diff --git a/en/ruby/resources/responses/methods/compact/index.md b/en/ruby/resources/responses/methods/compact/index.md new file mode 100644 index 0000000..4dc46d5 --- /dev/null +++ b/en/ruby/resources/responses/methods/compact/index.md @@ -0,0 +1,6336 @@ +## Compact a response + +`responses.compact(**kwargs) -> CompactedResponse` + +**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](https://platform.openai.com/docs/guides/conversation-state#managing-the-context-window). For ZDR-compatible compaction details, see [Compaction (advanced)](https://platform.openai.com/docs/guides/conversation-state#compaction-advanced). + +### Parameters + +- `model: :"gpt-5.4" | :"gpt-5.4-mini" | :"gpt-5.4-nano" | 89 more | 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](https://platform.openai.com/docs/models) to browse and compare available models. + + - `Model = :"gpt-5.4" | :"gpt-5.4-mini" | :"gpt-5.4-nano" | 89 more` + + 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](https://platform.openai.com/docs/models) to browse and compare available models. + + - `:"gpt-5.4"` + + - `:"gpt-5.4-mini"` + + - `:"gpt-5.4-nano"` + + - `:"gpt-5.4-mini-2026-03-17"` + + - `:"gpt-5.4-nano-2026-03-17"` + + - `:"gpt-5.3-chat-latest"` + + - `:"gpt-5.2"` + + - `:"gpt-5.2-2025-12-11"` + + - `:"gpt-5.2-chat-latest"` + + - `:"gpt-5.2-pro"` + + - `:"gpt-5.2-pro-2025-12-11"` + + - `:"gpt-5.1"` + + - `:"gpt-5.1-2025-11-13"` + + - `:"gpt-5.1-codex"` + + - `:"gpt-5.1-mini"` + + - `:"gpt-5.1-chat-latest"` + + - `:"gpt-5"` + + - `:"gpt-5-mini"` + + - `:"gpt-5-nano"` + + - `:"gpt-5-2025-08-07"` + + - `:"gpt-5-mini-2025-08-07"` + + - `:"gpt-5-nano-2025-08-07"` + + - `:"gpt-5-chat-latest"` + + - `:"gpt-4.1"` + + - `:"gpt-4.1-mini"` + + - `:"gpt-4.1-nano"` + + - `:"gpt-4.1-2025-04-14"` + + - `:"gpt-4.1-mini-2025-04-14"` + + - `:"gpt-4.1-nano-2025-04-14"` + + - `:"o4-mini"` + + - `:"o4-mini-2025-04-16"` + + - `:o3` + + - `:"o3-2025-04-16"` + + - `:"o3-mini"` + + - `:"o3-mini-2025-01-31"` + + - `:o1` + + - `:"o1-2024-12-17"` + + - `:"o1-preview"` + + - `:"o1-preview-2024-09-12"` + + - `:"o1-mini"` + + - `:"o1-mini-2024-09-12"` + + - `:"gpt-4o"` + + - `:"gpt-4o-2024-11-20"` + + - `:"gpt-4o-2024-08-06"` + + - `:"gpt-4o-2024-05-13"` + + - `:"gpt-4o-audio-preview"` + + - `:"gpt-4o-audio-preview-2024-10-01"` + + - `:"gpt-4o-audio-preview-2024-12-17"` + + - `:"gpt-4o-audio-preview-2025-06-03"` + + - `:"gpt-4o-mini-audio-preview"` + + - `:"gpt-4o-mini-audio-preview-2024-12-17"` + + - `:"gpt-4o-search-preview"` + + - `:"gpt-4o-mini-search-preview"` + + - `:"gpt-4o-search-preview-2025-03-11"` + + - `:"gpt-4o-mini-search-preview-2025-03-11"` + + - `:"chatgpt-4o-latest"` + + - `:"codex-mini-latest"` + + - `:"gpt-4o-mini"` + + - `:"gpt-4o-mini-2024-07-18"` + + - `:"gpt-4-turbo"` + + - `:"gpt-4-turbo-2024-04-09"` + + - `:"gpt-4-0125-preview"` + + - `:"gpt-4-turbo-preview"` + + - `:"gpt-4-1106-preview"` + + - `:"gpt-4-vision-preview"` + + - `:"gpt-4"` + + - `:"gpt-4-0314"` + + - `:"gpt-4-0613"` + + - `:"gpt-4-32k"` + + - `:"gpt-4-32k-0314"` + + - `:"gpt-4-32k-0613"` + + - `:"gpt-3.5-turbo"` + + - `:"gpt-3.5-turbo-16k"` + + - `:"gpt-3.5-turbo-0301"` + + - `:"gpt-3.5-turbo-0613"` + + - `:"gpt-3.5-turbo-1106"` + + - `:"gpt-3.5-turbo-0125"` + + - `:"gpt-3.5-turbo-16k-0613"` + + - `:"o1-pro"` + + - `:"o1-pro-2025-03-19"` + + - `:"o3-pro"` + + - `:"o3-pro-2025-06-10"` + + - `:"o3-deep-research"` + + - `:"o3-deep-research-2025-06-26"` + + - `:"o4-mini-deep-research"` + + - `:"o4-mini-deep-research-2025-06-26"` + + - `:"computer-use-preview"` + + - `:"computer-use-preview-2025-03-11"` + + - `:"gpt-5-codex"` + + - `:"gpt-5-pro"` + + - `:"gpt-5-pro-2025-10-06"` + + - `:"gpt-5.1-codex-max"` + + - `String = String` + +- `input: String | Array[ResponseInputItem]` + + Text, image, or file inputs to the model, used to generate a response + + - `String = String` + + A text input to the model, equivalent to a text input with the `user` role. + + - `UnionMember1 = Array[ResponseInputItem]` + + A list of one or many input items to the model, containing different content types. + + - `class EasyInputMessage` + + 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: String | ResponseInputMessageContentList` + + Text, image, or audio input to the model, used to generate a response. + Can also contain previous assistant responses. + + - `String = String` + + A text input to the model. + + - `ResponseInputMessageContentList = Array[ResponseInputContent]` + + A list of one or many input items to the model, containing different content + types. + + - `class ResponseInputText` + + A text input to the model. + + - `text: String` + + The text input to the model. + + - `type: :input_text` + + The type of the input item. Always `input_text`. + + - `:input_text` + + - `class ResponseInputImage` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `detail: :low | :high | :auto | :original` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `:low` + + - `:high` + + - `:auto` + + - `:original` + + - `type: :input_image` + + The type of the input item. Always `input_image`. + + - `:input_image` + + - `file_id: String` + + The ID of the file to be sent to the model. + + - `image_url: String` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `class ResponseInputFile` + + A file input to the model. + + - `type: :input_file` + + The type of the input item. Always `input_file`. + + - `:input_file` + + - `detail: :low | :high` + + 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`. + + - `:low` + + - `:high` + + - `file_data: String` + + The content of the file to be sent to the model. + + - `file_id: String` + + The ID of the file to be sent to the model. + + - `file_url: 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: :user | :assistant | :system | :developer` + + The role of the message input. One of `user`, `assistant`, `system`, or + `developer`. + + - `:user` + + - `:assistant` + + - `:system` + + - `:developer` + + - `phase: :commentary | :final_answer` + + 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. + + - `:commentary` + + - `:final_answer` + + - `type: :message` + + The type of the message input. Always `message`. + + - `:message` + + - `class Message` + + 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: :user | :system | :developer` + + The role of the message input. One of `user`, `system`, or `developer`. + + - `:user` + + - `:system` + + - `:developer` + + - `status: :in_progress | :completed | :incomplete` + + The status of item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `type: :message` + + The type of the message input. Always set to `message`. + + - `:message` + + - `class ResponseOutputMessage` + + An output message from the model. + + - `id: String` + + The unique ID of the output message. + + - `content: Array[ResponseOutputText | ResponseOutputRefusal]` + + The content of the output message. + + - `class ResponseOutputText` + + A text output from the model. + + - `annotations: Array[FileCitation{ file_id, filename, index, type} | URLCitation{ end_index, start_index, title, 2 more} | ContainerFileCitation{ container_id, end_index, file_id, 3 more} | FilePath{ file_id, index, type}]` + + The annotations of the text output. + + - `class FileCitation` + + A citation to a file. + + - `file_id: String` + + The ID of the file. + + - `filename: String` + + The filename of the file cited. + + - `index: Integer` + + The index of the file in the list of files. + + - `type: :file_citation` + + The type of the file citation. Always `file_citation`. + + - `:file_citation` + + - `class URLCitation` + + A citation for a web resource used to generate a model response. + + - `end_index: Integer` + + The index of the last character of the URL citation in the message. + + - `start_index: Integer` + + The index of the first character of the URL citation in the message. + + - `title: String` + + The title of the web resource. + + - `type: :url_citation` + + The type of the URL citation. Always `url_citation`. + + - `:url_citation` + + - `url: String` + + The URL of the web resource. + + - `class ContainerFileCitation` + + A citation for a container file used to generate a model response. + + - `container_id: String` + + The ID of the container file. + + - `end_index: Integer` + + The index of the last character of the container file citation in the message. + + - `file_id: String` + + The ID of the file. + + - `filename: String` + + The filename of the container file cited. + + - `start_index: Integer` + + The index of the first character of the container file citation in the message. + + - `type: :container_file_citation` + + The type of the container file citation. Always `container_file_citation`. + + - `:container_file_citation` + + - `class FilePath` + + A path to a file. + + - `file_id: String` + + The ID of the file. + + - `index: Integer` + + The index of the file in the list of files. + + - `type: :file_path` + + The type of the file path. Always `file_path`. + + - `:file_path` + + - `text: String` + + The text output from the model. + + - `type: :output_text` + + The type of the output text. Always `output_text`. + + - `:output_text` + + - `logprobs: Array[Logprob{ token, bytes, logprob, top_logprobs}]` + + - `token: String` + + - `bytes: Array[Integer]` + + - `logprob: Float` + + - `top_logprobs: Array[TopLogprob{ token, bytes, logprob}]` + + - `token: String` + + - `bytes: Array[Integer]` + + - `logprob: Float` + + - `class ResponseOutputRefusal` + + A refusal from the model. + + - `refusal: String` + + The refusal explanation from the model. + + - `type: :refusal` + + The type of the refusal. Always `refusal`. + + - `:refusal` + + - `role: :assistant` + + The role of the output message. Always `assistant`. + + - `:assistant` + + - `status: :in_progress | :completed | :incomplete` + + The status of the message input. One of `in_progress`, `completed`, or + `incomplete`. Populated when input items are returned via API. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `type: :message` + + The type of the output message. Always `message`. + + - `:message` + + - `phase: :commentary | :final_answer` + + 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. + + - `:commentary` + + - `:final_answer` + + - `class ResponseFileSearchToolCall` + + The results of a file search tool call. See the + [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information. + + - `id: String` + + The unique ID of the file search tool call. + + - `queries: Array[String]` + + The queries used to search for files. + + - `status: :in_progress | :searching | :completed | 2 more` + + The status of the file search tool call. One of `in_progress`, + `searching`, `incomplete` or `failed`, + + - `:in_progress` + + - `:searching` + + - `:completed` + + - `:incomplete` + + - `:failed` + + - `type: :file_search_call` + + The type of the file search tool call. Always `file_search_call`. + + - `:file_search_call` + + - `results: Array[Result{ attributes, file_id, filename, 2 more}]` + + The results of the file search tool call. + + - `attributes: Hash[Symbol, String | Float | bool]` + + 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 = String` + + - `Float = Float` + + - `UnionMember2 = bool` + + - `file_id: String` + + The unique ID of the file. + + - `filename: String` + + The name of the file. + + - `score: Float` + + The relevance score of the file - a value between 0 and 1. + + - `text: String` + + The text that was retrieved from the file. + + - `class ResponseComputerToolCall` + + A tool call to a computer use tool. See the + [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information. + + - `id: String` + + The unique ID of the computer call. + + - `call_id: String` + + An identifier used when responding to the tool call with output. + + - `pending_safety_checks: Array[PendingSafetyCheck{ id, code, message}]` + + 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: :in_progress | :completed | :incomplete` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `type: :computer_call` + + The type of the computer call. Always `computer_call`. + + - `:computer_call` + + - `action: Click{ button, type, x, 2 more} | DoubleClick{ keys, type, x, y_} | Drag{ path, type, keys} | 6 more` + + A click action. + + - `class Click` + + A click action. + + - `button: :left | :right | :wheel | 2 more` + + Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. + + - `:left` + + - `:right` + + - `:wheel` + + - `:back` + + - `:forward` + + - `type: :click` + + Specifies the event type. For a click action, this property is always `click`. + + - `:click` + + - `x: Integer` + + The x-coordinate where the click occurred. + + - `y_: Integer` + + The y-coordinate where the click occurred. + + - `keys: Array[String]` + + The keys being held while clicking. + + - `class DoubleClick` + + A double click action. + + - `keys: Array[String]` + + The keys being held while double-clicking. + + - `type: :double_click` + + Specifies the event type. For a double click action, this property is always set to `double_click`. + + - `:double_click` + + - `x: Integer` + + The x-coordinate where the double click occurred. + + - `y_: Integer` + + The y-coordinate where the double click occurred. + + - `class Drag` + + A drag action. + + - `path: Array[Path{ x, y_}]` + + 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: Integer` + + The x-coordinate. + + - `y_: Integer` + + The y-coordinate. + + - `type: :drag` + + Specifies the event type. For a drag action, this property is always set to `drag`. + + - `:drag` + + - `keys: Array[String]` + + The keys being held while dragging the mouse. + + - `class Keypress` + + A collection of keypresses the model would like to perform. + + - `keys: Array[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`. + + - `:keypress` + + - `class Move` + + A mouse move action. + + - `type: :move` + + Specifies the event type. For a move action, this property is always set to `move`. + + - `:move` + + - `x: Integer` + + The x-coordinate to move to. + + - `y_: Integer` + + The y-coordinate to move to. + + - `keys: Array[String]` + + The keys being held while moving the mouse. + + - `class Screenshot` + + A screenshot action. + + - `type: :screenshot` + + Specifies the event type. For a screenshot action, this property is always set to `screenshot`. + + - `:screenshot` + + - `class Scroll` + + A scroll action. + + - `scroll_x: Integer` + + The horizontal scroll distance. + + - `scroll_y: Integer` + + The vertical scroll distance. + + - `type: :scroll` + + Specifies the event type. For a scroll action, this property is always set to `scroll`. + + - `:scroll` + + - `x: Integer` + + The x-coordinate where the scroll occurred. + + - `y_: Integer` + + The y-coordinate where the scroll occurred. + + - `keys: Array[String]` + + The keys being held while scrolling. + + - `class Type` + + 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`. + + - `:type` + + - `class Wait` + + A wait action. + + - `type: :wait` + + Specifies the event type. For a wait action, this property is always set to `wait`. + + - `:wait` + + - `actions: ComputerActionList` + + Flattened batched actions for `computer_use`. Each action includes an + `type` discriminator and action-specific fields. + + - `class Click` + + A click action. + + - `button: :left | :right | :wheel | 2 more` + + Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. + + - `:left` + + - `:right` + + - `:wheel` + + - `:back` + + - `:forward` + + - `type: :click` + + Specifies the event type. For a click action, this property is always `click`. + + - `:click` + + - `x: Integer` + + The x-coordinate where the click occurred. + + - `y_: Integer` + + The y-coordinate where the click occurred. + + - `keys: Array[String]` + + The keys being held while clicking. + + - `class DoubleClick` + + A double click action. + + - `keys: Array[String]` + + The keys being held while double-clicking. + + - `type: :double_click` + + Specifies the event type. For a double click action, this property is always set to `double_click`. + + - `:double_click` + + - `x: Integer` + + The x-coordinate where the double click occurred. + + - `y_: Integer` + + The y-coordinate where the double click occurred. + + - `class Drag` + + A drag action. + + - `path: Array[Path{ x, y_}]` + + 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: Integer` + + The x-coordinate. + + - `y_: Integer` + + The y-coordinate. + + - `type: :drag` + + Specifies the event type. For a drag action, this property is always set to `drag`. + + - `:drag` + + - `keys: Array[String]` + + The keys being held while dragging the mouse. + + - `class Keypress` + + A collection of keypresses the model would like to perform. + + - `keys: Array[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`. + + - `:keypress` + + - `class Move` + + A mouse move action. + + - `type: :move` + + Specifies the event type. For a move action, this property is always set to `move`. + + - `:move` + + - `x: Integer` + + The x-coordinate to move to. + + - `y_: Integer` + + The y-coordinate to move to. + + - `keys: Array[String]` + + The keys being held while moving the mouse. + + - `class Screenshot` + + A screenshot action. + + - `type: :screenshot` + + Specifies the event type. For a screenshot action, this property is always set to `screenshot`. + + - `:screenshot` + + - `class Scroll` + + A scroll action. + + - `scroll_x: Integer` + + The horizontal scroll distance. + + - `scroll_y: Integer` + + The vertical scroll distance. + + - `type: :scroll` + + Specifies the event type. For a scroll action, this property is always set to `scroll`. + + - `:scroll` + + - `x: Integer` + + The x-coordinate where the scroll occurred. + + - `y_: Integer` + + The y-coordinate where the scroll occurred. + + - `keys: Array[String]` + + The keys being held while scrolling. + + - `class Type` + + 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`. + + - `:type` + + - `class Wait` + + A wait action. + + - `type: :wait` + + Specifies the event type. For a wait action, this property is always set to `wait`. + + - `:wait` + + - `class ComputerCallOutput` + + The output of a computer tool call. + + - `call_id: 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: :computer_screenshot` + + Specifies the event type. For a computer screenshot, this property is + always set to `computer_screenshot`. + + - `:computer_screenshot` + + - `file_id: String` + + The identifier of an uploaded file that contains the screenshot. + + - `image_url: String` + + The URL of the screenshot image. + + - `type: :computer_call_output` + + The type of the computer tool call output. Always `computer_call_output`. + + - `:computer_call_output` + + - `id: String` + + The ID of the computer tool call output. + + - `acknowledged_safety_checks: Array[AcknowledgedSafetyCheck{ id, code, message}]` + + 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: :in_progress | :completed | :incomplete` + + The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `class ResponseFunctionWebSearch` + + The results of a web search tool call. See the + [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information. + + - `id: String` + + The unique ID of the web search tool call. + + - `action: Search{ type, queries, query, sources} | OpenPage{ type, url} | FindInPage{ pattern, type, url}` + + 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). + + - `class Search` + + Action type "search" - Performs a web search query. + + - `type: :search` + + The action type. + + - `:search` + + - `queries: Array[String]` + + The search queries. + + - `query: String` + + The search query. + + - `sources: Array[Source{ type, url}]` + + The sources used in the search. + + - `type: :url` + + The type of source. Always `url`. + + - `:url` + + - `url: String` + + The URL of the source. + + - `class OpenPage` + + Action type "open_page" - Opens a specific URL from search results. + + - `type: :open_page` + + The action type. + + - `:open_page` + + - `url: String` + + The URL opened by the model. + + - `class FindInPage` + + 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: :find_in_page` + + The action type. + + - `:find_in_page` + + - `url: String` + + The URL of the page searched for the pattern. + + - `status: :in_progress | :searching | :completed | :failed` + + The status of the web search tool call. + + - `:in_progress` + + - `:searching` + + - `:completed` + + - `:failed` + + - `type: :web_search_call` + + The type of the web search tool call. Always `web_search_call`. + + - `:web_search_call` + + - `class ResponseFunctionToolCall` + + A tool call to run a function. See the + [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information. + + - `arguments: String` + + A JSON string of the arguments to pass to the function. + + - `call_id: String` + + The unique ID of the function tool call generated by the model. + + - `name: String` + + The name of the function to run. + + - `type: :function_call` + + The type of the function tool call. Always `function_call`. + + - `:function_call` + + - `id: String` + + The unique ID of the function tool call. + + - `namespace: String` + + The namespace of the function to run. + + - `status: :in_progress | :completed | :incomplete` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `class FunctionCallOutput` + + The output of a function tool call. + + - `call_id: String` + + The unique ID of the function tool call generated by the model. + + - `output: String | ResponseFunctionCallOutputItemList` + + Text, image, or file output of the function tool call. + + - `String = String` + + A JSON string of the output of the function tool call. + + - `ResponseFunctionCallOutputItemList = Array[ResponseFunctionCallOutputItem]` + + An array of content outputs (text, image, file) for the function tool call. + + - `class ResponseInputTextContent` + + A text input to the model. + + - `text: String` + + The text input to the model. + + - `type: :input_text` + + The type of the input item. Always `input_text`. + + - `:input_text` + + - `class ResponseInputImageContent` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision) + + - `type: :input_image` + + The type of the input item. Always `input_image`. + + - `:input_image` + + - `detail: :low | :high | :auto | :original` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `:low` + + - `:high` + + - `:auto` + + - `:original` + + - `file_id: String` + + The ID of the file to be sent to the model. + + - `image_url: String` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `class ResponseInputFileContent` + + A file input to the model. + + - `type: :input_file` + + The type of the input item. Always `input_file`. + + - `:input_file` + + - `detail: :low | :high` + + 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`. + + - `:low` + + - `:high` + + - `file_data: String` + + The base64-encoded data of the file to be sent to the model. + + - `file_id: String` + + The ID of the file to be sent to the model. + + - `file_url: 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: :function_call_output` + + The type of the function tool call output. Always `function_call_output`. + + - `:function_call_output` + + - `id: String` + + The unique ID of the function tool call output. Populated when this item is returned via API. + + - `status: :in_progress | :completed | :incomplete` + + The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `class ToolSearchCall` + + - `arguments: untyped` + + The arguments supplied to the tool search call. + + - `type: :tool_search_call` + + The item type. Always `tool_search_call`. + + - `:tool_search_call` + + - `id: String` + + The unique ID of this tool search call. + + - `call_id: String` + + The unique ID of the tool search call generated by the model. + + - `execution: :server | :client` + + Whether tool search was executed by the server or by the client. + + - `:server` + + - `:client` + + - `status: :in_progress | :completed | :incomplete` + + The status of the tool search call. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `class ResponseToolSearchOutputItemParam` + + - `tools: Array[Tool]` + + The loaded tool definitions returned by the tool search output. + + - `class FunctionTool` + + Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling). + + - `name: String` + + The name of the function to call. + + - `parameters: Hash[Symbol, untyped]` + + 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`. + + - `:function` + + - `defer_loading: 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. + + - `class FileSearchTool` + + A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://platform.openai.com/docs/guides/tools-file-search). + + - `type: :file_search` + + The type of the file search tool. Always `file_search`. + + - `:file_search` + + - `vector_store_ids: Array[String]` + + The IDs of the vector stores to search. + + - `filters: ComparisonFilter | CompoundFilter` + + A filter to apply. + + - `class ComparisonFilter` + + 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: :eq | :ne | :gt | 5 more` + + 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 + + - `:eq` + + - `:ne` + + - `:gt` + + - `:gte` + + - `:lt` + + - `:lte` + + - `:in` + + - `:nin` + + - `value: String | Float | bool | Array[String | Float]` + + The value to compare against the attribute key; supports string, number, or boolean types. + + - `String = String` + + - `Float = Float` + + - `UnionMember2 = bool` + + - `UnionMember3 = Array[String | Float]` + + - `String = String` + + - `Float = Float` + + - `class CompoundFilter` + + Combine multiple filters using `and` or `or`. + + - `filters: Array[ComparisonFilter | untyped]` + + Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`. + + - `class ComparisonFilter` + + A filter used to compare a specified attribute key to a given value using a defined comparison operation. + + - `UnionMember1 = untyped` + + - `type: :and | :or` + + Type of operation: `and` or `or`. + + - `:and` + + - `:or` + + - `max_num_results: Integer` + + The maximum number of results to return. This number should be between 1 and 50 inclusive. + + - `ranking_options: RankingOptions{ hybrid_search, ranker, score_threshold}` + + Ranking options for search. + + - `hybrid_search: HybridSearch{ embedding_weight, text_weight}` + + Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. + + - `embedding_weight: Float` + + The weight of the embedding in the reciprocal ranking fusion. + + - `text_weight: Float` + + The weight of the text in the reciprocal ranking fusion. + + - `ranker: :auto | :"default-2024-11-15"` + + The ranker to use for the file search. + + - `:auto` + + - `:"default-2024-11-15"` + + - `score_threshold: Float` + + 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. + + - `class ComputerTool` + + A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use). + + - `type: :computer` + + The type of the computer tool. Always `computer`. + + - `:computer` + + - `class ComputerUsePreviewTool` + + A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use). + + - `display_height: Integer` + + The height of the computer display. + + - `display_width: Integer` + + The width of the computer display. + + - `environment: :windows | :mac | :linux | 2 more` + + The type of computer environment to control. + + - `:windows` + + - `:mac` + + - `:linux` + + - `:ubuntu` + + - `:browser` + + - `type: :computer_use_preview` + + The type of the computer use tool. Always `computer_use_preview`. + + - `:computer_use_preview` + + - `class WebSearchTool` + + Search the Internet for sources related to the prompt. Learn more about the + [web search tool](https://platform.openai.com/docs/guides/tools-web-search). + + - `type: :web_search | :web_search_2025_08_26` + + The type of the web search tool. One of `web_search` or `web_search_2025_08_26`. + + - `:web_search` + + - `:web_search_2025_08_26` + + - `filters: Filters{ allowed_domains}` + + Filters for the search. + + - `allowed_domains: Array[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"]` + + - `search_context_size: :low | :medium | :high` + + 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. + + - `:low` + + - `:medium` + + - `:high` + + - `user_location: UserLocation{ city, country, region, 2 more}` + + 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](https://en.wikipedia.org/wiki/ISO_3166-1) 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](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. + + - `type: :approximate` + + The type of location approximation. Always `approximate`. + + - `:approximate` + + - `class Mcp` + + Give the model access to additional tools via remote Model Context Protocol + (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). + + - `server_label: String` + + A label for this MCP server, used to identify it in tool calls. + + - `type: :mcp` + + The type of the MCP tool. Always `mcp`. + + - `:mcp` + + - `allowed_tools: Array[String] | McpToolFilter{ read_only, tool_names}` + + List of allowed tool names or a filter object. + + - `McpAllowedTools = Array[String]` + + A string array of allowed tool names + + - `class McpToolFilter` + + A filter object to specify which tools are allowed. + + - `read_only: bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `tool_names: Array[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. + + - `connector_id: :connector_dropbox | :connector_gmail | :connector_googlecalendar | 5 more` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + 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` + + - `:connector_dropbox` + + - `:connector_gmail` + + - `:connector_googlecalendar` + + - `:connector_googledrive` + + - `:connector_microsoftteams` + + - `:connector_outlookcalendar` + + - `:connector_outlookemail` + + - `:connector_sharepoint` + + - `defer_loading: bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `headers: Hash[Symbol, String]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `require_approval: McpToolApprovalFilter{ always, never} | :always | :never` + + Specify which of the MCP server's tools require approval. + + - `class McpToolApprovalFilter` + + 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: Always{ read_only, tool_names}` + + A filter object to specify which tools are allowed. + + - `read_only: bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `tool_names: Array[String]` + + List of allowed tool names. + + - `never: Never{ read_only, tool_names}` + + A filter object to specify which tools are allowed. + + - `read_only: bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `tool_names: Array[String]` + + List of allowed tool names. + + - `McpToolApprovalSetting = :always | :never` + + 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. + + - `:always` + + - `:never` + + - `server_description: String` + + Optional description of the MCP server, used to provide more context. + + - `server_url: String` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + + - `class CodeInterpreter` + + A tool that runs Python code to help generate a response to a prompt. + + - `container: String | CodeInterpreterToolAuto{ type, file_ids, memory_limit, network_policy}` + + 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 = String` + + The container ID. + + - `class CodeInterpreterToolAuto` + + Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on. + + - `type: :auto` + + Always `auto`. + + - `:auto` + + - `file_ids: Array[String]` + + An optional list of uploaded files to make available to your code. + + - `memory_limit: :"1g" | :"4g" | :"16g" | :"64g"` + + The memory limit for the code interpreter container. + + - `:"1g"` + + - `:"4g"` + + - `:"16g"` + + - `:"64g"` + + - `network_policy: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` + + Network access policy for the container. + + - `class ContainerNetworkPolicyDisabled` + + - `type: :disabled` + + Disable outbound network access. Always `disabled`. + + - `:disabled` + + - `class ContainerNetworkPolicyAllowlist` + + - `allowed_domains: Array[String]` + + A list of allowed domains when type is `allowlist`. + + - `type: :allowlist` + + Allow outbound network access only to specified domains. Always `allowlist`. + + - `:allowlist` + + - `domain_secrets: Array[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: :code_interpreter` + + The type of the code interpreter tool. Always `code_interpreter`. + + - `:code_interpreter` + + - `class ImageGeneration` + + A tool that generates images using the GPT image models. + + - `type: :image_generation` + + The type of the image generation tool. Always `image_generation`. + + - `:image_generation` + + - `action: :generate | :edit | :auto` + + Whether to generate a new image or edit an existing image. Default: `auto`. + + - `:generate` + + - `:edit` + + - `:auto` + + - `background: :transparent | :opaque | :auto` + + 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`. + + - `:transparent` + + - `:opaque` + + - `:auto` + + - `input_fidelity: :high | :low` + + 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`. + + - `:high` + + - `:low` + + - `input_image_mask: InputImageMask{ file_id, image_url}` + + Optional mask for inpainting. Contains `image_url` + (string, optional) and `file_id` (string, optional). + + - `file_id: String` + + File ID for the mask image. + + - `image_url: String` + + Base64-encoded mask image. + + - `model: String | :"gpt-image-1" | :"gpt-image-1-mini" | :"gpt-image-2" | 3 more` + + The image generation model to use. Default: `gpt-image-1`. + + - `String = String` + + - `Model = :"gpt-image-1" | :"gpt-image-1-mini" | :"gpt-image-2" | 3 more` + + The image generation model to use. Default: `gpt-image-1`. + + - `:"gpt-image-1"` + + - `:"gpt-image-1-mini"` + + - `:"gpt-image-2"` + + - `:"gpt-image-2-2026-04-21"` + + - `:"gpt-image-1.5"` + + - `:"chatgpt-image-latest"` + + - `moderation: :auto | :low` + + Moderation level for the generated image. Default: `auto`. + + - `:auto` + + - `:low` + + - `output_compression: Integer` + + Compression level for the output image. Default: 100. + + - `output_format: :png | :webp | :jpeg` + + The output format of the generated image. One of `png`, `webp`, or + `jpeg`. Default: `png`. + + - `:png` + + - `:webp` + + - `:jpeg` + + - `partial_images: Integer` + + Number of partial images to generate in streaming mode, from 0 (default value) to 3. + + - `quality: :low | :medium | :high | :auto` + + The quality of the generated image. One of `low`, `medium`, `high`, + or `auto`. Default: `auto`. + + - `:low` + + - `:medium` + + - `:high` + + - `:auto` + + - `size: String | :"1024x1024" | :"1024x1536" | :"1536x1024" | :auto` + + 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` + + - `Size = :"1024x1024" | :"1024x1536" | :"1536x1024" | :auto` + + 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`. + + - `:"1024x1024"` + + - `:"1024x1536"` + + - `:"1536x1024"` + + - `:auto` + + - `class LocalShell` + + A tool that allows the model to execute shell commands in a local environment. + + - `type: :local_shell` + + The type of the local shell tool. Always `local_shell`. + + - `:local_shell` + + - `class FunctionShellTool` + + A tool that allows the model to execute shell commands. + + - `type: :shell` + + The type of the shell tool. Always `shell`. + + - `:shell` + + - `environment: ContainerAuto | LocalEnvironment | ContainerReference` + + - `class ContainerAuto` + + - `type: :container_auto` + + Automatically creates a container for this request + + - `:container_auto` + + - `file_ids: Array[String]` + + An optional list of uploaded files to make available to your code. + + - `memory_limit: :"1g" | :"4g" | :"16g" | :"64g"` + + The memory limit for the container. + + - `:"1g"` + + - `:"4g"` + + - `:"16g"` + + - `:"64g"` + + - `network_policy: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` + + Network access policy for the container. + + - `class ContainerNetworkPolicyDisabled` + + - `class ContainerNetworkPolicyAllowlist` + + - `skills: Array[SkillReference | InlineSkill]` + + An optional list of skills referenced by id or inline data. + + - `class SkillReference` + + - `skill_id: String` + + The ID of the referenced skill. + + - `type: :skill_reference` + + References a skill created with the /v1/skills endpoint. + + - `:skill_reference` + + - `version: String` + + Optional skill version. Use a positive integer or 'latest'. Omit for default. + + - `class InlineSkill` + + - `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. + + - `media_type: :"application/zip"` + + The media type of the inline skill payload. Must be `application/zip`. + + - `:"application/zip"` + + - `type: :base64` + + The type of the inline skill source. Must be `base64`. + + - `:base64` + + - `type: :inline` + + Defines an inline skill for this request. + + - `:inline` + + - `class LocalEnvironment` + + - `type: :local` + + Use a local computer environment. + + - `:local` + + - `skills: Array[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. + + - `class ContainerReference` + + - `container_id: String` + + The ID of the referenced container. + + - `type: :container_reference` + + References a container created with the /v1/containers endpoint + + - `:container_reference` + + - `class CustomTool` + + A custom tool that processes input using a specified format. Learn more about [custom tools](https://platform.openai.com/docs/guides/function-calling#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`. + + - `:custom` + + - `defer_loading: 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_: CustomToolInputFormat` + + The input format for the custom tool. Default is unconstrained text. + + - `class Text` + + Unconstrained free-form text. + + - `type: :text` + + Unconstrained text format. Always `text`. + + - `:text` + + - `class Grammar` + + A grammar defined by the user. + + - `definition: String` + + The grammar definition. + + - `syntax: :lark | :regex` + + The syntax of the grammar definition. One of `lark` or `regex`. + + - `:lark` + + - `:regex` + + - `type: :grammar` + + Grammar format. Always `grammar`. + + - `:grammar` + + - `class NamespaceTool` + + 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: Array[Function{ name, type, defer_loading, 3 more} | CustomTool]` + + The function/custom tools available inside this namespace. + + - `class Function` + + - `name: String` + + - `type: :function` + + - `:function` + + - `defer_loading: bool` + + Whether this function should be deferred and discovered via tool search. + + - `description: String` + + - `parameters: untyped` + + - `strict: bool` + + - `class CustomTool` + + A custom tool that processes input using a specified format. Learn more about [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools) + + - `type: :namespace` + + The type of the tool. Always `namespace`. + + - `:namespace` + + - `class ToolSearchTool` + + Hosted or BYOT tool search configuration for deferred tools. + + - `type: :tool_search` + + The type of the tool. Always `tool_search`. + + - `:tool_search` + + - `description: String` + + Description shown to the model for a client-executed tool search tool. + + - `execution: :server | :client` + + Whether tool search is executed by the server or by the client. + + - `:server` + + - `:client` + + - `parameters: untyped` + + Parameter schema for a client-executed tool search tool. + + - `class WebSearchPreviewTool` + + This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search). + + - `type: :web_search_preview | :web_search_preview_2025_03_11` + + The type of the web search tool. One of `web_search_preview` or `web_search_preview_2025_03_11`. + + - `:web_search_preview` + + - `:web_search_preview_2025_03_11` + + - `search_content_types: Array[:text | :image]` + + - `:text` + + - `:image` + + - `search_context_size: :low | :medium | :high` + + 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. + + - `:low` + + - `:medium` + + - `:high` + + - `user_location: UserLocation{ type, city, country, 2 more}` + + The user's location. + + - `type: :approximate` + + The type of location approximation. Always `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](https://en.wikipedia.org/wiki/ISO_3166-1) 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](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. + + - `class ApplyPatchTool` + + Allows the assistant to create, delete, or update files using unified diffs. + + - `type: :apply_patch` + + The type of the tool. Always `apply_patch`. + + - `:apply_patch` + + - `type: :tool_search_output` + + The item type. Always `tool_search_output`. + + - `:tool_search_output` + + - `id: String` + + The unique ID of this tool search output. + + - `call_id: String` + + The unique ID of the tool search call generated by the model. + + - `execution: :server | :client` + + Whether tool search was executed by the server or by the client. + + - `:server` + + - `:client` + + - `status: :in_progress | :completed | :incomplete` + + The status of the tool search output. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `class AdditionalTools` + + - `role: :developer` + + The role that provided the additional tools. Only `developer` is supported. + + - `:developer` + + - `tools: Array[Tool]` + + A list of additional tools made available at this item. + + - `class FunctionTool` + + Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling). + + - `class FileSearchTool` + + A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://platform.openai.com/docs/guides/tools-file-search). + + - `class ComputerTool` + + A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use). + + - `class ComputerUsePreviewTool` + + A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use). + + - `class WebSearchTool` + + Search the Internet for sources related to the prompt. Learn more about the + [web search tool](https://platform.openai.com/docs/guides/tools-web-search). + + - `class Mcp` + + Give the model access to additional tools via remote Model Context Protocol + (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). + + - `class CodeInterpreter` + + A tool that runs Python code to help generate a response to a prompt. + + - `class ImageGeneration` + + A tool that generates images using the GPT image models. + + - `class LocalShell` + + A tool that allows the model to execute shell commands in a local environment. + + - `class FunctionShellTool` + + A tool that allows the model to execute shell commands. + + - `class CustomTool` + + A custom tool that processes input using a specified format. Learn more about [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools) + + - `class NamespaceTool` + + Groups function/custom tools under a shared namespace. + + - `class ToolSearchTool` + + Hosted or BYOT tool search configuration for deferred tools. + + - `class WebSearchPreviewTool` + + This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search). + + - `class ApplyPatchTool` + + Allows the assistant to create, delete, or update files using unified diffs. + + - `type: :additional_tools` + + The item type. Always `additional_tools`. + + - `:additional_tools` + + - `id: String` + + The unique ID of this additional tools item. + + - `class ResponseReasoningItem` + + 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](https://platform.openai.com/docs/guides/conversation-state). + + - `id: String` + + The unique identifier of the reasoning content. + + - `summary: Array[Summary{ text, type}]` + + Reasoning summary content. + + - `text: String` + + A summary of the reasoning output from the model so far. + + - `type: :summary_text` + + The type of the object. Always `summary_text`. + + - `:summary_text` + + - `type: :reasoning` + + The type of the object. Always `reasoning`. + + - `:reasoning` + + - `content: Array[Content{ text, type}]` + + Reasoning text content. + + - `text: String` + + The reasoning text from the model. + + - `type: :reasoning_text` + + The type of the reasoning text. Always `reasoning_text`. + + - `:reasoning_text` + + - `encrypted_content: String` + + The encrypted content of the reasoning item - populated when a response is + generated with `reasoning.encrypted_content` in the `include` parameter. + + - `status: :in_progress | :completed | :incomplete` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `class ResponseCompactionItemParam` + + A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). + + - `encrypted_content: String` + + The encrypted content of the compaction summary. + + - `type: :compaction` + + The type of the item. Always `compaction`. + + - `:compaction` + + - `id: String` + + The ID of the compaction item. + + - `class ImageGenerationCall` + + 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: :in_progress | :completed | :generating | :failed` + + The status of the image generation call. + + - `:in_progress` + + - `:completed` + + - `:generating` + + - `:failed` + + - `type: :image_generation_call` + + The type of the image generation call. Always `image_generation_call`. + + - `:image_generation_call` + + - `class ResponseCodeInterpreterToolCall` + + 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. + + - `container_id: String` + + The ID of the container used to run the code. + + - `outputs: Array[Logs{ logs, type} | Image{ type, url}]` + + The outputs generated by the code interpreter, such as logs or images. + Can be null if no outputs are available. + + - `class Logs` + + 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`. + + - `:logs` + + - `class Image` + + The image output from the code interpreter. + + - `type: :image` + + The type of the output. Always `image`. + + - `:image` + + - `url: String` + + The URL of the image output from the code interpreter. + + - `status: :in_progress | :completed | :incomplete | 2 more` + + The status of the code interpreter tool call. Valid values are `in_progress`, `completed`, `incomplete`, `interpreting`, and `failed`. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `:interpreting` + + - `:failed` + + - `type: :code_interpreter_call` + + The type of the code interpreter tool call. Always `code_interpreter_call`. + + - `:code_interpreter_call` + + - `class LocalShellCall` + + A tool call to run a command on the local shell. + + - `id: String` + + The unique ID of the local shell call. + + - `action: Action{ command, env, type, 3 more}` + + Execute a shell command on the server. + + - `command: Array[String]` + + The command to run. + + - `env: Hash[Symbol, String]` + + Environment variables to set for the command. + + - `type: :exec` + + The type of the local shell action. Always `exec`. + + - `:exec` + + - `timeout_ms: Integer` + + Optional timeout in milliseconds for the command. + + - `user: String` + + Optional user to run the command as. + + - `working_directory: String` + + Optional working directory to run the command in. + + - `call_id: String` + + The unique ID of the local shell tool call generated by the model. + + - `status: :in_progress | :completed | :incomplete` + + The status of the local shell call. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `type: :local_shell_call` + + The type of the local shell call. Always `local_shell_call`. + + - `:local_shell_call` + + - `class LocalShellCallOutput` + + 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: :local_shell_call_output` + + The type of the local shell tool call output. Always `local_shell_call_output`. + + - `:local_shell_call_output` + + - `status: :in_progress | :completed | :incomplete` + + The status of the item. One of `in_progress`, `completed`, or `incomplete`. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `class ShellCall` + + A tool representing a request to execute one or more shell commands. + + - `action: Action{ commands, max_output_length, timeout_ms}` + + The shell commands and limits that describe how to run the tool call. + + - `commands: Array[String]` + + Ordered shell commands for the execution environment to run. + + - `max_output_length: Integer` + + Maximum number of UTF-8 characters to capture from combined stdout and stderr output. + + - `timeout_ms: Integer` + + Maximum wall-clock time in milliseconds to allow the shell commands to run. + + - `call_id: String` + + The unique ID of the shell tool call generated by the model. + + - `type: :shell_call` + + The type of the item. Always `shell_call`. + + - `:shell_call` + + - `id: String` + + The unique ID of the shell tool call. Populated when this item is returned via API. + + - `environment: LocalEnvironment | ContainerReference` + + The environment to execute the shell commands in. + + - `class LocalEnvironment` + + - `class ContainerReference` + + - `status: :in_progress | :completed | :incomplete` + + The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `class ShellCallOutput` + + The streamed output items emitted by a shell tool call. + + - `call_id: String` + + The unique ID of the shell tool call generated by the model. + + - `output: Array[ResponseFunctionShellCallOutputContent]` + + Captured chunks of stdout and stderr output, along with their associated outcomes. + + - `outcome: Timeout{ type} | Exit{ exit_code, type}` + + The exit or timeout outcome associated with this shell call. + + - `class Timeout` + + Indicates that the shell call exceeded its configured time limit. + + - `type: :timeout` + + The outcome type. Always `timeout`. + + - `:timeout` + + - `class Exit` + + Indicates that the shell commands finished and returned an exit code. + + - `exit_code: Integer` + + The exit code returned by the shell process. + + - `type: :exit` + + The outcome type. Always `exit`. + + - `:exit` + + - `stderr: String` + + Captured stderr output for the shell call. + + - `stdout: String` + + Captured stdout output for the shell call. + + - `type: :shell_call_output` + + The type of the item. Always `shell_call_output`. + + - `:shell_call_output` + + - `id: String` + + The unique ID of the shell tool call output. Populated when this item is returned via API. + + - `max_output_length: Integer` + + The maximum number of UTF-8 characters captured for this shell call's combined output. + + - `status: :in_progress | :completed | :incomplete` + + The status of the shell call output. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `class ApplyPatchCall` + + A tool call representing a request to create, delete, or update files using diff patches. + + - `call_id: String` + + The unique ID of the apply patch tool call generated by the model. + + - `operation: CreateFile{ diff, path, type} | DeleteFile{ path, type} | UpdateFile{ diff, path, type}` + + The specific create, delete, or update instruction for the apply_patch tool call. + + - `class CreateFile` + + 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: :create_file` + + The operation type. Always `create_file`. + + - `:create_file` + + - `class DeleteFile` + + 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: :delete_file` + + The operation type. Always `delete_file`. + + - `:delete_file` + + - `class UpdateFile` + + 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: :update_file` + + The operation type. Always `update_file`. + + - `:update_file` + + - `status: :in_progress | :completed` + + The status of the apply patch tool call. One of `in_progress` or `completed`. + + - `:in_progress` + + - `:completed` + + - `type: :apply_patch_call` + + The type of the item. Always `apply_patch_call`. + + - `:apply_patch_call` + + - `id: String` + + The unique ID of the apply patch tool call. Populated when this item is returned via API. + + - `class ApplyPatchCallOutput` + + The streamed output emitted by an apply patch tool call. + + - `call_id: String` + + The unique ID of the apply patch tool call generated by the model. + + - `status: :completed | :failed` + + The status of the apply patch tool call output. One of `completed` or `failed`. + + - `:completed` + + - `:failed` + + - `type: :apply_patch_call_output` + + The type of the item. Always `apply_patch_call_output`. + + - `: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). + + - `class McpListTools` + + A list of tools available on an MCP server. + + - `id: String` + + The unique ID of the list. + + - `server_label: String` + + The label of the MCP server. + + - `tools: Array[Tool{ input_schema, name, annotations, description}]` + + The tools available on the server. + + - `input_schema: untyped` + + The JSON schema describing the tool's input. + + - `name: String` + + The name of the tool. + + - `annotations: untyped` + + Additional annotations about the tool. + + - `description: String` + + The description of the tool. + + - `type: :mcp_list_tools` + + The type of the item. Always `mcp_list_tools`. + + - `:mcp_list_tools` + + - `error: String` + + Error message if the server could not list tools. + + - `class McpApprovalRequest` + + 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. + + - `server_label: String` + + The label of the MCP server making the request. + + - `type: :mcp_approval_request` + + The type of the item. Always `mcp_approval_request`. + + - `:mcp_approval_request` + + - `class McpApprovalResponse` + + A response to an MCP approval request. + + - `approval_request_id: String` + + The ID of the approval request being answered. + + - `approve: bool` + + Whether the request was approved. + + - `type: :mcp_approval_response` + + The type of the item. Always `mcp_approval_response`. + + - `:mcp_approval_response` + + - `id: String` + + The unique ID of the approval response + + - `reason: String` + + Optional reason for the decision. + + - `class McpCall` + + 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. + + - `server_label: String` + + The label of the MCP server running the tool. + + - `type: :mcp_call` + + The type of the item. Always `mcp_call`. + + - `:mcp_call` + + - `approval_request_id: 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: :in_progress | :completed | :incomplete | 2 more` + + The status of the tool call. One of `in_progress`, `completed`, `incomplete`, `calling`, or `failed`. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `:calling` + + - `:failed` + + - `class ResponseCustomToolCallOutput` + + The output of a custom tool call from your code, being sent back to the model. + + - `call_id: String` + + The call ID, used to map this custom tool call output to a custom tool call. + + - `output: String | Array[ResponseInputText | ResponseInputImage | ResponseInputFile]` + + The output from the custom tool call generated by your code. + Can be a string or an list of output content. + + - `String = String` + + A string of the output of the custom tool call. + + - `OutputContentList = Array[ResponseInputText | ResponseInputImage | ResponseInputFile]` + + Text, image, or file output of the custom tool call. + + - `class ResponseInputText` + + A text input to the model. + + - `class ResponseInputImage` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `class ResponseInputFile` + + A file input to the model. + + - `type: :custom_tool_call_output` + + The type of the custom tool call output. Always `custom_tool_call_output`. + + - `:custom_tool_call_output` + + - `id: String` + + The unique ID of the custom tool call output in the OpenAI platform. + + - `class ResponseCustomToolCall` + + A call to a custom tool created by the model. + + - `call_id: 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: :custom_tool_call` + + The type of the custom tool call. Always `custom_tool_call`. + + - `: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. + + - `class CompactionTrigger` + + Compacts the current context. Must be the final input item. + + - `type: :compaction_trigger` + + The type of the item. Always `compaction_trigger`. + + - `:compaction_trigger` + + - `class ItemReference` + + An internal identifier for an item to reference. + + - `id: String` + + The ID of the item to reference. + + - `type: :item_reference` + + The type of item to reference. Always `item_reference`. + + - `:item_reference` + +- `instructions: 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. + +- `previous_response_id: String` + + The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](https://platform.openai.com/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. + +- `prompt_cache_key: String` + + A key to use when reading from or writing to the prompt cache. + +- `prompt_cache_retention: :in_memory | :"24h"` + + How long to retain a prompt cache entry created by this request. + + - `:in_memory` + + - `:"24h"` + +- `service_tier: :auto | :default | :flex | :priority` + + The service tier to use for this request. + + - `:auto` + + - `:default` + + - `:flex` + + - `:priority` + +### Returns + +- `class CompactedResponse` + + - `id: String` + + The unique identifier for the compacted response. + + - `created_at: Integer` + + Unix timestamp (in seconds) when the compacted conversation was created. + + - `object: :"response.compaction"` + + The object type. Always `response.compaction`. + + - `:"response.compaction"` + + - `output: Array[ResponseOutputItem]` + + The compacted list of output items. This is a list of all user messages, followed by a single compaction item. + + - `class ResponseOutputMessage` + + An output message from the model. + + - `id: String` + + The unique ID of the output message. + + - `content: Array[ResponseOutputText | ResponseOutputRefusal]` + + The content of the output message. + + - `class ResponseOutputText` + + A text output from the model. + + - `annotations: Array[FileCitation{ file_id, filename, index, type} | URLCitation{ end_index, start_index, title, 2 more} | ContainerFileCitation{ container_id, end_index, file_id, 3 more} | FilePath{ file_id, index, type}]` + + The annotations of the text output. + + - `class FileCitation` + + A citation to a file. + + - `file_id: String` + + The ID of the file. + + - `filename: String` + + The filename of the file cited. + + - `index: Integer` + + The index of the file in the list of files. + + - `type: :file_citation` + + The type of the file citation. Always `file_citation`. + + - `:file_citation` + + - `class URLCitation` + + A citation for a web resource used to generate a model response. + + - `end_index: Integer` + + The index of the last character of the URL citation in the message. + + - `start_index: Integer` + + The index of the first character of the URL citation in the message. + + - `title: String` + + The title of the web resource. + + - `type: :url_citation` + + The type of the URL citation. Always `url_citation`. + + - `:url_citation` + + - `url: String` + + The URL of the web resource. + + - `class ContainerFileCitation` + + A citation for a container file used to generate a model response. + + - `container_id: String` + + The ID of the container file. + + - `end_index: Integer` + + The index of the last character of the container file citation in the message. + + - `file_id: String` + + The ID of the file. + + - `filename: String` + + The filename of the container file cited. + + - `start_index: Integer` + + The index of the first character of the container file citation in the message. + + - `type: :container_file_citation` + + The type of the container file citation. Always `container_file_citation`. + + - `:container_file_citation` + + - `class FilePath` + + A path to a file. + + - `file_id: String` + + The ID of the file. + + - `index: Integer` + + The index of the file in the list of files. + + - `type: :file_path` + + The type of the file path. Always `file_path`. + + - `:file_path` + + - `text: String` + + The text output from the model. + + - `type: :output_text` + + The type of the output text. Always `output_text`. + + - `:output_text` + + - `logprobs: Array[Logprob{ token, bytes, logprob, top_logprobs}]` + + - `token: String` + + - `bytes: Array[Integer]` + + - `logprob: Float` + + - `top_logprobs: Array[TopLogprob{ token, bytes, logprob}]` + + - `token: String` + + - `bytes: Array[Integer]` + + - `logprob: Float` + + - `class ResponseOutputRefusal` + + A refusal from the model. + + - `refusal: String` + + The refusal explanation from the model. + + - `type: :refusal` + + The type of the refusal. Always `refusal`. + + - `:refusal` + + - `role: :assistant` + + The role of the output message. Always `assistant`. + + - `:assistant` + + - `status: :in_progress | :completed | :incomplete` + + The status of the message input. One of `in_progress`, `completed`, or + `incomplete`. Populated when input items are returned via API. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `type: :message` + + The type of the output message. Always `message`. + + - `:message` + + - `phase: :commentary | :final_answer` + + 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. + + - `:commentary` + + - `:final_answer` + + - `class ResponseFileSearchToolCall` + + The results of a file search tool call. See the + [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information. + + - `id: String` + + The unique ID of the file search tool call. + + - `queries: Array[String]` + + The queries used to search for files. + + - `status: :in_progress | :searching | :completed | 2 more` + + The status of the file search tool call. One of `in_progress`, + `searching`, `incomplete` or `failed`, + + - `:in_progress` + + - `:searching` + + - `:completed` + + - `:incomplete` + + - `:failed` + + - `type: :file_search_call` + + The type of the file search tool call. Always `file_search_call`. + + - `:file_search_call` + + - `results: Array[Result{ attributes, file_id, filename, 2 more}]` + + The results of the file search tool call. + + - `attributes: Hash[Symbol, String | Float | bool]` + + 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 = String` + + - `Float = Float` + + - `UnionMember2 = bool` + + - `file_id: String` + + The unique ID of the file. + + - `filename: String` + + The name of the file. + + - `score: Float` + + The relevance score of the file - a value between 0 and 1. + + - `text: String` + + The text that was retrieved from the file. + + - `class ResponseFunctionToolCall` + + A tool call to run a function. See the + [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information. + + - `arguments: String` + + A JSON string of the arguments to pass to the function. + + - `call_id: String` + + The unique ID of the function tool call generated by the model. + + - `name: String` + + The name of the function to run. + + - `type: :function_call` + + The type of the function tool call. Always `function_call`. + + - `:function_call` + + - `id: String` + + The unique ID of the function tool call. + + - `namespace: String` + + The namespace of the function to run. + + - `status: :in_progress | :completed | :incomplete` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `class ResponseFunctionToolCallOutputItem` + + - `id: String` + + The unique ID of the function call tool output. + + - `call_id: String` + + The unique ID of the function tool call generated by the model. + + - `output: String | Array[ResponseInputText | ResponseInputImage | ResponseInputFile]` + + The output from the function call generated by your code. + Can be a string or an list of output content. + + - `String = String` + + A string of the output of the function call. + + - `OutputContentList = Array[ResponseInputText | ResponseInputImage | ResponseInputFile]` + + Text, image, or file output of the function call. + + - `class ResponseInputText` + + A text input to the model. + + - `text: String` + + The text input to the model. + + - `type: :input_text` + + The type of the input item. Always `input_text`. + + - `:input_text` + + - `class ResponseInputImage` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `detail: :low | :high | :auto | :original` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `:low` + + - `:high` + + - `:auto` + + - `:original` + + - `type: :input_image` + + The type of the input item. Always `input_image`. + + - `:input_image` + + - `file_id: String` + + The ID of the file to be sent to the model. + + - `image_url: String` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `class ResponseInputFile` + + A file input to the model. + + - `type: :input_file` + + The type of the input item. Always `input_file`. + + - `:input_file` + + - `detail: :low | :high` + + 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`. + + - `:low` + + - `:high` + + - `file_data: String` + + The content of the file to be sent to the model. + + - `file_id: String` + + The ID of the file to be sent to the model. + + - `file_url: 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: :in_progress | :completed | :incomplete` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `type: :function_call_output` + + The type of the function tool call output. Always `function_call_output`. + + - `:function_call_output` + + - `created_by: String` + + The identifier of the actor that created the item. + + - `class ResponseFunctionWebSearch` + + The results of a web search tool call. See the + [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information. + + - `id: String` + + The unique ID of the web search tool call. + + - `action: Search{ type, queries, query, sources} | OpenPage{ type, url} | FindInPage{ pattern, type, url}` + + 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). + + - `class Search` + + Action type "search" - Performs a web search query. + + - `type: :search` + + The action type. + + - `:search` + + - `queries: Array[String]` + + The search queries. + + - `query: String` + + The search query. + + - `sources: Array[Source{ type, url}]` + + The sources used in the search. + + - `type: :url` + + The type of source. Always `url`. + + - `:url` + + - `url: String` + + The URL of the source. + + - `class OpenPage` + + Action type "open_page" - Opens a specific URL from search results. + + - `type: :open_page` + + The action type. + + - `:open_page` + + - `url: String` + + The URL opened by the model. + + - `class FindInPage` + + 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: :find_in_page` + + The action type. + + - `:find_in_page` + + - `url: String` + + The URL of the page searched for the pattern. + + - `status: :in_progress | :searching | :completed | :failed` + + The status of the web search tool call. + + - `:in_progress` + + - `:searching` + + - `:completed` + + - `:failed` + + - `type: :web_search_call` + + The type of the web search tool call. Always `web_search_call`. + + - `:web_search_call` + + - `class ResponseComputerToolCall` + + A tool call to a computer use tool. See the + [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information. + + - `id: String` + + The unique ID of the computer call. + + - `call_id: String` + + An identifier used when responding to the tool call with output. + + - `pending_safety_checks: Array[PendingSafetyCheck{ id, code, message}]` + + 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: :in_progress | :completed | :incomplete` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `type: :computer_call` + + The type of the computer call. Always `computer_call`. + + - `:computer_call` + + - `action: Click{ button, type, x, 2 more} | DoubleClick{ keys, type, x, y_} | Drag{ path, type, keys} | 6 more` + + A click action. + + - `class Click` + + A click action. + + - `button: :left | :right | :wheel | 2 more` + + Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. + + - `:left` + + - `:right` + + - `:wheel` + + - `:back` + + - `:forward` + + - `type: :click` + + Specifies the event type. For a click action, this property is always `click`. + + - `:click` + + - `x: Integer` + + The x-coordinate where the click occurred. + + - `y_: Integer` + + The y-coordinate where the click occurred. + + - `keys: Array[String]` + + The keys being held while clicking. + + - `class DoubleClick` + + A double click action. + + - `keys: Array[String]` + + The keys being held while double-clicking. + + - `type: :double_click` + + Specifies the event type. For a double click action, this property is always set to `double_click`. + + - `:double_click` + + - `x: Integer` + + The x-coordinate where the double click occurred. + + - `y_: Integer` + + The y-coordinate where the double click occurred. + + - `class Drag` + + A drag action. + + - `path: Array[Path{ x, y_}]` + + 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: Integer` + + The x-coordinate. + + - `y_: Integer` + + The y-coordinate. + + - `type: :drag` + + Specifies the event type. For a drag action, this property is always set to `drag`. + + - `:drag` + + - `keys: Array[String]` + + The keys being held while dragging the mouse. + + - `class Keypress` + + A collection of keypresses the model would like to perform. + + - `keys: Array[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`. + + - `:keypress` + + - `class Move` + + A mouse move action. + + - `type: :move` + + Specifies the event type. For a move action, this property is always set to `move`. + + - `:move` + + - `x: Integer` + + The x-coordinate to move to. + + - `y_: Integer` + + The y-coordinate to move to. + + - `keys: Array[String]` + + The keys being held while moving the mouse. + + - `class Screenshot` + + A screenshot action. + + - `type: :screenshot` + + Specifies the event type. For a screenshot action, this property is always set to `screenshot`. + + - `:screenshot` + + - `class Scroll` + + A scroll action. + + - `scroll_x: Integer` + + The horizontal scroll distance. + + - `scroll_y: Integer` + + The vertical scroll distance. + + - `type: :scroll` + + Specifies the event type. For a scroll action, this property is always set to `scroll`. + + - `:scroll` + + - `x: Integer` + + The x-coordinate where the scroll occurred. + + - `y_: Integer` + + The y-coordinate where the scroll occurred. + + - `keys: Array[String]` + + The keys being held while scrolling. + + - `class Type` + + 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`. + + - `:type` + + - `class Wait` + + A wait action. + + - `type: :wait` + + Specifies the event type. For a wait action, this property is always set to `wait`. + + - `:wait` + + - `actions: ComputerActionList` + + Flattened batched actions for `computer_use`. Each action includes an + `type` discriminator and action-specific fields. + + - `class Click` + + A click action. + + - `button: :left | :right | :wheel | 2 more` + + Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. + + - `:left` + + - `:right` + + - `:wheel` + + - `:back` + + - `:forward` + + - `type: :click` + + Specifies the event type. For a click action, this property is always `click`. + + - `:click` + + - `x: Integer` + + The x-coordinate where the click occurred. + + - `y_: Integer` + + The y-coordinate where the click occurred. + + - `keys: Array[String]` + + The keys being held while clicking. + + - `class DoubleClick` + + A double click action. + + - `keys: Array[String]` + + The keys being held while double-clicking. + + - `type: :double_click` + + Specifies the event type. For a double click action, this property is always set to `double_click`. + + - `:double_click` + + - `x: Integer` + + The x-coordinate where the double click occurred. + + - `y_: Integer` + + The y-coordinate where the double click occurred. + + - `class Drag` + + A drag action. + + - `path: Array[Path{ x, y_}]` + + 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: Integer` + + The x-coordinate. + + - `y_: Integer` + + The y-coordinate. + + - `type: :drag` + + Specifies the event type. For a drag action, this property is always set to `drag`. + + - `:drag` + + - `keys: Array[String]` + + The keys being held while dragging the mouse. + + - `class Keypress` + + A collection of keypresses the model would like to perform. + + - `keys: Array[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`. + + - `:keypress` + + - `class Move` + + A mouse move action. + + - `type: :move` + + Specifies the event type. For a move action, this property is always set to `move`. + + - `:move` + + - `x: Integer` + + The x-coordinate to move to. + + - `y_: Integer` + + The y-coordinate to move to. + + - `keys: Array[String]` + + The keys being held while moving the mouse. + + - `class Screenshot` + + A screenshot action. + + - `type: :screenshot` + + Specifies the event type. For a screenshot action, this property is always set to `screenshot`. + + - `:screenshot` + + - `class Scroll` + + A scroll action. + + - `scroll_x: Integer` + + The horizontal scroll distance. + + - `scroll_y: Integer` + + The vertical scroll distance. + + - `type: :scroll` + + Specifies the event type. For a scroll action, this property is always set to `scroll`. + + - `:scroll` + + - `x: Integer` + + The x-coordinate where the scroll occurred. + + - `y_: Integer` + + The y-coordinate where the scroll occurred. + + - `keys: Array[String]` + + The keys being held while scrolling. + + - `class Type` + + 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`. + + - `:type` + + - `class Wait` + + A wait action. + + - `type: :wait` + + Specifies the event type. For a wait action, this property is always set to `wait`. + + - `:wait` + + - `class ResponseComputerToolCallOutputItem` + + - `id: String` + + The unique ID of the computer call tool output. + + - `call_id: 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: :computer_screenshot` + + Specifies the event type. For a computer screenshot, this property is + always set to `computer_screenshot`. + + - `:computer_screenshot` + + - `file_id: String` + + The identifier of an uploaded file that contains the screenshot. + + - `image_url: String` + + The URL of the screenshot image. + + - `status: :completed | :incomplete | :failed | :in_progress` + + The status of the message input. One of `in_progress`, `completed`, or + `incomplete`. Populated when input items are returned via API. + + - `:completed` + + - `:incomplete` + + - `:failed` + + - `:in_progress` + + - `type: :computer_call_output` + + The type of the computer tool call output. Always `computer_call_output`. + + - `:computer_call_output` + + - `acknowledged_safety_checks: Array[AcknowledgedSafetyCheck{ id, code, message}]` + + 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. + + - `created_by: String` + + The identifier of the actor that created the item. + + - `class ResponseReasoningItem` + + 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](https://platform.openai.com/docs/guides/conversation-state). + + - `id: String` + + The unique identifier of the reasoning content. + + - `summary: Array[Summary{ text, type}]` + + Reasoning summary content. + + - `text: String` + + A summary of the reasoning output from the model so far. + + - `type: :summary_text` + + The type of the object. Always `summary_text`. + + - `:summary_text` + + - `type: :reasoning` + + The type of the object. Always `reasoning`. + + - `:reasoning` + + - `content: Array[Content{ text, type}]` + + Reasoning text content. + + - `text: String` + + The reasoning text from the model. + + - `type: :reasoning_text` + + The type of the reasoning text. Always `reasoning_text`. + + - `:reasoning_text` + + - `encrypted_content: String` + + The encrypted content of the reasoning item - populated when a response is + generated with `reasoning.encrypted_content` in the `include` parameter. + + - `status: :in_progress | :completed | :incomplete` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `class ResponseToolSearchCall` + + - `id: String` + + The unique ID of the tool search call item. + + - `arguments: untyped` + + Arguments used for the tool search call. + + - `call_id: String` + + The unique ID of the tool search call generated by the model. + + - `execution: :server | :client` + + Whether tool search was executed by the server or by the client. + + - `:server` + + - `:client` + + - `status: :in_progress | :completed | :incomplete` + + The status of the tool search call item that was recorded. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `type: :tool_search_call` + + The type of the item. Always `tool_search_call`. + + - `:tool_search_call` + + - `created_by: String` + + The identifier of the actor that created the item. + + - `class ResponseToolSearchOutputItem` + + - `id: String` + + The unique ID of the tool search output item. + + - `call_id: String` + + The unique ID of the tool search call generated by the model. + + - `execution: :server | :client` + + Whether tool search was executed by the server or by the client. + + - `:server` + + - `:client` + + - `status: :in_progress | :completed | :incomplete` + + The status of the tool search output item that was recorded. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `tools: Array[Tool]` + + The loaded tool definitions returned by tool search. + + - `class FunctionTool` + + Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling). + + - `name: String` + + The name of the function to call. + + - `parameters: Hash[Symbol, untyped]` + + 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`. + + - `:function` + + - `defer_loading: 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. + + - `class FileSearchTool` + + A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://platform.openai.com/docs/guides/tools-file-search). + + - `type: :file_search` + + The type of the file search tool. Always `file_search`. + + - `:file_search` + + - `vector_store_ids: Array[String]` + + The IDs of the vector stores to search. + + - `filters: ComparisonFilter | CompoundFilter` + + A filter to apply. + + - `class ComparisonFilter` + + 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: :eq | :ne | :gt | 5 more` + + 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 + + - `:eq` + + - `:ne` + + - `:gt` + + - `:gte` + + - `:lt` + + - `:lte` + + - `:in` + + - `:nin` + + - `value: String | Float | bool | Array[String | Float]` + + The value to compare against the attribute key; supports string, number, or boolean types. + + - `String = String` + + - `Float = Float` + + - `UnionMember2 = bool` + + - `UnionMember3 = Array[String | Float]` + + - `String = String` + + - `Float = Float` + + - `class CompoundFilter` + + Combine multiple filters using `and` or `or`. + + - `filters: Array[ComparisonFilter | untyped]` + + Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`. + + - `class ComparisonFilter` + + A filter used to compare a specified attribute key to a given value using a defined comparison operation. + + - `UnionMember1 = untyped` + + - `type: :and | :or` + + Type of operation: `and` or `or`. + + - `:and` + + - `:or` + + - `max_num_results: Integer` + + The maximum number of results to return. This number should be between 1 and 50 inclusive. + + - `ranking_options: RankingOptions{ hybrid_search, ranker, score_threshold}` + + Ranking options for search. + + - `hybrid_search: HybridSearch{ embedding_weight, text_weight}` + + Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. + + - `embedding_weight: Float` + + The weight of the embedding in the reciprocal ranking fusion. + + - `text_weight: Float` + + The weight of the text in the reciprocal ranking fusion. + + - `ranker: :auto | :"default-2024-11-15"` + + The ranker to use for the file search. + + - `:auto` + + - `:"default-2024-11-15"` + + - `score_threshold: Float` + + 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. + + - `class ComputerTool` + + A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use). + + - `type: :computer` + + The type of the computer tool. Always `computer`. + + - `:computer` + + - `class ComputerUsePreviewTool` + + A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use). + + - `display_height: Integer` + + The height of the computer display. + + - `display_width: Integer` + + The width of the computer display. + + - `environment: :windows | :mac | :linux | 2 more` + + The type of computer environment to control. + + - `:windows` + + - `:mac` + + - `:linux` + + - `:ubuntu` + + - `:browser` + + - `type: :computer_use_preview` + + The type of the computer use tool. Always `computer_use_preview`. + + - `:computer_use_preview` + + - `class WebSearchTool` + + Search the Internet for sources related to the prompt. Learn more about the + [web search tool](https://platform.openai.com/docs/guides/tools-web-search). + + - `type: :web_search | :web_search_2025_08_26` + + The type of the web search tool. One of `web_search` or `web_search_2025_08_26`. + + - `:web_search` + + - `:web_search_2025_08_26` + + - `filters: Filters{ allowed_domains}` + + Filters for the search. + + - `allowed_domains: Array[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"]` + + - `search_context_size: :low | :medium | :high` + + 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. + + - `:low` + + - `:medium` + + - `:high` + + - `user_location: UserLocation{ city, country, region, 2 more}` + + 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](https://en.wikipedia.org/wiki/ISO_3166-1) 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](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. + + - `type: :approximate` + + The type of location approximation. Always `approximate`. + + - `:approximate` + + - `class Mcp` + + Give the model access to additional tools via remote Model Context Protocol + (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). + + - `server_label: String` + + A label for this MCP server, used to identify it in tool calls. + + - `type: :mcp` + + The type of the MCP tool. Always `mcp`. + + - `:mcp` + + - `allowed_tools: Array[String] | McpToolFilter{ read_only, tool_names}` + + List of allowed tool names or a filter object. + + - `McpAllowedTools = Array[String]` + + A string array of allowed tool names + + - `class McpToolFilter` + + A filter object to specify which tools are allowed. + + - `read_only: bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `tool_names: Array[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. + + - `connector_id: :connector_dropbox | :connector_gmail | :connector_googlecalendar | 5 more` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + 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` + + - `:connector_dropbox` + + - `:connector_gmail` + + - `:connector_googlecalendar` + + - `:connector_googledrive` + + - `:connector_microsoftteams` + + - `:connector_outlookcalendar` + + - `:connector_outlookemail` + + - `:connector_sharepoint` + + - `defer_loading: bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `headers: Hash[Symbol, String]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `require_approval: McpToolApprovalFilter{ always, never} | :always | :never` + + Specify which of the MCP server's tools require approval. + + - `class McpToolApprovalFilter` + + 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: Always{ read_only, tool_names}` + + A filter object to specify which tools are allowed. + + - `read_only: bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `tool_names: Array[String]` + + List of allowed tool names. + + - `never: Never{ read_only, tool_names}` + + A filter object to specify which tools are allowed. + + - `read_only: bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `tool_names: Array[String]` + + List of allowed tool names. + + - `McpToolApprovalSetting = :always | :never` + + 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. + + - `:always` + + - `:never` + + - `server_description: String` + + Optional description of the MCP server, used to provide more context. + + - `server_url: String` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + + - `class CodeInterpreter` + + A tool that runs Python code to help generate a response to a prompt. + + - `container: String | CodeInterpreterToolAuto{ type, file_ids, memory_limit, network_policy}` + + 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 = String` + + The container ID. + + - `class CodeInterpreterToolAuto` + + Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on. + + - `type: :auto` + + Always `auto`. + + - `:auto` + + - `file_ids: Array[String]` + + An optional list of uploaded files to make available to your code. + + - `memory_limit: :"1g" | :"4g" | :"16g" | :"64g"` + + The memory limit for the code interpreter container. + + - `:"1g"` + + - `:"4g"` + + - `:"16g"` + + - `:"64g"` + + - `network_policy: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` + + Network access policy for the container. + + - `class ContainerNetworkPolicyDisabled` + + - `type: :disabled` + + Disable outbound network access. Always `disabled`. + + - `:disabled` + + - `class ContainerNetworkPolicyAllowlist` + + - `allowed_domains: Array[String]` + + A list of allowed domains when type is `allowlist`. + + - `type: :allowlist` + + Allow outbound network access only to specified domains. Always `allowlist`. + + - `:allowlist` + + - `domain_secrets: Array[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: :code_interpreter` + + The type of the code interpreter tool. Always `code_interpreter`. + + - `:code_interpreter` + + - `class ImageGeneration` + + A tool that generates images using the GPT image models. + + - `type: :image_generation` + + The type of the image generation tool. Always `image_generation`. + + - `:image_generation` + + - `action: :generate | :edit | :auto` + + Whether to generate a new image or edit an existing image. Default: `auto`. + + - `:generate` + + - `:edit` + + - `:auto` + + - `background: :transparent | :opaque | :auto` + + 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`. + + - `:transparent` + + - `:opaque` + + - `:auto` + + - `input_fidelity: :high | :low` + + 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`. + + - `:high` + + - `:low` + + - `input_image_mask: InputImageMask{ file_id, image_url}` + + Optional mask for inpainting. Contains `image_url` + (string, optional) and `file_id` (string, optional). + + - `file_id: String` + + File ID for the mask image. + + - `image_url: String` + + Base64-encoded mask image. + + - `model: String | :"gpt-image-1" | :"gpt-image-1-mini" | :"gpt-image-2" | 3 more` + + The image generation model to use. Default: `gpt-image-1`. + + - `String = String` + + - `Model = :"gpt-image-1" | :"gpt-image-1-mini" | :"gpt-image-2" | 3 more` + + The image generation model to use. Default: `gpt-image-1`. + + - `:"gpt-image-1"` + + - `:"gpt-image-1-mini"` + + - `:"gpt-image-2"` + + - `:"gpt-image-2-2026-04-21"` + + - `:"gpt-image-1.5"` + + - `:"chatgpt-image-latest"` + + - `moderation: :auto | :low` + + Moderation level for the generated image. Default: `auto`. + + - `:auto` + + - `:low` + + - `output_compression: Integer` + + Compression level for the output image. Default: 100. + + - `output_format: :png | :webp | :jpeg` + + The output format of the generated image. One of `png`, `webp`, or + `jpeg`. Default: `png`. + + - `:png` + + - `:webp` + + - `:jpeg` + + - `partial_images: Integer` + + Number of partial images to generate in streaming mode, from 0 (default value) to 3. + + - `quality: :low | :medium | :high | :auto` + + The quality of the generated image. One of `low`, `medium`, `high`, + or `auto`. Default: `auto`. + + - `:low` + + - `:medium` + + - `:high` + + - `:auto` + + - `size: String | :"1024x1024" | :"1024x1536" | :"1536x1024" | :auto` + + 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` + + - `Size = :"1024x1024" | :"1024x1536" | :"1536x1024" | :auto` + + 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`. + + - `:"1024x1024"` + + - `:"1024x1536"` + + - `:"1536x1024"` + + - `:auto` + + - `class LocalShell` + + A tool that allows the model to execute shell commands in a local environment. + + - `type: :local_shell` + + The type of the local shell tool. Always `local_shell`. + + - `:local_shell` + + - `class FunctionShellTool` + + A tool that allows the model to execute shell commands. + + - `type: :shell` + + The type of the shell tool. Always `shell`. + + - `:shell` + + - `environment: ContainerAuto | LocalEnvironment | ContainerReference` + + - `class ContainerAuto` + + - `type: :container_auto` + + Automatically creates a container for this request + + - `:container_auto` + + - `file_ids: Array[String]` + + An optional list of uploaded files to make available to your code. + + - `memory_limit: :"1g" | :"4g" | :"16g" | :"64g"` + + The memory limit for the container. + + - `:"1g"` + + - `:"4g"` + + - `:"16g"` + + - `:"64g"` + + - `network_policy: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` + + Network access policy for the container. + + - `class ContainerNetworkPolicyDisabled` + + - `class ContainerNetworkPolicyAllowlist` + + - `skills: Array[SkillReference | InlineSkill]` + + An optional list of skills referenced by id or inline data. + + - `class SkillReference` + + - `skill_id: String` + + The ID of the referenced skill. + + - `type: :skill_reference` + + References a skill created with the /v1/skills endpoint. + + - `:skill_reference` + + - `version: String` + + Optional skill version. Use a positive integer or 'latest'. Omit for default. + + - `class InlineSkill` + + - `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. + + - `media_type: :"application/zip"` + + The media type of the inline skill payload. Must be `application/zip`. + + - `:"application/zip"` + + - `type: :base64` + + The type of the inline skill source. Must be `base64`. + + - `:base64` + + - `type: :inline` + + Defines an inline skill for this request. + + - `:inline` + + - `class LocalEnvironment` + + - `type: :local` + + Use a local computer environment. + + - `:local` + + - `skills: Array[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. + + - `class ContainerReference` + + - `container_id: String` + + The ID of the referenced container. + + - `type: :container_reference` + + References a container created with the /v1/containers endpoint + + - `:container_reference` + + - `class CustomTool` + + A custom tool that processes input using a specified format. Learn more about [custom tools](https://platform.openai.com/docs/guides/function-calling#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`. + + - `:custom` + + - `defer_loading: 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_: CustomToolInputFormat` + + The input format for the custom tool. Default is unconstrained text. + + - `class Text` + + Unconstrained free-form text. + + - `type: :text` + + Unconstrained text format. Always `text`. + + - `:text` + + - `class Grammar` + + A grammar defined by the user. + + - `definition: String` + + The grammar definition. + + - `syntax: :lark | :regex` + + The syntax of the grammar definition. One of `lark` or `regex`. + + - `:lark` + + - `:regex` + + - `type: :grammar` + + Grammar format. Always `grammar`. + + - `:grammar` + + - `class NamespaceTool` + + 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: Array[Function{ name, type, defer_loading, 3 more} | CustomTool]` + + The function/custom tools available inside this namespace. + + - `class Function` + + - `name: String` + + - `type: :function` + + - `:function` + + - `defer_loading: bool` + + Whether this function should be deferred and discovered via tool search. + + - `description: String` + + - `parameters: untyped` + + - `strict: bool` + + - `class CustomTool` + + A custom tool that processes input using a specified format. Learn more about [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools) + + - `type: :namespace` + + The type of the tool. Always `namespace`. + + - `:namespace` + + - `class ToolSearchTool` + + Hosted or BYOT tool search configuration for deferred tools. + + - `type: :tool_search` + + The type of the tool. Always `tool_search`. + + - `:tool_search` + + - `description: String` + + Description shown to the model for a client-executed tool search tool. + + - `execution: :server | :client` + + Whether tool search is executed by the server or by the client. + + - `:server` + + - `:client` + + - `parameters: untyped` + + Parameter schema for a client-executed tool search tool. + + - `class WebSearchPreviewTool` + + This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search). + + - `type: :web_search_preview | :web_search_preview_2025_03_11` + + The type of the web search tool. One of `web_search_preview` or `web_search_preview_2025_03_11`. + + - `:web_search_preview` + + - `:web_search_preview_2025_03_11` + + - `search_content_types: Array[:text | :image]` + + - `:text` + + - `:image` + + - `search_context_size: :low | :medium | :high` + + 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. + + - `:low` + + - `:medium` + + - `:high` + + - `user_location: UserLocation{ type, city, country, 2 more}` + + The user's location. + + - `type: :approximate` + + The type of location approximation. Always `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](https://en.wikipedia.org/wiki/ISO_3166-1) 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](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. + + - `class ApplyPatchTool` + + Allows the assistant to create, delete, or update files using unified diffs. + + - `type: :apply_patch` + + The type of the tool. Always `apply_patch`. + + - `:apply_patch` + + - `type: :tool_search_output` + + The type of the item. Always `tool_search_output`. + + - `:tool_search_output` + + - `created_by: String` + + The identifier of the actor that created the item. + + - `class AdditionalTools` + + - `id: String` + + The unique ID of the additional tools item. + + - `role: :unknown | :user | :assistant | 5 more` + + The role that provided the additional tools. + + - `:unknown` + + - `:user` + + - `:assistant` + + - `:system` + + - `:critic` + + - `:discriminator` + + - `:developer` + + - `:tool` + + - `tools: Array[Tool]` + + The additional tool definitions made available at this item. + + - `class FunctionTool` + + Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling). + + - `class FileSearchTool` + + A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://platform.openai.com/docs/guides/tools-file-search). + + - `class ComputerTool` + + A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use). + + - `class ComputerUsePreviewTool` + + A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use). + + - `class WebSearchTool` + + Search the Internet for sources related to the prompt. Learn more about the + [web search tool](https://platform.openai.com/docs/guides/tools-web-search). + + - `class Mcp` + + Give the model access to additional tools via remote Model Context Protocol + (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). + + - `class CodeInterpreter` + + A tool that runs Python code to help generate a response to a prompt. + + - `class ImageGeneration` + + A tool that generates images using the GPT image models. + + - `class LocalShell` + + A tool that allows the model to execute shell commands in a local environment. + + - `class FunctionShellTool` + + A tool that allows the model to execute shell commands. + + - `class CustomTool` + + A custom tool that processes input using a specified format. Learn more about [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools) + + - `class NamespaceTool` + + Groups function/custom tools under a shared namespace. + + - `class ToolSearchTool` + + Hosted or BYOT tool search configuration for deferred tools. + + - `class WebSearchPreviewTool` + + This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search). + + - `class ApplyPatchTool` + + Allows the assistant to create, delete, or update files using unified diffs. + + - `type: :additional_tools` + + The type of the item. Always `additional_tools`. + + - `:additional_tools` + + - `class ResponseCompactionItem` + + A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). + + - `id: String` + + The unique ID of the compaction item. + + - `encrypted_content: String` + + The encrypted content that was produced by compaction. + + - `type: :compaction` + + The type of the item. Always `compaction`. + + - `:compaction` + + - `created_by: String` + + The identifier of the actor that created the item. + + - `class ImageGenerationCall` + + 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: :in_progress | :completed | :generating | :failed` + + The status of the image generation call. + + - `:in_progress` + + - `:completed` + + - `:generating` + + - `:failed` + + - `type: :image_generation_call` + + The type of the image generation call. Always `image_generation_call`. + + - `:image_generation_call` + + - `class ResponseCodeInterpreterToolCall` + + 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. + + - `container_id: String` + + The ID of the container used to run the code. + + - `outputs: Array[Logs{ logs, type} | Image{ type, url}]` + + The outputs generated by the code interpreter, such as logs or images. + Can be null if no outputs are available. + + - `class Logs` + + 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`. + + - `:logs` + + - `class Image` + + The image output from the code interpreter. + + - `type: :image` + + The type of the output. Always `image`. + + - `:image` + + - `url: String` + + The URL of the image output from the code interpreter. + + - `status: :in_progress | :completed | :incomplete | 2 more` + + The status of the code interpreter tool call. Valid values are `in_progress`, `completed`, `incomplete`, `interpreting`, and `failed`. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `:interpreting` + + - `:failed` + + - `type: :code_interpreter_call` + + The type of the code interpreter tool call. Always `code_interpreter_call`. + + - `:code_interpreter_call` + + - `class LocalShellCall` + + A tool call to run a command on the local shell. + + - `id: String` + + The unique ID of the local shell call. + + - `action: Action{ command, env, type, 3 more}` + + Execute a shell command on the server. + + - `command: Array[String]` + + The command to run. + + - `env: Hash[Symbol, String]` + + Environment variables to set for the command. + + - `type: :exec` + + The type of the local shell action. Always `exec`. + + - `:exec` + + - `timeout_ms: Integer` + + Optional timeout in milliseconds for the command. + + - `user: String` + + Optional user to run the command as. + + - `working_directory: String` + + Optional working directory to run the command in. + + - `call_id: String` + + The unique ID of the local shell tool call generated by the model. + + - `status: :in_progress | :completed | :incomplete` + + The status of the local shell call. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `type: :local_shell_call` + + The type of the local shell call. Always `local_shell_call`. + + - `:local_shell_call` + + - `class LocalShellCallOutput` + + 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: :local_shell_call_output` + + The type of the local shell tool call output. Always `local_shell_call_output`. + + - `:local_shell_call_output` + + - `status: :in_progress | :completed | :incomplete` + + The status of the item. One of `in_progress`, `completed`, or `incomplete`. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `class ResponseFunctionShellToolCall` + + 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: Action{ commands, max_output_length, timeout_ms}` + + The shell commands and limits that describe how to run the tool call. + + - `commands: Array[String]` + + - `max_output_length: Integer` + + Optional maximum number of characters to return from each command. + + - `timeout_ms: Integer` + + Optional timeout in milliseconds for the commands. + + - `call_id: String` + + The unique ID of the shell tool call generated by the model. + + - `environment: ResponseLocalEnvironment | ResponseContainerReference` + + Represents the use of a local environment to perform shell actions. + + - `class ResponseLocalEnvironment` + + Represents the use of a local environment to perform shell actions. + + - `type: :local` + + The environment type. Always `local`. + + - `:local` + + - `class ResponseContainerReference` + + Represents a container created with /v1/containers. + + - `container_id: String` + + - `type: :container_reference` + + The environment type. Always `container_reference`. + + - `:container_reference` + + - `status: :in_progress | :completed | :incomplete` + + The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `type: :shell_call` + + The type of the item. Always `shell_call`. + + - `:shell_call` + + - `created_by: String` + + The ID of the entity that created this tool call. + + - `class ResponseFunctionShellToolCallOutput` + + 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. + + - `call_id: String` + + The unique ID of the shell tool call generated by the model. + + - `max_output_length: Integer` + + The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. + + - `output: Array[Output{ outcome, stderr, stdout, created_by}]` + + An array of shell call output contents + + - `outcome: Timeout{ type} | Exit{ exit_code, type}` + + Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk. + + - `class Timeout` + + Indicates that the shell call exceeded its configured time limit. + + - `type: :timeout` + + The outcome type. Always `timeout`. + + - `:timeout` + + - `class Exit` + + Indicates that the shell commands finished and returned an exit code. + + - `exit_code: Integer` + + Exit code from the shell process. + + - `type: :exit` + + The outcome type. Always `exit`. + + - `:exit` + + - `stderr: String` + + The standard error output that was captured. + + - `stdout: String` + + The standard output that was captured. + + - `created_by: String` + + The identifier of the actor that created the item. + + - `status: :in_progress | :completed | :incomplete` + + The status of the shell call output. One of `in_progress`, `completed`, or `incomplete`. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `type: :shell_call_output` + + The type of the shell call output. Always `shell_call_output`. + + - `:shell_call_output` + + - `created_by: String` + + The identifier of the actor that created the item. + + - `class ResponseApplyPatchToolCall` + + 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. + + - `call_id: String` + + The unique ID of the apply patch tool call generated by the model. + + - `operation: CreateFile{ diff, path, type} | DeleteFile{ path, type} | UpdateFile{ diff, path, type}` + + One of the create_file, delete_file, or update_file operations applied via apply_patch. + + - `class CreateFile` + + 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: :create_file` + + Create a new file with the provided diff. + + - `:create_file` + + - `class DeleteFile` + + Instruction describing how to delete a file via the apply_patch tool. + + - `path: String` + + Path of the file to delete. + + - `type: :delete_file` + + Delete the specified file. + + - `:delete_file` + + - `class UpdateFile` + + 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: :update_file` + + Update an existing file with the provided diff. + + - `:update_file` + + - `status: :in_progress | :completed` + + The status of the apply patch tool call. One of `in_progress` or `completed`. + + - `:in_progress` + + - `:completed` + + - `type: :apply_patch_call` + + The type of the item. Always `apply_patch_call`. + + - `:apply_patch_call` + + - `created_by: String` + + The ID of the entity that created this tool call. + + - `class ResponseApplyPatchToolCallOutput` + + 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. + + - `call_id: String` + + The unique ID of the apply patch tool call generated by the model. + + - `status: :completed | :failed` + + The status of the apply patch tool call output. One of `completed` or `failed`. + + - `:completed` + + - `:failed` + + - `type: :apply_patch_call_output` + + The type of the item. Always `apply_patch_call_output`. + + - `:apply_patch_call_output` + + - `created_by: String` + + The ID of the entity that created this tool call output. + + - `output: String` + + Optional textual output returned by the apply patch tool. + + - `class McpCall` + + 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. + + - `server_label: String` + + The label of the MCP server running the tool. + + - `type: :mcp_call` + + The type of the item. Always `mcp_call`. + + - `:mcp_call` + + - `approval_request_id: 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: :in_progress | :completed | :incomplete | 2 more` + + The status of the tool call. One of `in_progress`, `completed`, `incomplete`, `calling`, or `failed`. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `:calling` + + - `:failed` + + - `class McpListTools` + + A list of tools available on an MCP server. + + - `id: String` + + The unique ID of the list. + + - `server_label: String` + + The label of the MCP server. + + - `tools: Array[Tool{ input_schema, name, annotations, description}]` + + The tools available on the server. + + - `input_schema: untyped` + + The JSON schema describing the tool's input. + + - `name: String` + + The name of the tool. + + - `annotations: untyped` + + Additional annotations about the tool. + + - `description: String` + + The description of the tool. + + - `type: :mcp_list_tools` + + The type of the item. Always `mcp_list_tools`. + + - `:mcp_list_tools` + + - `error: String` + + Error message if the server could not list tools. + + - `class McpApprovalRequest` + + 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. + + - `server_label: String` + + The label of the MCP server making the request. + + - `type: :mcp_approval_request` + + The type of the item. Always `mcp_approval_request`. + + - `:mcp_approval_request` + + - `class McpApprovalResponse` + + A response to an MCP approval request. + + - `id: String` + + The unique ID of the approval response + + - `approval_request_id: String` + + The ID of the approval request being answered. + + - `approve: bool` + + Whether the request was approved. + + - `type: :mcp_approval_response` + + The type of the item. Always `mcp_approval_response`. + + - `:mcp_approval_response` + + - `reason: String` + + Optional reason for the decision. + + - `class ResponseCustomToolCall` + + A call to a custom tool created by the model. + + - `call_id: 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: :custom_tool_call` + + The type of the custom tool call. Always `custom_tool_call`. + + - `: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. + + - `class ResponseCustomToolCallOutputItem` + + 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: :in_progress | :completed | :incomplete` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `:in_progress` + + - `:completed` + + - `:incomplete` + + - `created_by: String` + + The identifier of the actor that created the item. + + - `usage: ResponseUsage` + + Token accounting for the compaction pass, including cached, reasoning, and total tokens. + + - `input_tokens: Integer` + + The number of input tokens. + + - `input_tokens_details: InputTokensDetails{ cached_tokens}` + + A detailed breakdown of the input tokens. + + - `cached_tokens: Integer` + + The number of tokens that were retrieved from the cache. + [More on prompt caching](https://platform.openai.com/docs/guides/prompt-caching). + + - `output_tokens: Integer` + + The number of output tokens. + + - `output_tokens_details: OutputTokensDetails{ reasoning_tokens}` + + A detailed breakdown of the output tokens. + + - `reasoning_tokens: Integer` + + The number of reasoning tokens. + + - `total_tokens: Integer` + + The total number of tokens used. + +### Example + +```ruby +require "openai" + +openai = OpenAI::Client.new(api_key: "My API Key") + +compacted_response = openai.responses.compact(model: :"gpt-5.4") + +puts(compacted_response) +``` + +#### Response + +```json +{ + "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 + } +} +```