623 1623

1624 Currently supported `connector_id` values are:1624 Currently supported `connector_id` values are:

1625 1625

1711 1711

1712 - `ServerURL string`1712 - `ServerURL string`

1713 1713

1714 The URL for the MCP server. One of `server_url` or `connector_id` must be1714 The URL for the MCP server. One of `server_url`, `connector_id`, or

1715 provided.1715 `tunnel_id` must be provided.

1716

1717 - `TunnelID string`

1718

1719 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

1720 `server_url`, `connector_id`, or `tunnel_id` must be provided.

1716 1721

1717 - `type ToolCodeInterpreter struct{…}`1722 - `type ToolCodeInterpreter struct{…}`

1718 1723

5159 - `ConnectorID string`5164 - `ConnectorID string`

5160 5165

5161 Identifier for service connectors, like those available in ChatGPT. One of5166 Identifier for service connectors, like those available in ChatGPT. One of

5162 `server_url` or `connector_id` must be provided. Learn more about service5167 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

5163 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).5168 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

5164 5169

5165 Currently supported `connector_id` values are:5170 Currently supported `connector_id` values are:

5166 5171

5252 5257

5253 - `ServerURL string`5258 - `ServerURL string`

5254 5259

5255 The URL for the MCP server. One of `server_url` or `connector_id` must be5260 The URL for the MCP server. One of `server_url`, `connector_id`, or

5256 provided.5261 `tunnel_id` must be provided.

5262

5263 - `TunnelID string`

5264

5265 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

5266 `server_url`, `connector_id`, or `tunnel_id` must be provided.

5257 5267

5258 - `type ToolCodeInterpreter struct{…}`5268 - `type ToolCodeInterpreter struct{…}`

5259 5269

10441 - `ConnectorID string`10451 - `ConnectorID string`

10442 10452

10443 Identifier for service connectors, like those available in ChatGPT. One of10453 Identifier for service connectors, like those available in ChatGPT. One of

10444 `server_url` or `connector_id` must be provided. Learn more about service10454 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

10445 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).10455 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

10446 10456

10447 Currently supported `connector_id` values are:10457 Currently supported `connector_id` values are:

10448 10458

10534 10544

10535 - `ServerURL string`10545 - `ServerURL string`

10536 10546

10537 The URL for the MCP server. One of `server_url` or `connector_id` must be10547 The URL for the MCP server. One of `server_url`, `connector_id`, or

10538 provided.10548 `tunnel_id` must be provided.

10549

10550 - `TunnelID string`

10551

10552 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

10553 `server_url`, `connector_id`, or `tunnel_id` must be provided.

10539 10554

10540 - `type ToolCodeInterpreter struct{…}`10555 - `type ToolCodeInterpreter struct{…}`

10541 10556

15725 - `ConnectorID string`15740 - `ConnectorID string`

15726 15741

15727 Identifier for service connectors, like those available in ChatGPT. One of15742 Identifier for service connectors, like those available in ChatGPT. One of

15728 `server_url` or `connector_id` must be provided. Learn more about service15743 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

15729 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).15744 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

15730 15745

15731 Currently supported `connector_id` values are:15746 Currently supported `connector_id` values are:

15732 15747

15818 15833

15819 - `ServerURL string`15834 - `ServerURL string`

15820 15835

15821 The URL for the MCP server. One of `server_url` or `connector_id` must be15836 The URL for the MCP server. One of `server_url`, `connector_id`, or

15822 provided.15837 `tunnel_id` must be provided.

15838

15839 - `TunnelID string`

15840

15841 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

15842 `server_url`, `connector_id`, or `tunnel_id` must be provided.

15823 15843

15824 - `type ToolCodeInterpreter struct{…}`15844 - `type ToolCodeInterpreter struct{…}`

15825 15845

21084 - `ConnectorID string`21104 - `ConnectorID string`

21085 21105

21086 Identifier for service connectors, like those available in ChatGPT. One of21106 Identifier for service connectors, like those available in ChatGPT. One of

21087 `server_url` or `connector_id` must be provided. Learn more about service21107 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

21088 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).21108 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

21089 21109

21090 Currently supported `connector_id` values are:21110 Currently supported `connector_id` values are:

21091 21111

21177 21197

21178 - `ServerURL string`21198 - `ServerURL string`

21179 21199

21180 The URL for the MCP server. One of `server_url` or `connector_id` must be21200 The URL for the MCP server. One of `server_url`, `connector_id`, or

21181 provided.21201 `tunnel_id` must be provided.

21202

21203 - `TunnelID string`

21204

21205 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

21206 `server_url`, `connector_id`, or `tunnel_id` must be provided.

21182 21207

21183 - `type ToolCodeInterpreter struct{…}`21208 - `type ToolCodeInterpreter struct{…}`

21184 21209

24109 - `ConnectorID string`24134 - `ConnectorID string`

24110 24135

24111 Identifier for service connectors, like those available in ChatGPT. One of24136 Identifier for service connectors, like those available in ChatGPT. One of

24112 `server_url` or `connector_id` must be provided. Learn more about service24137 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

24113 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).24138 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

24114 24139

24115 Currently supported `connector_id` values are:24140 Currently supported `connector_id` values are:

24116 24141

24202 24227

24203 - `ServerURL string`24228 - `ServerURL string`

24204 24229

24205 The URL for the MCP server. One of `server_url` or `connector_id` must be24230 The URL for the MCP server. One of `server_url`, `connector_id`, or

24206 provided.24231 `tunnel_id` must be provided.

24232

24233 - `TunnelID string`

24234

24235 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

24236 `server_url`, `connector_id`, or `tunnel_id` must be provided.

24207 24237

24208 - `type ToolCodeInterpreter struct{…}`24238 - `type ToolCodeInterpreter struct{…}`

24209 24239

27167 - `ConnectorID string`27197 - `ConnectorID string`

27168 27198

27169 Identifier for service connectors, like those available in ChatGPT. One of27199 Identifier for service connectors, like those available in ChatGPT. One of

27170 `server_url` or `connector_id` must be provided. Learn more about service27200 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

27171 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).27201 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

27172 27202

27173 Currently supported `connector_id` values are:27203 Currently supported `connector_id` values are:

27174 27204

27260 27290

27261 - `ServerURL string`27291 - `ServerURL string`

27262 27292

27263 The URL for the MCP server. One of `server_url` or `connector_id` must be27293 The URL for the MCP server. One of `server_url`, `connector_id`, or

27264 provided.27294 `tunnel_id` must be provided.

27295

27296 - `TunnelID string`

27297

27298 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

27299 `server_url`, `connector_id`, or `tunnel_id` must be provided.

27265 27300

27266 - `type ToolCodeInterpreter struct{…}`27301 - `type ToolCodeInterpreter struct{…}`

27267 27302

31601 - `ConnectorID string`31636 - `ConnectorID string`

31602 31637

31603 Identifier for service connectors, like those available in ChatGPT. One of31638 Identifier for service connectors, like those available in ChatGPT. One of

31604 `server_url` or `connector_id` must be provided. Learn more about service31639 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

31605 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).31640 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

31606 31641

31607 Currently supported `connector_id` values are:31642 Currently supported `connector_id` values are:

31608 31643

31694 31729

31695 - `ServerURL string`31730 - `ServerURL string`

31696 31731

31697 The URL for the MCP server. One of `server_url` or `connector_id` must be31732 The URL for the MCP server. One of `server_url`, `connector_id`, or

31698 provided.31733 `tunnel_id` must be provided.

31734

31735 - `TunnelID string`

31736

31737 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

31738 `server_url`, `connector_id`, or `tunnel_id` must be provided.

31699 31739

31700 - `type ToolCodeInterpreter struct{…}`31740 - `type ToolCodeInterpreter struct{…}`

31701 31741

37087 - `ConnectorID string`37127 - `ConnectorID string`

37088 37128

37089 Identifier for service connectors, like those available in ChatGPT. One of37129 Identifier for service connectors, like those available in ChatGPT. One of

37090 `server_url` or `connector_id` must be provided. Learn more about service37130 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

37091 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).37131 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

37092 37132

37093 Currently supported `connector_id` values are:37133 Currently supported `connector_id` values are:

37094 37134

37180 37220

37181 - `ServerURL string`37221 - `ServerURL string`

37182 37222

37183 The URL for the MCP server. One of `server_url` or `connector_id` must be37223 The URL for the MCP server. One of `server_url`, `connector_id`, or

37184 provided.37224 `tunnel_id` must be provided.

37225

37226 - `TunnelID string`

37227

37228 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

37229 `server_url`, `connector_id`, or `tunnel_id` must be provided.

37185 37230

37186 - `type ToolCodeInterpreter struct{…}`37231 - `type ToolCodeInterpreter struct{…}`

37187 37232

43321 - `ConnectorID string`43366 - `ConnectorID string`

43322 43367

43323 Identifier for service connectors, like those available in ChatGPT. One of43368 Identifier for service connectors, like those available in ChatGPT. One of

43324 `server_url` or `connector_id` must be provided. Learn more about service43369 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

43325 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).43370 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

43326 43371

43327 Currently supported `connector_id` values are:43372 Currently supported `connector_id` values are:

43328 43373

43414 43459

43415 - `ServerURL string`43460 - `ServerURL string`

43416 43461

43417 The URL for the MCP server. One of `server_url` or `connector_id` must be43462 The URL for the MCP server. One of `server_url`, `connector_id`, or

43418 provided.43463 `tunnel_id` must be provided.

43464

43465 - `TunnelID string`

43466

43467 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

43468 `server_url`, `connector_id`, or `tunnel_id` must be provided.

43419 43469

43420 - `type ToolCodeInterpreter struct{…}`43470 - `type ToolCodeInterpreter struct{…}`

43421 43471

48705 - `ConnectorID string`48755 - `ConnectorID string`

48706 48756

48707 Identifier for service connectors, like those available in ChatGPT. One of48757 Identifier for service connectors, like those available in ChatGPT. One of

48708 `server_url` or `connector_id` must be provided. Learn more about service48758 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

48709 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).48759 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

48710 48760

48711 Currently supported `connector_id` values are:48761 Currently supported `connector_id` values are:

48712 48762

48798 48848

48799 - `ServerURL string`48849 - `ServerURL string`

48800 48850

48801 The URL for the MCP server. One of `server_url` or `connector_id` must be48851 The URL for the MCP server. One of `server_url`, `connector_id`, or

48802 provided.48852 `tunnel_id` must be provided.

48853

48854 - `TunnelID string`

48855

48856 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

48857 `server_url`, `connector_id`, or `tunnel_id` must be provided.

48803 48858

48804 - `type ToolCodeInterpreter struct{…}`48859 - `type ToolCodeInterpreter struct{…}`

48805 48860

54835 - `ConnectorID string`54890 - `ConnectorID string`

54836 54891

54837 Identifier for service connectors, like those available in ChatGPT. One of54892 Identifier for service connectors, like those available in ChatGPT. One of

54838 `server_url` or `connector_id` must be provided. Learn more about service54893 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

54839 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).54894 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

54840 54895

54841 Currently supported `connector_id` values are:54896 Currently supported `connector_id` values are:

54842 54897

54928 54983

54929 - `ServerURL string`54984 - `ServerURL string`

54930 54985

54931 The URL for the MCP server. One of `server_url` or `connector_id` must be54986 The URL for the MCP server. One of `server_url`, `connector_id`, or

54932 provided.54987 `tunnel_id` must be provided.

54988

54989 - `TunnelID string`

54990

54991 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

54992 `server_url`, `connector_id`, or `tunnel_id` must be provided.

54933 54993

54934 - `type ToolCodeInterpreter struct{…}`54994 - `type ToolCodeInterpreter struct{…}`

54935 54995

59925 - `ConnectorID string`59985 - `ConnectorID string`

59926 59986

59927 Identifier for service connectors, like those available in ChatGPT. One of59987 Identifier for service connectors, like those available in ChatGPT. One of

59928 `server_url` or `connector_id` must be provided. Learn more about service59988 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

59929 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).59989 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

59930 59990

59931 Currently supported `connector_id` values are:59991 Currently supported `connector_id` values are:

59932 59992

60018 60078

60019 - `ServerURL string`60079 - `ServerURL string`

60020 60080

60021 The URL for the MCP server. One of `server_url` or `connector_id` must be60081 The URL for the MCP server. One of `server_url`, `connector_id`, or

60022 provided.60082 `tunnel_id` must be provided.

60083

60084 - `TunnelID string`

60085

60086 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

60087 `server_url`, `connector_id`, or `tunnel_id` must be provided.

60023 60088

60024 - `type ToolCodeInterpreter struct{…}`60089 - `type ToolCodeInterpreter struct{…}`

60025 60090

64898 - `ConnectorID string`64963 - `ConnectorID string`

64899 64964

64900 Identifier for service connectors, like those available in ChatGPT. One of64965 Identifier for service connectors, like those available in ChatGPT. One of

64901 `server_url` or `connector_id` must be provided. Learn more about service64966 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

64902 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).64967 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

64903 64968

64904 Currently supported `connector_id` values are:64969 Currently supported `connector_id` values are:

64905 64970

64991 65056

64992 - `ServerURL string`65057 - `ServerURL string`

64993 65058

64994 The URL for the MCP server. One of `server_url` or `connector_id` must be65059 The URL for the MCP server. One of `server_url`, `connector_id`, or

64995 provided.65060 `tunnel_id` must be provided.

65061

65062 - `TunnelID string`

65063

65064 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

65065 `server_url`, `connector_id`, or `tunnel_id` must be provided.

64996 65066

64997 - `type ToolCodeInterpreter struct{…}`65067 - `type ToolCodeInterpreter struct{…}`

64998 65068

68189 - `ConnectorID string`68259 - `ConnectorID string`

68190 68260

68191 Identifier for service connectors, like those available in ChatGPT. One of68261 Identifier for service connectors, like those available in ChatGPT. One of

68192 `server_url` or `connector_id` must be provided. Learn more about service68262 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

68193 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).68263 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

68194 68264

68195 Currently supported `connector_id` values are:68265 Currently supported `connector_id` values are:

68196 68266

68282 68352

68283 - `ServerURL string`68353 - `ServerURL string`

68284 68354

68285 The URL for the MCP server. One of `server_url` or `connector_id` must be68355 The URL for the MCP server. One of `server_url`, `connector_id`, or

68286 provided.68356 `tunnel_id` must be provided.

68357

68358 - `TunnelID string`

68359

68360 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

68361 `server_url`, `connector_id`, or `tunnel_id` must be provided.

68287 68362

68288 - `type ToolCodeInterpreter struct{…}`68363 - `type ToolCodeInterpreter struct{…}`

68289 68364

71371 - `ConnectorID string`71446 - `ConnectorID string`

71372 71447

71373 Identifier for service connectors, like those available in ChatGPT. One of71448 Identifier for service connectors, like those available in ChatGPT. One of

71374 `server_url` or `connector_id` must be provided. Learn more about service71449 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

71375 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).71450 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

71376 71451

71377 Currently supported `connector_id` values are:71452 Currently supported `connector_id` values are:

71378 71453

71464 71539

71465 - `ServerURL string`71540 - `ServerURL string`

71466 71541

71467 The URL for the MCP server. One of `server_url` or `connector_id` must be71542 The URL for the MCP server. One of `server_url`, `connector_id`, or

71468 provided.71543 `tunnel_id` must be provided.

71544

71545 - `TunnelID string`

71546

71547 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

71548 `server_url`, `connector_id`, or `tunnel_id` must be provided.

71469 71549

71470 - `type ToolCodeInterpreter struct{…}`71550 - `type ToolCodeInterpreter struct{…}`

71471 71551

74562 - `ConnectorID string`74642 - `ConnectorID string`

74563 74643

74564 Identifier for service connectors, like those available in ChatGPT. One of74644 Identifier for service connectors, like those available in ChatGPT. One of

74565 `server_url` or `connector_id` must be provided. Learn more about service74645 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

74566 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).74646 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

74567 74647

74568 Currently supported `connector_id` values are:74648 Currently supported `connector_id` values are:

74569 74649

74655 74735

74656 - `ServerURL string`74736 - `ServerURL string`

74657 74737

74658 The URL for the MCP server. One of `server_url` or `connector_id` must be74738 The URL for the MCP server. One of `server_url`, `connector_id`, or

74659 provided.74739 `tunnel_id` must be provided.

74740

74741 - `TunnelID string`

74742

74743 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

74744 `server_url`, `connector_id`, or `tunnel_id` must be provided.

74660 74745

74661 - `type ToolCodeInterpreter struct{…}`74746 - `type ToolCodeInterpreter struct{…}`

74662 74747

77471 - `ConnectorID string`77556 - `ConnectorID string`

77472 77557

77473 Identifier for service connectors, like those available in ChatGPT. One of77558 Identifier for service connectors, like those available in ChatGPT. One of

77474 `server_url` or `connector_id` must be provided. Learn more about service77559 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

77475 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).77560 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

77476 77561

77477 Currently supported `connector_id` values are:77562 Currently supported `connector_id` values are:

77478 77563

77564 77649

77565 - `ServerURL string`77650 - `ServerURL string`

77566 77651

77567 The URL for the MCP server. One of `server_url` or `connector_id` must be77652 The URL for the MCP server. One of `server_url`, `connector_id`, or

77568 provided.77653 `tunnel_id` must be provided.

77654

77655 - `TunnelID string`

77656

77657 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

77658 `server_url`, `connector_id`, or `tunnel_id` must be provided.

77569 77659

77570 - `type ToolCodeInterpreter struct{…}`77660 - `type ToolCodeInterpreter struct{…}`

77571 77661

80394 - `ConnectorID string`80484 - `ConnectorID string`

80395 80485

80396 Identifier for service connectors, like those available in ChatGPT. One of80486 Identifier for service connectors, like those available in ChatGPT. One of

80397 `server_url` or `connector_id` must be provided. Learn more about service80487 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

80398 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).80488 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

80399 80489

80400 Currently supported `connector_id` values are:80490 Currently supported `connector_id` values are:

80401 80491

80487 80577

80488 - `ServerURL string`80578 - `ServerURL string`

80489 80579

80490 The URL for the MCP server. One of `server_url` or `connector_id` must be80580 The URL for the MCP server. One of `server_url`, `connector_id`, or

80491 provided.80581 `tunnel_id` must be provided.

80582

80583 - `TunnelID string`

80584

80585 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

80586 `server_url`, `connector_id`, or `tunnel_id` must be provided.

80492 80587

80493 - `type ToolCodeInterpreter struct{…}`80588 - `type ToolCodeInterpreter struct{…}`

80494 80589

83940 - `ConnectorID string`84035 - `ConnectorID string`

83941 84036

83942 Identifier for service connectors, like those available in ChatGPT. One of84037 Identifier for service connectors, like those available in ChatGPT. One of

83943 `server_url` or `connector_id` must be provided. Learn more about service84038 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

83944 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).84039 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

83945 84040

83946 Currently supported `connector_id` values are:84041 Currently supported `connector_id` values are:

83947 84042

84033 84128

84034 - `ServerURL string`84129 - `ServerURL string`

84035 84130

84036 The URL for the MCP server. One of `server_url` or `connector_id` must be84131 The URL for the MCP server. One of `server_url`, `connector_id`, or

84037 provided.84132 `tunnel_id` must be provided.

84133

84134 - `TunnelID string`

84135

84136 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

84137 `server_url`, `connector_id`, or `tunnel_id` must be provided.

84038 84138

84039 - `type ToolCodeInterpreter struct{…}`84139 - `type ToolCodeInterpreter struct{…}`

84040 84140

89543 - `ConnectorID string`89643 - `ConnectorID string`

89544 89644

89545 Identifier for service connectors, like those available in ChatGPT. One of89645 Identifier for service connectors, like those available in ChatGPT. One of

89546 `server_url` or `connector_id` must be provided. Learn more about service89646 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

89547 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).89647 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

89548 89648

89549 Currently supported `connector_id` values are:89649 Currently supported `connector_id` values are:

89550 89650

89636 89736

89637 - `ServerURL string`89737 - `ServerURL string`

89638 89738

89639 The URL for the MCP server. One of `server_url` or `connector_id` must be89739 The URL for the MCP server. One of `server_url`, `connector_id`, or

89640 provided.89740 `tunnel_id` must be provided.

89741

89742 - `TunnelID string`

89743

89744 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

89745 `server_url`, `connector_id`, or `tunnel_id` must be provided.

89641 89746

89642 - `type ToolCodeInterpreter struct{…}`89747 - `type ToolCodeInterpreter struct{…}`

89643 89748

94859 - `ConnectorID string`94964 - `ConnectorID string`

94860 94965

94861 Identifier for service connectors, like those available in ChatGPT. One of94966 Identifier for service connectors, like those available in ChatGPT. One of

94862 `server_url` or `connector_id` must be provided. Learn more about service94967 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

94863 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).94968 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

94864 94969

94865 Currently supported `connector_id` values are:94970 Currently supported `connector_id` values are:

94866 94971

94952 95057

94953 - `ServerURL string`95058 - `ServerURL string`

94954 95059

94955 The URL for the MCP server. One of `server_url` or `connector_id` must be95060 The URL for the MCP server. One of `server_url`, `connector_id`, or

94956 provided.95061 `tunnel_id` must be provided.

95062

95063 - `TunnelID string`

95064

95065 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

95066 `server_url`, `connector_id`, or `tunnel_id` must be provided.

94957 95067

94958 - `type ToolCodeInterpreter struct{…}`95068 - `type ToolCodeInterpreter struct{…}`

94959 95069

95835 - `ConnectorID string`95945 - `ConnectorID string`

95836 95946

95837 Identifier for service connectors, like those available in ChatGPT. One of95947 Identifier for service connectors, like those available in ChatGPT. One of

95838 `server_url` or `connector_id` must be provided. Learn more about service95948 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

95839 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).95949 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

95840 95950

95841 Currently supported `connector_id` values are:95951 Currently supported `connector_id` values are:

95842 95952

95928 96038

95929 - `ServerURL string`96039 - `ServerURL string`

95930 96040

95931 The URL for the MCP server. One of `server_url` or `connector_id` must be96041 The URL for the MCP server. One of `server_url`, `connector_id`, or

95932 provided.96042 `tunnel_id` must be provided.

96043

96044 - `TunnelID string`

96045

96046 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

96047 `server_url`, `connector_id`, or `tunnel_id` must be provided.

95933 96048

95934 - `type ToolCodeInterpreter struct{…}`96049 - `type ToolCodeInterpreter struct{…}`

95935 96050

98242 - `ConnectorID string`98357 - `ConnectorID string`

98243 98358

98244 Identifier for service connectors, like those available in ChatGPT. One of98359 Identifier for service connectors, like those available in ChatGPT. One of

98245 `server_url` or `connector_id` must be provided. Learn more about service98360 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

98246 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).98361 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

98247 98362

98248 Currently supported `connector_id` values are:98363 Currently supported `connector_id` values are:

98249 98364

98335 98450

98336 - `ServerURL string`98451 - `ServerURL string`

98337 98452

98338 The URL for the MCP server. One of `server_url` or `connector_id` must be98453 The URL for the MCP server. One of `server_url`, `connector_id`, or

98339 provided.98454 `tunnel_id` must be provided.

98455

98456 - `TunnelID string`

98457

98458 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

98459 `server_url`, `connector_id`, or `tunnel_id` must be provided.

98340 98460

98341 - `type ToolCodeInterpreter struct{…}`98461 - `type ToolCodeInterpreter struct{…}`

98342 98462

102348 - `ConnectorID string`102468 - `ConnectorID string`

102349 102469

102350 Identifier for service connectors, like those available in ChatGPT. One of102470 Identifier for service connectors, like those available in ChatGPT. One of

102351 `server_url` or `connector_id` must be provided. Learn more about service102471 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

102352 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).102472 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

102353 102473

102354 Currently supported `connector_id` values are:102474 Currently supported `connector_id` values are:

102355 102475

102441 102561

102442 - `ServerURL string`102562 - `ServerURL string`

102443 102563

102444 The URL for the MCP server. One of `server_url` or `connector_id` must be102564 The URL for the MCP server. One of `server_url`, `connector_id`, or

102445 provided.102565 `tunnel_id` must be provided.

102566

102567 - `TunnelID string`

102568

102569 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

102570 `server_url`, `connector_id`, or `tunnel_id` must be provided.

102446 102571

102447 - `type ToolCodeInterpreter struct{…}`102572 - `type ToolCodeInterpreter struct{…}`

102448 102573

107403 - `ConnectorID string`107528 - `ConnectorID string`

107404 107529

107405 Identifier for service connectors, like those available in ChatGPT. One of107530 Identifier for service connectors, like those available in ChatGPT. One of

107406 `server_url` or `connector_id` must be provided. Learn more about service107531 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

107407 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).107532 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

107408 107533

107409 Currently supported `connector_id` values are:107534 Currently supported `connector_id` values are:

107410 107535

107496 107621

107497 - `ServerURL string`107622 - `ServerURL string`

107498 107623

107499 The URL for the MCP server. One of `server_url` or `connector_id` must be107624 The URL for the MCP server. One of `server_url`, `connector_id`, or

107500 provided.107625 `tunnel_id` must be provided.

107626

107627 - `TunnelID string`

107628

107629 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

107630 `server_url`, `connector_id`, or `tunnel_id` must be provided.

107501 107631

107502 - `type ToolCodeInterpreter struct{…}`107632 - `type ToolCodeInterpreter struct{…}`

107503 107633

109869 - `ConnectorID string`109999 - `ConnectorID string`

109870 110000

109871 Identifier for service connectors, like those available in ChatGPT. One of110001 Identifier for service connectors, like those available in ChatGPT. One of

109872 `server_url` or `connector_id` must be provided. Learn more about service110002 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

109873 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).110003 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

109874 110004

109875 Currently supported `connector_id` values are:110005 Currently supported `connector_id` values are:

109876 110006

109962 110092

109963 - `ServerURL string`110093 - `ServerURL string`

109964 110094

109965 The URL for the MCP server. One of `server_url` or `connector_id` must be110095 The URL for the MCP server. One of `server_url`, `connector_id`, or

109966 provided.110096 `tunnel_id` must be provided.

110097

110098 - `TunnelID string`

110099

110100 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

110101 `server_url`, `connector_id`, or `tunnel_id` must be provided.

109967 110102

109968 - `type ToolCodeInterpreter struct{…}`110103 - `type ToolCodeInterpreter struct{…}`

109969 110104

112862 - `ConnectorID string`112997 - `ConnectorID string`

112863 112998

112864 Identifier for service connectors, like those available in ChatGPT. One of112999 Identifier for service connectors, like those available in ChatGPT. One of

112865 `server_url` or `connector_id` must be provided. Learn more about service113000 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

112866 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).113001 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

112867 113002

112868 Currently supported `connector_id` values are:113003 Currently supported `connector_id` values are:

112869 113004

112955 113090

112956 - `ServerURL string`113091 - `ServerURL string`

112957 113092

112958 The URL for the MCP server. One of `server_url` or `connector_id` must be113093 The URL for the MCP server. One of `server_url`, `connector_id`, or

112959 provided.113094 `tunnel_id` must be provided.

113095

113096 - `TunnelID string`

113097

113098 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

113099 `server_url`, `connector_id`, or `tunnel_id` must be provided.

112960 113100

112961 - `type ToolCodeInterpreter struct{…}`113101 - `type ToolCodeInterpreter struct{…}`

112962 113102

115938 - `ConnectorID string`116078 - `ConnectorID string`

115939 116079

115940 Identifier for service connectors, like those available in ChatGPT. One of116080 Identifier for service connectors, like those available in ChatGPT. One of

115941 `server_url` or `connector_id` must be provided. Learn more about service116081 `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more

115942 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).116082 about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

115943 116083

115944 Currently supported `connector_id` values are:116084 Currently supported `connector_id` values are:

115945 116085

116031 116171

116032 - `ServerURL string`116172 - `ServerURL string`

116033 116173

116034 The URL for the MCP server. One of `server_url` or `connector_id` must be116174 The URL for the MCP server. One of `server_url`, `connector_id`, or

116035 provided.116175 `tunnel_id` must be provided.

116176

116177 - `TunnelID string`

116178

116179 The Secure MCP Tunnel ID to use instead of a direct server URL. One of

116180 `server_url`, `connector_id`, or `tunnel_id` must be provided.

116036 116181

116037 - `type ToolCodeInterpreter struct{…}`116182 - `type ToolCodeInterpreter struct{…}`

116038 116183

go/resources/responses/index.md 2026-06-16 21:57 UTC to 2026-06-17 18:02 UTC

Responses

Create a model response

Parameters

Returns

Example

Response

Get a model response

Parameters

Returns

Example

Response

Delete a model response

Parameters

Example

Cancel a response

Parameters

Returns

Example

Response

Compact a response

Parameters

Returns

Example

Response

Domain Types

Apply Patch Tool

Compacted Response

Computer Action

Computer Action List

Computer Tool

Computer Use Preview Tool

Container Auto

Container Network Policy Allowlist

Container Network Policy Disabled

Container Network Policy Domain Secret

Container Reference

Custom Tool

Easy Input Message

File Search Tool

Function Shell Tool

Function Tool

Inline Skill

Inline Skill Source

Local Environment

Local Skill

Namespace Tool

Response

Response Apply Patch Tool Call

Response Apply Patch Tool Call Output

Response Audio Delta Event

Response Audio Done Event

Response Audio Transcript Delta Event

Response Audio Transcript Done Event

Response Code Interpreter Call Code Delta Event

Response Code Interpreter Call Code Done Event

Response Code Interpreter Call Completed Event

Response Code Interpreter Call In Progress Event

Response Code Interpreter Call Interpreting Event

Response Code Interpreter Tool Call

Response Compaction Item

Response Compaction Item Param

Response Completed Event

Response Computer Tool Call

Response Computer Tool Call Output Item

Response Computer Tool Call Output Screenshot

Response Container Reference

Response Content

Response Content Part Added Event

Response Content Part Done Event

Response Conversation Param

Response Created Event

Response Custom Tool Call

Response Custom Tool Call Input Delta Event

Response Custom Tool Call Input Done Event

Response Custom Tool Call Item

Response Custom Tool Call Output

Response Custom Tool Call Output Item

Response Error

Response Error Event