diff --git a/en/java/resources/responses/methods/compact/index.md b/en/java/resources/responses/methods/compact/index.md new file mode 100644 index 0000000..bf966d5 --- /dev/null +++ b/en/java/resources/responses/methods/compact/index.md @@ -0,0 +1,6163 @@ +## Compact a response + +`CompactedResponse responses().compact(ResponseCompactParamsparams, RequestOptionsrequestOptions = RequestOptions.none())` + +**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 + +- `ResponseCompactParams params` + + - `Optional model` + + 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")` + + - `GPT_5_4_MINI("gpt-5.4-mini")` + + - `GPT_5_4_NANO("gpt-5.4-nano")` + + - `GPT_5_4_MINI_2026_03_17("gpt-5.4-mini-2026-03-17")` + + - `GPT_5_4_NANO_2026_03_17("gpt-5.4-nano-2026-03-17")` + + - `GPT_5_3_CHAT_LATEST("gpt-5.3-chat-latest")` + + - `GPT_5_2("gpt-5.2")` + + - `GPT_5_2_2025_12_11("gpt-5.2-2025-12-11")` + + - `GPT_5_2_CHAT_LATEST("gpt-5.2-chat-latest")` + + - `GPT_5_2_PRO("gpt-5.2-pro")` + + - `GPT_5_2_PRO_2025_12_11("gpt-5.2-pro-2025-12-11")` + + - `GPT_5_1("gpt-5.1")` + + - `GPT_5_1_2025_11_13("gpt-5.1-2025-11-13")` + + - `GPT_5_1_CODEX("gpt-5.1-codex")` + + - `GPT_5_1_MINI("gpt-5.1-mini")` + + - `GPT_5_1_CHAT_LATEST("gpt-5.1-chat-latest")` + + - `GPT_5("gpt-5")` + + - `GPT_5_MINI("gpt-5-mini")` + + - `GPT_5_NANO("gpt-5-nano")` + + - `GPT_5_2025_08_07("gpt-5-2025-08-07")` + + - `GPT_5_MINI_2025_08_07("gpt-5-mini-2025-08-07")` + + - `GPT_5_NANO_2025_08_07("gpt-5-nano-2025-08-07")` + + - `GPT_5_CHAT_LATEST("gpt-5-chat-latest")` + + - `GPT_4_1("gpt-4.1")` + + - `GPT_4_1_MINI("gpt-4.1-mini")` + + - `GPT_4_1_NANO("gpt-4.1-nano")` + + - `GPT_4_1_2025_04_14("gpt-4.1-2025-04-14")` + + - `GPT_4_1_MINI_2025_04_14("gpt-4.1-mini-2025-04-14")` + + - `GPT_4_1_NANO_2025_04_14("gpt-4.1-nano-2025-04-14")` + + - `O4_MINI("o4-mini")` + + - `O4_MINI_2025_04_16("o4-mini-2025-04-16")` + + - `O3("o3")` + + - `O3_2025_04_16("o3-2025-04-16")` + + - `O3_MINI("o3-mini")` + + - `O3_MINI_2025_01_31("o3-mini-2025-01-31")` + + - `O1("o1")` + + - `O1_2024_12_17("o1-2024-12-17")` + + - `O1_PREVIEW("o1-preview")` + + - `O1_PREVIEW_2024_09_12("o1-preview-2024-09-12")` + + - `O1_MINI("o1-mini")` + + - `O1_MINI_2024_09_12("o1-mini-2024-09-12")` + + - `GPT_4O("gpt-4o")` + + - `GPT_4O_2024_11_20("gpt-4o-2024-11-20")` + + - `GPT_4O_2024_08_06("gpt-4o-2024-08-06")` + + - `GPT_4O_2024_05_13("gpt-4o-2024-05-13")` + + - `GPT_4O_AUDIO_PREVIEW("gpt-4o-audio-preview")` + + - `GPT_4O_AUDIO_PREVIEW_2024_10_01("gpt-4o-audio-preview-2024-10-01")` + + - `GPT_4O_AUDIO_PREVIEW_2024_12_17("gpt-4o-audio-preview-2024-12-17")` + + - `GPT_4O_AUDIO_PREVIEW_2025_06_03("gpt-4o-audio-preview-2025-06-03")` + + - `GPT_4O_MINI_AUDIO_PREVIEW("gpt-4o-mini-audio-preview")` + + - `GPT_4O_MINI_AUDIO_PREVIEW_2024_12_17("gpt-4o-mini-audio-preview-2024-12-17")` + + - `GPT_4O_SEARCH_PREVIEW("gpt-4o-search-preview")` + + - `GPT_4O_MINI_SEARCH_PREVIEW("gpt-4o-mini-search-preview")` + + - `GPT_4O_SEARCH_PREVIEW_2025_03_11("gpt-4o-search-preview-2025-03-11")` + + - `GPT_4O_MINI_SEARCH_PREVIEW_2025_03_11("gpt-4o-mini-search-preview-2025-03-11")` + + - `CHATGPT_4O_LATEST("chatgpt-4o-latest")` + + - `CODEX_MINI_LATEST("codex-mini-latest")` + + - `GPT_4O_MINI("gpt-4o-mini")` + + - `GPT_4O_MINI_2024_07_18("gpt-4o-mini-2024-07-18")` + + - `GPT_4_TURBO("gpt-4-turbo")` + + - `GPT_4_TURBO_2024_04_09("gpt-4-turbo-2024-04-09")` + + - `GPT_4_0125_PREVIEW("gpt-4-0125-preview")` + + - `GPT_4_TURBO_PREVIEW("gpt-4-turbo-preview")` + + - `GPT_4_1106_PREVIEW("gpt-4-1106-preview")` + + - `GPT_4_VISION_PREVIEW("gpt-4-vision-preview")` + + - `GPT_4("gpt-4")` + + - `GPT_4_0314("gpt-4-0314")` + + - `GPT_4_0613("gpt-4-0613")` + + - `GPT_4_32K("gpt-4-32k")` + + - `GPT_4_32K_0314("gpt-4-32k-0314")` + + - `GPT_4_32K_0613("gpt-4-32k-0613")` + + - `GPT_3_5_TURBO("gpt-3.5-turbo")` + + - `GPT_3_5_TURBO_16K("gpt-3.5-turbo-16k")` + + - `GPT_3_5_TURBO_0301("gpt-3.5-turbo-0301")` + + - `GPT_3_5_TURBO_0613("gpt-3.5-turbo-0613")` + + - `GPT_3_5_TURBO_1106("gpt-3.5-turbo-1106")` + + - `GPT_3_5_TURBO_0125("gpt-3.5-turbo-0125")` + + - `GPT_3_5_TURBO_16K_0613("gpt-3.5-turbo-16k-0613")` + + - `O1_PRO("o1-pro")` + + - `O1_PRO_2025_03_19("o1-pro-2025-03-19")` + + - `O3_PRO("o3-pro")` + + - `O3_PRO_2025_06_10("o3-pro-2025-06-10")` + + - `O3_DEEP_RESEARCH("o3-deep-research")` + + - `O3_DEEP_RESEARCH_2025_06_26("o3-deep-research-2025-06-26")` + + - `O4_MINI_DEEP_RESEARCH("o4-mini-deep-research")` + + - `O4_MINI_DEEP_RESEARCH_2025_06_26("o4-mini-deep-research-2025-06-26")` + + - `COMPUTER_USE_PREVIEW("computer-use-preview")` + + - `COMPUTER_USE_PREVIEW_2025_03_11("computer-use-preview-2025-03-11")` + + - `GPT_5_CODEX("gpt-5-codex")` + + - `GPT_5_PRO("gpt-5-pro")` + + - `GPT_5_PRO_2025_10_06("gpt-5-pro-2025-10-06")` + + - `GPT_5_1_CODEX_MAX("gpt-5.1-codex-max")` + + - `Optional input` + + Text, image, or file inputs to the model, used to generate a response + + - `String` + + - `List` + + - `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 content` + + Text, image, or audio input to the model, used to generate a response. + Can also contain previous assistant responses. + + - `String` + + - `List` + + - `class ResponseInputText:` + + A text input to the model. + + - `String text` + + The text input to the model. + + - `JsonValue; type "input_text"constant` + + The type of the input item. Always `input_text`. + + - `INPUT_TEXT("input_text")` + + - `class ResponseInputImage:` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `Detail detail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `LOW("low")` + + - `HIGH("high")` + + - `AUTO("auto")` + + - `ORIGINAL("original")` + + - `JsonValue; type "input_image"constant` + + The type of the input item. Always `input_image`. + + - `INPUT_IMAGE("input_image")` + + - `Optional fileId` + + The ID of the file to be sent to the model. + + - `Optional imageUrl` + + 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. + + - `JsonValue; type "input_file"constant` + + The type of the input item. Always `input_file`. + + - `INPUT_FILE("input_file")` + + - `Optional detail` + + 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("low")` + + - `HIGH("high")` + + - `Optional fileData` + + The content of the file to be sent to the model. + + - `Optional fileId` + + The ID of the file to be sent to the model. + + - `Optional fileUrl` + + The URL of the file to be sent to the model. + + - `Optional filename` + + The name of the file to be sent to the model. + + - `Role role` + + The role of the message input. One of `user`, `assistant`, `system`, or + `developer`. + + - `USER("user")` + + - `ASSISTANT("assistant")` + + - `SYSTEM("system")` + + - `DEVELOPER("developer")` + + - `Optional phase` + + 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("commentary")` + + - `FINAL_ANSWER("final_answer")` + + - `Optional type` + + The type of the message input. Always `message`. + + - `MESSAGE("message")` + + - `Message` + + - `List content` + + A list of one or many input items to the model, containing different content + types. + + - `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. + + - `Role role` + + The role of the message input. One of `user`, `system`, or `developer`. + + - `USER("user")` + + - `SYSTEM("system")` + + - `DEVELOPER("developer")` + + - `Optional status` + + The status of item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `Optional type` + + The type of the message input. Always set to `message`. + + - `MESSAGE("message")` + + - `class ResponseOutputMessage:` + + An output message from the model. + + - `String id` + + The unique ID of the output message. + + - `List content` + + The content of the output message. + + - `class ResponseOutputText:` + + A text output from the model. + + - `List annotations` + + The annotations of the text output. + + - `class FileCitation:` + + A citation to a file. + + - `String fileId` + + The ID of the file. + + - `String filename` + + The filename of the file cited. + + - `long index` + + The index of the file in the list of files. + + - `JsonValue; type "file_citation"constant` + + The type of the file citation. Always `file_citation`. + + - `FILE_CITATION("file_citation")` + + - `class UrlCitation:` + + A citation for a web resource used to generate a model response. + + - `long endIndex` + + The index of the last character of the URL citation in the message. + + - `long startIndex` + + The index of the first character of the URL citation in the message. + + - `String title` + + The title of the web resource. + + - `JsonValue; type "url_citation"constant` + + The type of the URL citation. Always `url_citation`. + + - `URL_CITATION("url_citation")` + + - `String url` + + The URL of the web resource. + + - `class ContainerFileCitation:` + + A citation for a container file used to generate a model response. + + - `String containerId` + + The ID of the container file. + + - `long endIndex` + + The index of the last character of the container file citation in the message. + + - `String fileId` + + The ID of the file. + + - `String filename` + + The filename of the container file cited. + + - `long startIndex` + + The index of the first character of the container file citation in the message. + + - `JsonValue; type "container_file_citation"constant` + + The type of the container file citation. Always `container_file_citation`. + + - `CONTAINER_FILE_CITATION("container_file_citation")` + + - `class FilePath:` + + A path to a file. + + - `String fileId` + + The ID of the file. + + - `long index` + + The index of the file in the list of files. + + - `JsonValue; type "file_path"constant` + + The type of the file path. Always `file_path`. + + - `FILE_PATH("file_path")` + + - `String text` + + The text output from the model. + + - `JsonValue; type "output_text"constant` + + The type of the output text. Always `output_text`. + + - `OUTPUT_TEXT("output_text")` + + - `Optional> logprobs` + + - `String token` + + - `List bytes` + + - `double logprob` + + - `List topLogprobs` + + - `String token` + + - `List bytes` + + - `double logprob` + + - `class ResponseOutputRefusal:` + + A refusal from the model. + + - `String refusal` + + The refusal explanation from the model. + + - `JsonValue; type "refusal"constant` + + The type of the refusal. Always `refusal`. + + - `REFUSAL("refusal")` + + - `JsonValue; role "assistant"constant` + + The role of the output message. Always `assistant`. + + - `ASSISTANT("assistant")` + + - `Status status` + + The status of the message input. One of `in_progress`, `completed`, or + `incomplete`. Populated when input items are returned via API. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `JsonValue; type "message"constant` + + The type of the output message. Always `message`. + + - `MESSAGE("message")` + + - `Optional phase` + + 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("commentary")` + + - `FINAL_ANSWER("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. + + - `String id` + + The unique ID of the file search tool call. + + - `List queries` + + The queries used to search for files. + + - `Status status` + + The status of the file search tool call. One of `in_progress`, + `searching`, `incomplete` or `failed`, + + - `IN_PROGRESS("in_progress")` + + - `SEARCHING("searching")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `FAILED("failed")` + + - `JsonValue; type "file_search_call"constant` + + The type of the file search tool call. Always `file_search_call`. + + - `FILE_SEARCH_CALL("file_search_call")` + + - `Optional> results` + + The results of the file search tool call. + + - `Optional attributes` + + 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` + + - `double` + + - `boolean` + + - `Optional fileId` + + The unique ID of the file. + + - `Optional filename` + + The name of the file. + + - `Optional score` + + The relevance score of the file - a value between 0 and 1. + + - `Optional text` + + 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. + + - `String id` + + The unique ID of the computer call. + + - `String callId` + + An identifier used when responding to the tool call with output. + + - `List pendingSafetyChecks` + + The pending safety checks for the computer call. + + - `String id` + + The ID of the pending safety check. + + - `Optional code` + + The type of the pending safety check. + + - `Optional message` + + Details about the pending safety check. + + - `Status status` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `Type type` + + The type of the computer call. Always `computer_call`. + + - `COMPUTER_CALL("computer_call")` + + - `Optional action` + + A click action. + + - `class Click:` + + A click action. + + - `Button button` + + Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. + + - `LEFT("left")` + + - `RIGHT("right")` + + - `WHEEL("wheel")` + + - `BACK("back")` + + - `FORWARD("forward")` + + - `JsonValue; type "click"constant` + + Specifies the event type. For a click action, this property is always `click`. + + - `CLICK("click")` + + - `long x` + + The x-coordinate where the click occurred. + + - `long y` + + The y-coordinate where the click occurred. + + - `Optional> keys` + + The keys being held while clicking. + + - `class DoubleClick:` + + A double click action. + + - `Optional> keys` + + The keys being held while double-clicking. + + - `JsonValue; type "double_click"constant` + + Specifies the event type. For a double click action, this property is always set to `double_click`. + + - `DOUBLE_CLICK("double_click")` + + - `long x` + + The x-coordinate where the double click occurred. + + - `long y` + + The y-coordinate where the double click occurred. + + - `class Drag:` + + A drag action. + + - `List path` + + 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 } + ] + ``` + + - `long x` + + The x-coordinate. + + - `long y` + + The y-coordinate. + + - `JsonValue; type "drag"constant` + + Specifies the event type. For a drag action, this property is always set to `drag`. + + - `DRAG("drag")` + + - `Optional> keys` + + The keys being held while dragging the mouse. + + - `class Keypress:` + + A collection of keypresses the model would like to perform. + + - `List keys` + + The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. + + - `JsonValue; type "keypress"constant` + + Specifies the event type. For a keypress action, this property is always set to `keypress`. + + - `KEYPRESS("keypress")` + + - `class Move:` + + A mouse move action. + + - `JsonValue; type "move"constant` + + Specifies the event type. For a move action, this property is always set to `move`. + + - `MOVE("move")` + + - `long x` + + The x-coordinate to move to. + + - `long y` + + The y-coordinate to move to. + + - `Optional> keys` + + The keys being held while moving the mouse. + + - `JsonValue;` + + - `JsonValue; type "screenshot"constant` + + Specifies the event type. For a screenshot action, this property is always set to `screenshot`. + + - `SCREENSHOT("screenshot")` + + - `class Scroll:` + + A scroll action. + + - `long scrollX` + + The horizontal scroll distance. + + - `long scrollY` + + The vertical scroll distance. + + - `JsonValue; type "scroll"constant` + + Specifies the event type. For a scroll action, this property is always set to `scroll`. + + - `SCROLL("scroll")` + + - `long x` + + The x-coordinate where the scroll occurred. + + - `long y` + + The y-coordinate where the scroll occurred. + + - `Optional> keys` + + The keys being held while scrolling. + + - `class Type:` + + An action to type in text. + + - `String text` + + The text to type. + + - `JsonValue; type "type"constant` + + Specifies the event type. For a type action, this property is always set to `type`. + + - `TYPE("type")` + + - `JsonValue;` + + - `JsonValue; type "wait"constant` + + Specifies the event type. For a wait action, this property is always set to `wait`. + + - `WAIT("wait")` + + - `Optional> actions` + + Flattened batched actions for `computer_use`. Each action includes an + `type` discriminator and action-specific fields. + + - `Click` + + - `Button button` + + Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. + + - `LEFT("left")` + + - `RIGHT("right")` + + - `WHEEL("wheel")` + + - `BACK("back")` + + - `FORWARD("forward")` + + - `JsonValue; type "click"constant` + + Specifies the event type. For a click action, this property is always `click`. + + - `CLICK("click")` + + - `long x` + + The x-coordinate where the click occurred. + + - `long y` + + The y-coordinate where the click occurred. + + - `Optional> keys` + + The keys being held while clicking. + + - `DoubleClick` + + - `Optional> keys` + + The keys being held while double-clicking. + + - `JsonValue; type "double_click"constant` + + Specifies the event type. For a double click action, this property is always set to `double_click`. + + - `DOUBLE_CLICK("double_click")` + + - `long x` + + The x-coordinate where the double click occurred. + + - `long y` + + The y-coordinate where the double click occurred. + + - `Drag` + + - `List path` + + 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 } + ] + ``` + + - `long x` + + The x-coordinate. + + - `long y` + + The y-coordinate. + + - `JsonValue; type "drag"constant` + + Specifies the event type. For a drag action, this property is always set to `drag`. + + - `DRAG("drag")` + + - `Optional> keys` + + The keys being held while dragging the mouse. + + - `Keypress` + + - `List keys` + + The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. + + - `JsonValue; type "keypress"constant` + + Specifies the event type. For a keypress action, this property is always set to `keypress`. + + - `KEYPRESS("keypress")` + + - `Move` + + - `JsonValue; type "move"constant` + + Specifies the event type. For a move action, this property is always set to `move`. + + - `MOVE("move")` + + - `long x` + + The x-coordinate to move to. + + - `long y` + + The y-coordinate to move to. + + - `Optional> keys` + + The keys being held while moving the mouse. + + - `JsonValue;` + + - `JsonValue; type "screenshot"constant` + + Specifies the event type. For a screenshot action, this property is always set to `screenshot`. + + - `SCREENSHOT("screenshot")` + + - `Scroll` + + - `long scrollX` + + The horizontal scroll distance. + + - `long scrollY` + + The vertical scroll distance. + + - `JsonValue; type "scroll"constant` + + Specifies the event type. For a scroll action, this property is always set to `scroll`. + + - `SCROLL("scroll")` + + - `long x` + + The x-coordinate where the scroll occurred. + + - `long y` + + The y-coordinate where the scroll occurred. + + - `Optional> keys` + + The keys being held while scrolling. + + - `Type` + + - `String text` + + The text to type. + + - `JsonValue; type "type"constant` + + Specifies the event type. For a type action, this property is always set to `type`. + + - `TYPE("type")` + + - `JsonValue;` + + - `JsonValue; type "wait"constant` + + Specifies the event type. For a wait action, this property is always set to `wait`. + + - `WAIT("wait")` + + - `ComputerCallOutput` + + - `String callId` + + The ID of the computer tool call that produced the output. + + - `ResponseComputerToolCallOutputScreenshot output` + + A computer screenshot image used with the computer use tool. + + - `JsonValue; type "computer_screenshot"constant` + + Specifies the event type. For a computer screenshot, this property is + always set to `computer_screenshot`. + + - `COMPUTER_SCREENSHOT("computer_screenshot")` + + - `Optional fileId` + + The identifier of an uploaded file that contains the screenshot. + + - `Optional imageUrl` + + The URL of the screenshot image. + + - `JsonValue; type "computer_call_output"constant` + + The type of the computer tool call output. Always `computer_call_output`. + + - `COMPUTER_CALL_OUTPUT("computer_call_output")` + + - `Optional id` + + The ID of the computer tool call output. + + - `Optional> acknowledgedSafetyChecks` + + The safety checks reported by the API that have been acknowledged by the developer. + + - `String id` + + The ID of the pending safety check. + + - `Optional code` + + The type of the pending safety check. + + - `Optional message` + + Details about the pending safety check. + + - `Optional status` + + The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("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. + + - `String id` + + The unique ID of the web search tool call. + + - `Action action` + + 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. + + - `JsonValue; type "search"constant` + + The action type. + + - `SEARCH("search")` + + - `Optional> queries` + + The search queries. + + - `Optional query` + + The search query. + + - `Optional> sources` + + The sources used in the search. + + - `JsonValue; type "url"constant` + + The type of source. Always `url`. + + - `URL("url")` + + - `String url` + + The URL of the source. + + - `class OpenPage:` + + Action type "open_page" - Opens a specific URL from search results. + + - `JsonValue; type "open_page"constant` + + The action type. + + - `OPEN_PAGE("open_page")` + + - `Optional url` + + The URL opened by the model. + + - `class FindInPage:` + + Action type "find_in_page": Searches for a pattern within a loaded page. + + - `String pattern` + + The pattern or text to search for within the page. + + - `JsonValue; type "find_in_page"constant` + + The action type. + + - `FIND_IN_PAGE("find_in_page")` + + - `String url` + + The URL of the page searched for the pattern. + + - `Status status` + + The status of the web search tool call. + + - `IN_PROGRESS("in_progress")` + + - `SEARCHING("searching")` + + - `COMPLETED("completed")` + + - `FAILED("failed")` + + - `JsonValue; type "web_search_call"constant` + + The type of the web search tool call. Always `web_search_call`. + + - `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. + + - `String arguments` + + A JSON string of the arguments to pass to the function. + + - `String callId` + + The unique ID of the function tool call generated by the model. + + - `String name` + + The name of the function to run. + + - `JsonValue; type "function_call"constant` + + The type of the function tool call. Always `function_call`. + + - `FUNCTION_CALL("function_call")` + + - `Optional id` + + The unique ID of the function tool call. + + - `Optional namespace` + + The namespace of the function to run. + + - `Optional status` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `FunctionCallOutput` + + - `String callId` + + The unique ID of the function tool call generated by the model. + + - `Output output` + + Text, image, or file output of the function tool call. + + - `String` + + - `List` + + - `class ResponseInputTextContent:` + + A text input to the model. + + - `String text` + + The text input to the model. + + - `JsonValue; type "input_text"constant` + + The type of the input item. Always `input_text`. + + - `INPUT_TEXT("input_text")` + + - `class ResponseInputImageContent:` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision) + + - `JsonValue; type "input_image"constant` + + The type of the input item. Always `input_image`. + + - `INPUT_IMAGE("input_image")` + + - `Optional detail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `LOW("low")` + + - `HIGH("high")` + + - `AUTO("auto")` + + - `ORIGINAL("original")` + + - `Optional fileId` + + The ID of the file to be sent to the model. + + - `Optional imageUrl` + + 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. + + - `JsonValue; type "input_file"constant` + + The type of the input item. Always `input_file`. + + - `INPUT_FILE("input_file")` + + - `Optional detail` + + 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("low")` + + - `HIGH("high")` + + - `Optional fileData` + + The base64-encoded data of the file to be sent to the model. + + - `Optional fileId` + + The ID of the file to be sent to the model. + + - `Optional fileUrl` + + The URL of the file to be sent to the model. + + - `Optional filename` + + The name of the file to be sent to the model. + + - `JsonValue; type "function_call_output"constant` + + The type of the function tool call output. Always `function_call_output`. + + - `FUNCTION_CALL_OUTPUT("function_call_output")` + + - `Optional id` + + The unique ID of the function tool call output. Populated when this item is returned via API. + + - `Optional status` + + The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `ToolSearchCall` + + - `JsonValue arguments` + + The arguments supplied to the tool search call. + + - `JsonValue; type "tool_search_call"constant` + + The item type. Always `tool_search_call`. + + - `TOOL_SEARCH_CALL("tool_search_call")` + + - `Optional id` + + The unique ID of this tool search call. + + - `Optional callId` + + The unique ID of the tool search call generated by the model. + + - `Optional execution` + + Whether tool search was executed by the server or by the client. + + - `SERVER("server")` + + - `CLIENT("client")` + + - `Optional status` + + The status of the tool search call. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `class ResponseToolSearchOutputItemParam:` + + - `List tools` + + 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). + + - `String name` + + The name of the function to call. + + - `Optional parameters` + + A JSON schema object describing the parameters of the function. + + - `Optional strict` + + Whether to enforce strict parameter validation. Default `true`. + + - `JsonValue; type "function"constant` + + The type of the function tool. Always `function`. + + - `FUNCTION("function")` + + - `Optional deferLoading` + + Whether this function is deferred and loaded via tool search. + + - `Optional description` + + 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). + + - `JsonValue; type "file_search"constant` + + The type of the file search tool. Always `file_search`. + + - `FILE_SEARCH("file_search")` + + - `List vectorStoreIds` + + The IDs of the vector stores to search. + + - `Optional filters` + + A filter to apply. + + - `class ComparisonFilter:` + + A filter used to compare a specified attribute key to a given value using a defined comparison operation. + + - `String key` + + The key to compare against the value. + + - `Type type` + + 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("eq")` + + - `NE("ne")` + + - `GT("gt")` + + - `GTE("gte")` + + - `LT("lt")` + + - `LTE("lte")` + + - `IN("in")` + + - `NIN("nin")` + + - `Value value` + + The value to compare against the attribute key; supports string, number, or boolean types. + + - `String` + + - `double` + + - `boolean` + + - `List` + + - `String` + + - `double` + + - `class CompoundFilter:` + + Combine multiple filters using `and` or `or`. + + - `List filters` + + 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. + + - `JsonValue` + + - `Type type` + + Type of operation: `and` or `or`. + + - `AND("and")` + + - `OR("or")` + + - `Optional maxNumResults` + + The maximum number of results to return. This number should be between 1 and 50 inclusive. + + - `Optional rankingOptions` + + Ranking options for search. + + - `Optional hybridSearch` + + Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. + + - `double embeddingWeight` + + The weight of the embedding in the reciprocal ranking fusion. + + - `double textWeight` + + The weight of the text in the reciprocal ranking fusion. + + - `Optional ranker` + + The ranker to use for the file search. + + - `AUTO("auto")` + + - `DEFAULT_2024_11_15("default-2024-11-15")` + + - `Optional scoreThreshold` + + 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). + + - `JsonValue; type "computer"constant` + + The type of the computer tool. Always `computer`. + + - `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). + + - `long displayHeight` + + The height of the computer display. + + - `long displayWidth` + + The width of the computer display. + + - `Environment environment` + + The type of computer environment to control. + + - `WINDOWS("windows")` + + - `MAC("mac")` + + - `LINUX("linux")` + + - `UBUNTU("ubuntu")` + + - `BROWSER("browser")` + + - `JsonValue; type "computer_use_preview"constant` + + The type of the computer use tool. Always `computer_use_preview`. + + - `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 type` + + The type of the web search tool. One of `web_search` or `web_search_2025_08_26`. + + - `WEB_SEARCH("web_search")` + + - `WEB_SEARCH_2025_08_26("web_search_2025_08_26")` + + - `Optional filters` + + Filters for the search. + + - `Optional> allowedDomains` + + 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"]` + + - `Optional searchContextSize` + + 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("low")` + + - `MEDIUM("medium")` + + - `HIGH("high")` + + - `Optional userLocation` + + The approximate location of the user. + + - `Optional city` + + Free text input for the city of the user, e.g. `San Francisco`. + + - `Optional country` + + The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. + + - `Optional region` + + Free text input for the region of the user, e.g. `California`. + + - `Optional timezone` + + The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. + + - `Optional type` + + The type of location approximation. Always `approximate`. + + - `APPROXIMATE("approximate")` + + - `Mcp` + + - `String serverLabel` + + A label for this MCP server, used to identify it in tool calls. + + - `JsonValue; type "mcp"constant` + + The type of the MCP tool. Always `mcp`. + + - `MCP("mcp")` + + - `Optional allowedTools` + + List of allowed tool names or a filter object. + + - `List` + + - `class McpToolFilter:` + + A filter object to specify which tools are allowed. + + - `Optional readOnly` + + 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. + + - `Optional> toolNames` + + List of allowed tool names. + + - `Optional authorization` + + 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. + + - `Optional connectorId` + + 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_dropbox")` + + - `CONNECTOR_GMAIL("connector_gmail")` + + - `CONNECTOR_GOOGLECALENDAR("connector_googlecalendar")` + + - `CONNECTOR_GOOGLEDRIVE("connector_googledrive")` + + - `CONNECTOR_MICROSOFTTEAMS("connector_microsoftteams")` + + - `CONNECTOR_OUTLOOKCALENDAR("connector_outlookcalendar")` + + - `CONNECTOR_OUTLOOKEMAIL("connector_outlookemail")` + + - `CONNECTOR_SHAREPOINT("connector_sharepoint")` + + - `Optional deferLoading` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Optional headers` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `Optional requireApproval` + + 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. + + - `Optional always` + + A filter object to specify which tools are allowed. + + - `Optional readOnly` + + 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. + + - `Optional> toolNames` + + List of allowed tool names. + + - `Optional never` + + A filter object to specify which tools are allowed. + + - `Optional readOnly` + + 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. + + - `Optional> toolNames` + + List of allowed tool names. + + - `enum McpToolApprovalSetting:` + + 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("always")` + + - `NEVER("never")` + + - `Optional serverDescription` + + Optional description of the MCP server, used to provide more context. + + - `Optional serverUrl` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + + - `CodeInterpreter` + + - `Container container` + + 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` + + - `class CodeInterpreterToolAuto:` + + Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on. + + - `JsonValue; type "auto"constant` + + Always `auto`. + + - `AUTO("auto")` + + - `Optional> fileIds` + + An optional list of uploaded files to make available to your code. + + - `Optional memoryLimit` + + The memory limit for the code interpreter container. + + - `_1G("1g")` + + - `_4G("4g")` + + - `_16G("16g")` + + - `_64G("64g")` + + - `Optional networkPolicy` + + Network access policy for the container. + + - `class ContainerNetworkPolicyDisabled:` + + - `JsonValue; type "disabled"constant` + + Disable outbound network access. Always `disabled`. + + - `DISABLED("disabled")` + + - `class ContainerNetworkPolicyAllowlist:` + + - `List allowedDomains` + + A list of allowed domains when type is `allowlist`. + + - `JsonValue; type "allowlist"constant` + + Allow outbound network access only to specified domains. Always `allowlist`. + + - `ALLOWLIST("allowlist")` + + - `Optional> domainSecrets` + + Optional domain-scoped secrets for allowlisted domains. + + - `String domain` + + The domain associated with the secret. + + - `String name` + + The name of the secret to inject for the domain. + + - `String value` + + The secret value to inject for the domain. + + - `JsonValue; type "code_interpreter"constant` + + The type of the code interpreter tool. Always `code_interpreter`. + + - `CODE_INTERPRETER("code_interpreter")` + + - `ImageGeneration` + + - `JsonValue; type "image_generation"constant` + + The type of the image generation tool. Always `image_generation`. + + - `IMAGE_GENERATION("image_generation")` + + - `Optional action` + + Whether to generate a new image or edit an existing image. Default: `auto`. + + - `GENERATE("generate")` + + - `EDIT("edit")` + + - `AUTO("auto")` + + - `Optional background` + + 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("transparent")` + + - `OPAQUE("opaque")` + + - `AUTO("auto")` + + - `Optional inputFidelity` + + 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("high")` + + - `LOW("low")` + + - `Optional inputImageMask` + + Optional mask for inpainting. Contains `image_url` + (string, optional) and `file_id` (string, optional). + + - `Optional fileId` + + File ID for the mask image. + + - `Optional imageUrl` + + Base64-encoded mask image. + + - `Optional model` + + The image generation model to use. Default: `gpt-image-1`. + + - `GPT_IMAGE_1("gpt-image-1")` + + - `GPT_IMAGE_1_MINI("gpt-image-1-mini")` + + - `GPT_IMAGE_2("gpt-image-2")` + + - `GPT_IMAGE_2_2026_04_21("gpt-image-2-2026-04-21")` + + - `GPT_IMAGE_1_5("gpt-image-1.5")` + + - `CHATGPT_IMAGE_LATEST("chatgpt-image-latest")` + + - `Optional moderation` + + Moderation level for the generated image. Default: `auto`. + + - `AUTO("auto")` + + - `LOW("low")` + + - `Optional outputCompression` + + Compression level for the output image. Default: 100. + + - `Optional outputFormat` + + The output format of the generated image. One of `png`, `webp`, or + `jpeg`. Default: `png`. + + - `PNG("png")` + + - `WEBP("webp")` + + - `JPEG("jpeg")` + + - `Optional partialImages` + + Number of partial images to generate in streaming mode, from 0 (default value) to 3. + + - `Optional quality` + + The quality of the generated image. One of `low`, `medium`, `high`, + or `auto`. Default: `auto`. + + - `LOW("low")` + + - `MEDIUM("medium")` + + - `HIGH("high")` + + - `AUTO("auto")` + + - `Optional size` + + 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("1024x1024")` + + - `_1024X1536("1024x1536")` + + - `_1536X1024("1536x1024")` + + - `AUTO("auto")` + + - `JsonValue;` + + - `JsonValue; type "local_shell"constant` + + The type of the local shell tool. Always `local_shell`. + + - `LOCAL_SHELL("local_shell")` + + - `class FunctionShellTool:` + + A tool that allows the model to execute shell commands. + + - `JsonValue; type "shell"constant` + + The type of the shell tool. Always `shell`. + + - `SHELL("shell")` + + - `Optional environment` + + - `class ContainerAuto:` + + - `JsonValue; type "container_auto"constant` + + Automatically creates a container for this request + + - `CONTAINER_AUTO("container_auto")` + + - `Optional> fileIds` + + An optional list of uploaded files to make available to your code. + + - `Optional memoryLimit` + + The memory limit for the container. + + - `_1G("1g")` + + - `_4G("4g")` + + - `_16G("16g")` + + - `_64G("64g")` + + - `Optional networkPolicy` + + Network access policy for the container. + + - `class ContainerNetworkPolicyDisabled:` + + - `class ContainerNetworkPolicyAllowlist:` + + - `Optional> skills` + + An optional list of skills referenced by id or inline data. + + - `class SkillReference:` + + - `String skillId` + + The ID of the referenced skill. + + - `JsonValue; type "skill_reference"constant` + + References a skill created with the /v1/skills endpoint. + + - `SKILL_REFERENCE("skill_reference")` + + - `Optional version` + + Optional skill version. Use a positive integer or 'latest'. Omit for default. + + - `class InlineSkill:` + + - `String description` + + The description of the skill. + + - `String name` + + The name of the skill. + + - `InlineSkillSource source` + + Inline skill payload + + - `String data` + + Base64-encoded skill zip bundle. + + - `JsonValue; mediaType "application/zip"constant` + + The media type of the inline skill payload. Must be `application/zip`. + + - `APPLICATION_ZIP("application/zip")` + + - `JsonValue; type "base64"constant` + + The type of the inline skill source. Must be `base64`. + + - `BASE64("base64")` + + - `JsonValue; type "inline"constant` + + Defines an inline skill for this request. + + - `INLINE("inline")` + + - `class LocalEnvironment:` + + - `JsonValue; type "local"constant` + + Use a local computer environment. + + - `LOCAL("local")` + + - `Optional> skills` + + An optional list of skills. + + - `String description` + + The description of the skill. + + - `String name` + + The name of the skill. + + - `String path` + + The path to the directory containing the skill. + + - `class ContainerReference:` + + - `String containerId` + + The ID of the referenced container. + + - `JsonValue; type "container_reference"constant` + + References a container created with the /v1/containers endpoint + + - `CONTAINER_REFERENCE("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) + + - `String name` + + The name of the custom tool, used to identify it in tool calls. + + - `JsonValue; type "custom"constant` + + The type of the custom tool. Always `custom`. + + - `CUSTOM("custom")` + + - `Optional deferLoading` + + Whether this tool should be deferred and discovered via tool search. + + - `Optional description` + + Optional description of the custom tool, used to provide more context. + + - `Optional format` + + The input format for the custom tool. Default is unconstrained text. + + - `JsonValue;` + + - `JsonValue; type "text"constant` + + Unconstrained text format. Always `text`. + + - `TEXT("text")` + + - `Grammar` + + - `String definition` + + The grammar definition. + + - `Syntax syntax` + + The syntax of the grammar definition. One of `lark` or `regex`. + + - `LARK("lark")` + + - `REGEX("regex")` + + - `JsonValue; type "grammar"constant` + + Grammar format. Always `grammar`. + + - `GRAMMAR("grammar")` + + - `class NamespaceTool:` + + Groups function/custom tools under a shared namespace. + + - `String description` + + A description of the namespace shown to the model. + + - `String name` + + The namespace name used in tool calls (for example, `crm`). + + - `List tools` + + The function/custom tools available inside this namespace. + + - `class Function:` + + - `String name` + + - `JsonValue; type "function"constant` + + - `FUNCTION("function")` + + - `Optional deferLoading` + + Whether this function should be deferred and discovered via tool search. + + - `Optional description` + + - `Optional parameters` + + - `Optional strict` + + - `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) + + - `JsonValue; type "namespace"constant` + + The type of the tool. Always `namespace`. + + - `NAMESPACE("namespace")` + + - `class ToolSearchTool:` + + Hosted or BYOT tool search configuration for deferred tools. + + - `JsonValue; type "tool_search"constant` + + The type of the tool. Always `tool_search`. + + - `TOOL_SEARCH("tool_search")` + + - `Optional description` + + Description shown to the model for a client-executed tool search tool. + + - `Optional execution` + + Whether tool search is executed by the server or by the client. + + - `SERVER("server")` + + - `CLIENT("client")` + + - `Optional parameters` + + 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 type` + + 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")` + + - `WEB_SEARCH_PREVIEW_2025_03_11("web_search_preview_2025_03_11")` + + - `Optional> searchContentTypes` + + - `TEXT("text")` + + - `IMAGE("image")` + + - `Optional searchContextSize` + + 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("low")` + + - `MEDIUM("medium")` + + - `HIGH("high")` + + - `Optional userLocation` + + The user's location. + + - `JsonValue; type "approximate"constant` + + The type of location approximation. Always `approximate`. + + - `APPROXIMATE("approximate")` + + - `Optional city` + + Free text input for the city of the user, e.g. `San Francisco`. + + - `Optional country` + + The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. + + - `Optional region` + + Free text input for the region of the user, e.g. `California`. + + - `Optional timezone` + + 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. + + - `JsonValue; type "apply_patch"constant` + + The type of the tool. Always `apply_patch`. + + - `APPLY_PATCH("apply_patch")` + + - `JsonValue; type "tool_search_output"constant` + + The item type. Always `tool_search_output`. + + - `TOOL_SEARCH_OUTPUT("tool_search_output")` + + - `Optional id` + + The unique ID of this tool search output. + + - `Optional callId` + + The unique ID of the tool search call generated by the model. + + - `Optional execution` + + Whether tool search was executed by the server or by the client. + + - `SERVER("server")` + + - `CLIENT("client")` + + - `Optional status` + + The status of the tool search output. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `AdditionalTools` + + - `JsonValue; role "developer"constant` + + The role that provided the additional tools. Only `developer` is supported. + + - `DEVELOPER("developer")` + + - `List tools` + + 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). + + - `Mcp` + + - `CodeInterpreter` + + - `ImageGeneration` + + - `JsonValue;` + + - `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. + + - `JsonValue; type "additional_tools"constant` + + The item type. Always `additional_tools`. + + - `ADDITIONAL_TOOLS("additional_tools")` + + - `Optional id` + + 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). + + - `String id` + + The unique identifier of the reasoning content. + + - `List summary` + + Reasoning summary content. + + - `String text` + + A summary of the reasoning output from the model so far. + + - `JsonValue; type "summary_text"constant` + + The type of the object. Always `summary_text`. + + - `SUMMARY_TEXT("summary_text")` + + - `JsonValue; type "reasoning"constant` + + The type of the object. Always `reasoning`. + + - `REASONING("reasoning")` + + - `Optional> content` + + Reasoning text content. + + - `String text` + + The reasoning text from the model. + + - `JsonValue; type "reasoning_text"constant` + + The type of the reasoning text. Always `reasoning_text`. + + - `REASONING_TEXT("reasoning_text")` + + - `Optional encryptedContent` + + The encrypted content of the reasoning item - populated when a response is + generated with `reasoning.encrypted_content` in the `include` parameter. + + - `Optional status` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `class ResponseCompactionItemParam:` + + A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). + + - `String encryptedContent` + + The encrypted content of the compaction summary. + + - `JsonValue; type "compaction"constant` + + The type of the item. Always `compaction`. + + - `COMPACTION("compaction")` + + - `Optional id` + + The ID of the compaction item. + + - `ImageGenerationCall` + + - `String id` + + The unique ID of the image generation call. + + - `Optional result` + + The generated image encoded in base64. + + - `Status status` + + The status of the image generation call. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `GENERATING("generating")` + + - `FAILED("failed")` + + - `JsonValue; type "image_generation_call"constant` + + The type of the image generation call. Always `image_generation_call`. + + - `IMAGE_GENERATION_CALL("image_generation_call")` + + - `class ResponseCodeInterpreterToolCall:` + + A tool call to run code. + + - `String id` + + The unique ID of the code interpreter tool call. + + - `Optional code` + + The code to run, or null if not available. + + - `String containerId` + + The ID of the container used to run the code. + + - `Optional> outputs` + + 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. + + - `String logs` + + The logs output from the code interpreter. + + - `JsonValue; type "logs"constant` + + The type of the output. Always `logs`. + + - `LOGS("logs")` + + - `class Image:` + + The image output from the code interpreter. + + - `JsonValue; type "image"constant` + + The type of the output. Always `image`. + + - `IMAGE("image")` + + - `String url` + + The URL of the image output from the code interpreter. + + - `Status status` + + The status of the code interpreter tool call. Valid values are `in_progress`, `completed`, `incomplete`, `interpreting`, and `failed`. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `INTERPRETING("interpreting")` + + - `FAILED("failed")` + + - `JsonValue; type "code_interpreter_call"constant` + + The type of the code interpreter tool call. Always `code_interpreter_call`. + + - `CODE_INTERPRETER_CALL("code_interpreter_call")` + + - `LocalShellCall` + + - `String id` + + The unique ID of the local shell call. + + - `Action action` + + Execute a shell command on the server. + + - `List command` + + The command to run. + + - `Env env` + + Environment variables to set for the command. + + - `JsonValue; type "exec"constant` + + The type of the local shell action. Always `exec`. + + - `EXEC("exec")` + + - `Optional timeoutMs` + + Optional timeout in milliseconds for the command. + + - `Optional user` + + Optional user to run the command as. + + - `Optional workingDirectory` + + Optional working directory to run the command in. + + - `String callId` + + The unique ID of the local shell tool call generated by the model. + + - `Status status` + + The status of the local shell call. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `JsonValue; type "local_shell_call"constant` + + The type of the local shell call. Always `local_shell_call`. + + - `LOCAL_SHELL_CALL("local_shell_call")` + + - `LocalShellCallOutput` + + - `String id` + + The unique ID of the local shell tool call generated by the model. + + - `String output` + + A JSON string of the output of the local shell tool call. + + - `JsonValue; type "local_shell_call_output"constant` + + The type of the local shell tool call output. Always `local_shell_call_output`. + + - `LOCAL_SHELL_CALL_OUTPUT("local_shell_call_output")` + + - `Optional status` + + The status of the item. One of `in_progress`, `completed`, or `incomplete`. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `ShellCall` + + - `Action action` + + The shell commands and limits that describe how to run the tool call. + + - `List commands` + + Ordered shell commands for the execution environment to run. + + - `Optional maxOutputLength` + + Maximum number of UTF-8 characters to capture from combined stdout and stderr output. + + - `Optional timeoutMs` + + Maximum wall-clock time in milliseconds to allow the shell commands to run. + + - `String callId` + + The unique ID of the shell tool call generated by the model. + + - `JsonValue; type "shell_call"constant` + + The type of the item. Always `shell_call`. + + - `SHELL_CALL("shell_call")` + + - `Optional id` + + The unique ID of the shell tool call. Populated when this item is returned via API. + + - `Optional environment` + + The environment to execute the shell commands in. + + - `class LocalEnvironment:` + + - `class ContainerReference:` + + - `Optional status` + + The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `ShellCallOutput` + + - `String callId` + + The unique ID of the shell tool call generated by the model. + + - `List output` + + Captured chunks of stdout and stderr output, along with their associated outcomes. + + - `Outcome outcome` + + The exit or timeout outcome associated with this shell call. + + - `JsonValue;` + + - `JsonValue; type "timeout"constant` + + The outcome type. Always `timeout`. + + - `TIMEOUT("timeout")` + + - `class Exit:` + + Indicates that the shell commands finished and returned an exit code. + + - `long exitCode` + + The exit code returned by the shell process. + + - `JsonValue; type "exit"constant` + + The outcome type. Always `exit`. + + - `EXIT("exit")` + + - `String stderr` + + Captured stderr output for the shell call. + + - `String stdout` + + Captured stdout output for the shell call. + + - `JsonValue; type "shell_call_output"constant` + + The type of the item. Always `shell_call_output`. + + - `SHELL_CALL_OUTPUT("shell_call_output")` + + - `Optional id` + + The unique ID of the shell tool call output. Populated when this item is returned via API. + + - `Optional maxOutputLength` + + The maximum number of UTF-8 characters captured for this shell call's combined output. + + - `Optional status` + + The status of the shell call output. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `ApplyPatchCall` + + - `String callId` + + The unique ID of the apply patch tool call generated by the model. + + - `Operation operation` + + 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. + + - `String diff` + + Unified diff content to apply when creating the file. + + - `String path` + + Path of the file to create relative to the workspace root. + + - `JsonValue; type "create_file"constant` + + The operation type. Always `create_file`. + + - `CREATE_FILE("create_file")` + + - `class DeleteFile:` + + Instruction for deleting an existing file via the apply_patch tool. + + - `String path` + + Path of the file to delete relative to the workspace root. + + - `JsonValue; type "delete_file"constant` + + The operation type. Always `delete_file`. + + - `DELETE_FILE("delete_file")` + + - `class UpdateFile:` + + Instruction for updating an existing file via the apply_patch tool. + + - `String diff` + + Unified diff content to apply to the existing file. + + - `String path` + + Path of the file to update relative to the workspace root. + + - `JsonValue; type "update_file"constant` + + The operation type. Always `update_file`. + + - `UPDATE_FILE("update_file")` + + - `Status status` + + The status of the apply patch tool call. One of `in_progress` or `completed`. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `JsonValue; type "apply_patch_call"constant` + + The type of the item. Always `apply_patch_call`. + + - `APPLY_PATCH_CALL("apply_patch_call")` + + - `Optional id` + + The unique ID of the apply patch tool call. Populated when this item is returned via API. + + - `ApplyPatchCallOutput` + + - `String callId` + + The unique ID of the apply patch tool call generated by the model. + + - `Status status` + + The status of the apply patch tool call output. One of `completed` or `failed`. + + - `COMPLETED("completed")` + + - `FAILED("failed")` + + - `JsonValue; type "apply_patch_call_output"constant` + + The type of the item. Always `apply_patch_call_output`. + + - `APPLY_PATCH_CALL_OUTPUT("apply_patch_call_output")` + + - `Optional id` + + The unique ID of the apply patch tool call output. Populated when this item is returned via API. + + - `Optional output` + + Optional human-readable log text from the apply patch tool (e.g., patch results or errors). + + - `McpListTools` + + - `String id` + + The unique ID of the list. + + - `String serverLabel` + + The label of the MCP server. + + - `List tools` + + The tools available on the server. + + - `JsonValue inputSchema` + + The JSON schema describing the tool's input. + + - `String name` + + The name of the tool. + + - `Optional annotations` + + Additional annotations about the tool. + + - `Optional description` + + The description of the tool. + + - `JsonValue; type "mcp_list_tools"constant` + + The type of the item. Always `mcp_list_tools`. + + - `MCP_LIST_TOOLS("mcp_list_tools")` + + - `Optional error` + + Error message if the server could not list tools. + + - `McpApprovalRequest` + + - `String id` + + The unique ID of the approval request. + + - `String arguments` + + A JSON string of arguments for the tool. + + - `String name` + + The name of the tool to run. + + - `String serverLabel` + + The label of the MCP server making the request. + + - `JsonValue; type "mcp_approval_request"constant` + + The type of the item. Always `mcp_approval_request`. + + - `MCP_APPROVAL_REQUEST("mcp_approval_request")` + + - `McpApprovalResponse` + + - `String approvalRequestId` + + The ID of the approval request being answered. + + - `boolean approve` + + Whether the request was approved. + + - `JsonValue; type "mcp_approval_response"constant` + + The type of the item. Always `mcp_approval_response`. + + - `MCP_APPROVAL_RESPONSE("mcp_approval_response")` + + - `Optional id` + + The unique ID of the approval response + + - `Optional reason` + + Optional reason for the decision. + + - `McpCall` + + - `String id` + + The unique ID of the tool call. + + - `String arguments` + + A JSON string of the arguments passed to the tool. + + - `String name` + + The name of the tool that was run. + + - `String serverLabel` + + The label of the MCP server running the tool. + + - `JsonValue; type "mcp_call"constant` + + The type of the item. Always `mcp_call`. + + - `MCP_CALL("mcp_call")` + + - `Optional approvalRequestId` + + 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. + + - `Optional error` + + The error from the tool call, if any. + + - `Optional output` + + The output from the tool call. + + - `Optional status` + + The status of the tool call. One of `in_progress`, `completed`, `incomplete`, `calling`, or `failed`. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `CALLING("calling")` + + - `FAILED("failed")` + + - `class ResponseCustomToolCallOutput:` + + The output of a custom tool call from your code, being sent back to the model. + + - `String callId` + + The call ID, used to map this custom tool call output to a custom tool call. + + - `Output output` + + The output from the custom tool call generated by your code. + Can be a string or an list of output content. + + - `String` + + - `List` + + - `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. + + - `JsonValue; type "custom_tool_call_output"constant` + + The type of the custom tool call output. Always `custom_tool_call_output`. + + - `CUSTOM_TOOL_CALL_OUTPUT("custom_tool_call_output")` + + - `Optional id` + + 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. + + - `String callId` + + An identifier used to map this custom tool call to a tool call output. + + - `String input` + + The input for the custom tool call generated by the model. + + - `String name` + + The name of the custom tool being called. + + - `JsonValue; type "custom_tool_call"constant` + + The type of the custom tool call. Always `custom_tool_call`. + + - `CUSTOM_TOOL_CALL("custom_tool_call")` + + - `Optional id` + + The unique ID of the custom tool call in the OpenAI platform. + + - `Optional namespace` + + The namespace of the custom tool being called. + + - `JsonValue;` + + - `JsonValue; type "compaction_trigger"constant` + + The type of the item. Always `compaction_trigger`. + + - `COMPACTION_TRIGGER("compaction_trigger")` + + - `ItemReference` + + - `String id` + + The ID of the item to reference. + + - `Optional type` + + The type of item to reference. Always `item_reference`. + + - `ITEM_REFERENCE("item_reference")` + + - `Optional instructions` + + 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. + + - `Optional previousResponseId` + + 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`. + + - `Optional promptCacheKey` + + A key to use when reading from or writing to the prompt cache. + + - `Optional promptCacheRetention` + + How long to retain a prompt cache entry created by this request. + + - `IN_MEMORY("in_memory")` + + - `_24H("24h")` + + - `Optional serviceTier` + + The service tier to use for this request. + + - `AUTO("auto")` + + - `DEFAULT("default")` + + - `FLEX("flex")` + + - `PRIORITY("priority")` + +### Returns + +- `class CompactedResponse:` + + - `String id` + + The unique identifier for the compacted response. + + - `long createdAt` + + Unix timestamp (in seconds) when the compacted conversation was created. + + - `JsonValue; object_ "response.compaction"constant` + + The object type. Always `response.compaction`. + + - `RESPONSE_COMPACTION("response.compaction")` + + - `List output` + + 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. + + - `String id` + + The unique ID of the output message. + + - `List content` + + The content of the output message. + + - `class ResponseOutputText:` + + A text output from the model. + + - `List annotations` + + The annotations of the text output. + + - `class FileCitation:` + + A citation to a file. + + - `String fileId` + + The ID of the file. + + - `String filename` + + The filename of the file cited. + + - `long index` + + The index of the file in the list of files. + + - `JsonValue; type "file_citation"constant` + + The type of the file citation. Always `file_citation`. + + - `FILE_CITATION("file_citation")` + + - `class UrlCitation:` + + A citation for a web resource used to generate a model response. + + - `long endIndex` + + The index of the last character of the URL citation in the message. + + - `long startIndex` + + The index of the first character of the URL citation in the message. + + - `String title` + + The title of the web resource. + + - `JsonValue; type "url_citation"constant` + + The type of the URL citation. Always `url_citation`. + + - `URL_CITATION("url_citation")` + + - `String url` + + The URL of the web resource. + + - `class ContainerFileCitation:` + + A citation for a container file used to generate a model response. + + - `String containerId` + + The ID of the container file. + + - `long endIndex` + + The index of the last character of the container file citation in the message. + + - `String fileId` + + The ID of the file. + + - `String filename` + + The filename of the container file cited. + + - `long startIndex` + + The index of the first character of the container file citation in the message. + + - `JsonValue; type "container_file_citation"constant` + + The type of the container file citation. Always `container_file_citation`. + + - `CONTAINER_FILE_CITATION("container_file_citation")` + + - `class FilePath:` + + A path to a file. + + - `String fileId` + + The ID of the file. + + - `long index` + + The index of the file in the list of files. + + - `JsonValue; type "file_path"constant` + + The type of the file path. Always `file_path`. + + - `FILE_PATH("file_path")` + + - `String text` + + The text output from the model. + + - `JsonValue; type "output_text"constant` + + The type of the output text. Always `output_text`. + + - `OUTPUT_TEXT("output_text")` + + - `Optional> logprobs` + + - `String token` + + - `List bytes` + + - `double logprob` + + - `List topLogprobs` + + - `String token` + + - `List bytes` + + - `double logprob` + + - `class ResponseOutputRefusal:` + + A refusal from the model. + + - `String refusal` + + The refusal explanation from the model. + + - `JsonValue; type "refusal"constant` + + The type of the refusal. Always `refusal`. + + - `REFUSAL("refusal")` + + - `JsonValue; role "assistant"constant` + + The role of the output message. Always `assistant`. + + - `ASSISTANT("assistant")` + + - `Status status` + + The status of the message input. One of `in_progress`, `completed`, or + `incomplete`. Populated when input items are returned via API. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `JsonValue; type "message"constant` + + The type of the output message. Always `message`. + + - `MESSAGE("message")` + + - `Optional phase` + + 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("commentary")` + + - `FINAL_ANSWER("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. + + - `String id` + + The unique ID of the file search tool call. + + - `List queries` + + The queries used to search for files. + + - `Status status` + + The status of the file search tool call. One of `in_progress`, + `searching`, `incomplete` or `failed`, + + - `IN_PROGRESS("in_progress")` + + - `SEARCHING("searching")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `FAILED("failed")` + + - `JsonValue; type "file_search_call"constant` + + The type of the file search tool call. Always `file_search_call`. + + - `FILE_SEARCH_CALL("file_search_call")` + + - `Optional> results` + + The results of the file search tool call. + + - `Optional attributes` + + 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` + + - `double` + + - `boolean` + + - `Optional fileId` + + The unique ID of the file. + + - `Optional filename` + + The name of the file. + + - `Optional score` + + The relevance score of the file - a value between 0 and 1. + + - `Optional text` + + 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. + + - `String arguments` + + A JSON string of the arguments to pass to the function. + + - `String callId` + + The unique ID of the function tool call generated by the model. + + - `String name` + + The name of the function to run. + + - `JsonValue; type "function_call"constant` + + The type of the function tool call. Always `function_call`. + + - `FUNCTION_CALL("function_call")` + + - `Optional id` + + The unique ID of the function tool call. + + - `Optional namespace` + + The namespace of the function to run. + + - `Optional status` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `class ResponseFunctionToolCallOutputItem:` + + - `String id` + + The unique ID of the function call tool output. + + - `String callId` + + The unique ID of the function tool call generated by the model. + + - `Output output` + + The output from the function call generated by your code. + Can be a string or an list of output content. + + - `String` + + - `List` + + - `class ResponseInputText:` + + A text input to the model. + + - `String text` + + The text input to the model. + + - `JsonValue; type "input_text"constant` + + The type of the input item. Always `input_text`. + + - `INPUT_TEXT("input_text")` + + - `class ResponseInputImage:` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `Detail detail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `LOW("low")` + + - `HIGH("high")` + + - `AUTO("auto")` + + - `ORIGINAL("original")` + + - `JsonValue; type "input_image"constant` + + The type of the input item. Always `input_image`. + + - `INPUT_IMAGE("input_image")` + + - `Optional fileId` + + The ID of the file to be sent to the model. + + - `Optional imageUrl` + + 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. + + - `JsonValue; type "input_file"constant` + + The type of the input item. Always `input_file`. + + - `INPUT_FILE("input_file")` + + - `Optional detail` + + 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("low")` + + - `HIGH("high")` + + - `Optional fileData` + + The content of the file to be sent to the model. + + - `Optional fileId` + + The ID of the file to be sent to the model. + + - `Optional fileUrl` + + The URL of the file to be sent to the model. + + - `Optional filename` + + The name of the file to be sent to the model. + + - `Status status` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `JsonValue; type "function_call_output"constant` + + The type of the function tool call output. Always `function_call_output`. + + - `FUNCTION_CALL_OUTPUT("function_call_output")` + + - `Optional createdBy` + + 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. + + - `String id` + + The unique ID of the web search tool call. + + - `Action action` + + 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. + + - `JsonValue; type "search"constant` + + The action type. + + - `SEARCH("search")` + + - `Optional> queries` + + The search queries. + + - `Optional query` + + The search query. + + - `Optional> sources` + + The sources used in the search. + + - `JsonValue; type "url"constant` + + The type of source. Always `url`. + + - `URL("url")` + + - `String url` + + The URL of the source. + + - `class OpenPage:` + + Action type "open_page" - Opens a specific URL from search results. + + - `JsonValue; type "open_page"constant` + + The action type. + + - `OPEN_PAGE("open_page")` + + - `Optional url` + + The URL opened by the model. + + - `class FindInPage:` + + Action type "find_in_page": Searches for a pattern within a loaded page. + + - `String pattern` + + The pattern or text to search for within the page. + + - `JsonValue; type "find_in_page"constant` + + The action type. + + - `FIND_IN_PAGE("find_in_page")` + + - `String url` + + The URL of the page searched for the pattern. + + - `Status status` + + The status of the web search tool call. + + - `IN_PROGRESS("in_progress")` + + - `SEARCHING("searching")` + + - `COMPLETED("completed")` + + - `FAILED("failed")` + + - `JsonValue; type "web_search_call"constant` + + The type of the web search tool call. Always `web_search_call`. + + - `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. + + - `String id` + + The unique ID of the computer call. + + - `String callId` + + An identifier used when responding to the tool call with output. + + - `List pendingSafetyChecks` + + The pending safety checks for the computer call. + + - `String id` + + The ID of the pending safety check. + + - `Optional code` + + The type of the pending safety check. + + - `Optional message` + + Details about the pending safety check. + + - `Status status` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `Type type` + + The type of the computer call. Always `computer_call`. + + - `COMPUTER_CALL("computer_call")` + + - `Optional action` + + A click action. + + - `class Click:` + + A click action. + + - `Button button` + + Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. + + - `LEFT("left")` + + - `RIGHT("right")` + + - `WHEEL("wheel")` + + - `BACK("back")` + + - `FORWARD("forward")` + + - `JsonValue; type "click"constant` + + Specifies the event type. For a click action, this property is always `click`. + + - `CLICK("click")` + + - `long x` + + The x-coordinate where the click occurred. + + - `long y` + + The y-coordinate where the click occurred. + + - `Optional> keys` + + The keys being held while clicking. + + - `class DoubleClick:` + + A double click action. + + - `Optional> keys` + + The keys being held while double-clicking. + + - `JsonValue; type "double_click"constant` + + Specifies the event type. For a double click action, this property is always set to `double_click`. + + - `DOUBLE_CLICK("double_click")` + + - `long x` + + The x-coordinate where the double click occurred. + + - `long y` + + The y-coordinate where the double click occurred. + + - `class Drag:` + + A drag action. + + - `List path` + + 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 } + ] + ``` + + - `long x` + + The x-coordinate. + + - `long y` + + The y-coordinate. + + - `JsonValue; type "drag"constant` + + Specifies the event type. For a drag action, this property is always set to `drag`. + + - `DRAG("drag")` + + - `Optional> keys` + + The keys being held while dragging the mouse. + + - `class Keypress:` + + A collection of keypresses the model would like to perform. + + - `List keys` + + The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. + + - `JsonValue; type "keypress"constant` + + Specifies the event type. For a keypress action, this property is always set to `keypress`. + + - `KEYPRESS("keypress")` + + - `class Move:` + + A mouse move action. + + - `JsonValue; type "move"constant` + + Specifies the event type. For a move action, this property is always set to `move`. + + - `MOVE("move")` + + - `long x` + + The x-coordinate to move to. + + - `long y` + + The y-coordinate to move to. + + - `Optional> keys` + + The keys being held while moving the mouse. + + - `JsonValue;` + + - `JsonValue; type "screenshot"constant` + + Specifies the event type. For a screenshot action, this property is always set to `screenshot`. + + - `SCREENSHOT("screenshot")` + + - `class Scroll:` + + A scroll action. + + - `long scrollX` + + The horizontal scroll distance. + + - `long scrollY` + + The vertical scroll distance. + + - `JsonValue; type "scroll"constant` + + Specifies the event type. For a scroll action, this property is always set to `scroll`. + + - `SCROLL("scroll")` + + - `long x` + + The x-coordinate where the scroll occurred. + + - `long y` + + The y-coordinate where the scroll occurred. + + - `Optional> keys` + + The keys being held while scrolling. + + - `class Type:` + + An action to type in text. + + - `String text` + + The text to type. + + - `JsonValue; type "type"constant` + + Specifies the event type. For a type action, this property is always set to `type`. + + - `TYPE("type")` + + - `JsonValue;` + + - `JsonValue; type "wait"constant` + + Specifies the event type. For a wait action, this property is always set to `wait`. + + - `WAIT("wait")` + + - `Optional> actions` + + Flattened batched actions for `computer_use`. Each action includes an + `type` discriminator and action-specific fields. + + - `Click` + + - `Button button` + + Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. + + - `LEFT("left")` + + - `RIGHT("right")` + + - `WHEEL("wheel")` + + - `BACK("back")` + + - `FORWARD("forward")` + + - `JsonValue; type "click"constant` + + Specifies the event type. For a click action, this property is always `click`. + + - `CLICK("click")` + + - `long x` + + The x-coordinate where the click occurred. + + - `long y` + + The y-coordinate where the click occurred. + + - `Optional> keys` + + The keys being held while clicking. + + - `DoubleClick` + + - `Optional> keys` + + The keys being held while double-clicking. + + - `JsonValue; type "double_click"constant` + + Specifies the event type. For a double click action, this property is always set to `double_click`. + + - `DOUBLE_CLICK("double_click")` + + - `long x` + + The x-coordinate where the double click occurred. + + - `long y` + + The y-coordinate where the double click occurred. + + - `Drag` + + - `List path` + + 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 } + ] + ``` + + - `long x` + + The x-coordinate. + + - `long y` + + The y-coordinate. + + - `JsonValue; type "drag"constant` + + Specifies the event type. For a drag action, this property is always set to `drag`. + + - `DRAG("drag")` + + - `Optional> keys` + + The keys being held while dragging the mouse. + + - `Keypress` + + - `List keys` + + The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. + + - `JsonValue; type "keypress"constant` + + Specifies the event type. For a keypress action, this property is always set to `keypress`. + + - `KEYPRESS("keypress")` + + - `Move` + + - `JsonValue; type "move"constant` + + Specifies the event type. For a move action, this property is always set to `move`. + + - `MOVE("move")` + + - `long x` + + The x-coordinate to move to. + + - `long y` + + The y-coordinate to move to. + + - `Optional> keys` + + The keys being held while moving the mouse. + + - `JsonValue;` + + - `JsonValue; type "screenshot"constant` + + Specifies the event type. For a screenshot action, this property is always set to `screenshot`. + + - `SCREENSHOT("screenshot")` + + - `Scroll` + + - `long scrollX` + + The horizontal scroll distance. + + - `long scrollY` + + The vertical scroll distance. + + - `JsonValue; type "scroll"constant` + + Specifies the event type. For a scroll action, this property is always set to `scroll`. + + - `SCROLL("scroll")` + + - `long x` + + The x-coordinate where the scroll occurred. + + - `long y` + + The y-coordinate where the scroll occurred. + + - `Optional> keys` + + The keys being held while scrolling. + + - `Type` + + - `String text` + + The text to type. + + - `JsonValue; type "type"constant` + + Specifies the event type. For a type action, this property is always set to `type`. + + - `TYPE("type")` + + - `JsonValue;` + + - `JsonValue; type "wait"constant` + + Specifies the event type. For a wait action, this property is always set to `wait`. + + - `WAIT("wait")` + + - `class ResponseComputerToolCallOutputItem:` + + - `String id` + + The unique ID of the computer call tool output. + + - `String callId` + + The ID of the computer tool call that produced the output. + + - `ResponseComputerToolCallOutputScreenshot output` + + A computer screenshot image used with the computer use tool. + + - `JsonValue; type "computer_screenshot"constant` + + Specifies the event type. For a computer screenshot, this property is + always set to `computer_screenshot`. + + - `COMPUTER_SCREENSHOT("computer_screenshot")` + + - `Optional fileId` + + The identifier of an uploaded file that contains the screenshot. + + - `Optional imageUrl` + + The URL of the screenshot image. + + - `Status status` + + The status of the message input. One of `in_progress`, `completed`, or + `incomplete`. Populated when input items are returned via API. + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `FAILED("failed")` + + - `IN_PROGRESS("in_progress")` + + - `JsonValue; type "computer_call_output"constant` + + The type of the computer tool call output. Always `computer_call_output`. + + - `COMPUTER_CALL_OUTPUT("computer_call_output")` + + - `Optional> acknowledgedSafetyChecks` + + The safety checks reported by the API that have been acknowledged by the + developer. + + - `String id` + + The ID of the pending safety check. + + - `Optional code` + + The type of the pending safety check. + + - `Optional message` + + Details about the pending safety check. + + - `Optional createdBy` + + 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). + + - `String id` + + The unique identifier of the reasoning content. + + - `List summary` + + Reasoning summary content. + + - `String text` + + A summary of the reasoning output from the model so far. + + - `JsonValue; type "summary_text"constant` + + The type of the object. Always `summary_text`. + + - `SUMMARY_TEXT("summary_text")` + + - `JsonValue; type "reasoning"constant` + + The type of the object. Always `reasoning`. + + - `REASONING("reasoning")` + + - `Optional> content` + + Reasoning text content. + + - `String text` + + The reasoning text from the model. + + - `JsonValue; type "reasoning_text"constant` + + The type of the reasoning text. Always `reasoning_text`. + + - `REASONING_TEXT("reasoning_text")` + + - `Optional encryptedContent` + + The encrypted content of the reasoning item - populated when a response is + generated with `reasoning.encrypted_content` in the `include` parameter. + + - `Optional status` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `class ResponseToolSearchCall:` + + - `String id` + + The unique ID of the tool search call item. + + - `JsonValue arguments` + + Arguments used for the tool search call. + + - `Optional callId` + + The unique ID of the tool search call generated by the model. + + - `Execution execution` + + Whether tool search was executed by the server or by the client. + + - `SERVER("server")` + + - `CLIENT("client")` + + - `Status status` + + The status of the tool search call item that was recorded. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `JsonValue; type "tool_search_call"constant` + + The type of the item. Always `tool_search_call`. + + - `TOOL_SEARCH_CALL("tool_search_call")` + + - `Optional createdBy` + + The identifier of the actor that created the item. + + - `class ResponseToolSearchOutputItem:` + + - `String id` + + The unique ID of the tool search output item. + + - `Optional callId` + + The unique ID of the tool search call generated by the model. + + - `Execution execution` + + Whether tool search was executed by the server or by the client. + + - `SERVER("server")` + + - `CLIENT("client")` + + - `Status status` + + The status of the tool search output item that was recorded. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `List tools` + + 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). + + - `String name` + + The name of the function to call. + + - `Optional parameters` + + A JSON schema object describing the parameters of the function. + + - `Optional strict` + + Whether to enforce strict parameter validation. Default `true`. + + - `JsonValue; type "function"constant` + + The type of the function tool. Always `function`. + + - `FUNCTION("function")` + + - `Optional deferLoading` + + Whether this function is deferred and loaded via tool search. + + - `Optional description` + + 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). + + - `JsonValue; type "file_search"constant` + + The type of the file search tool. Always `file_search`. + + - `FILE_SEARCH("file_search")` + + - `List vectorStoreIds` + + The IDs of the vector stores to search. + + - `Optional filters` + + A filter to apply. + + - `class ComparisonFilter:` + + A filter used to compare a specified attribute key to a given value using a defined comparison operation. + + - `String key` + + The key to compare against the value. + + - `Type type` + + 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("eq")` + + - `NE("ne")` + + - `GT("gt")` + + - `GTE("gte")` + + - `LT("lt")` + + - `LTE("lte")` + + - `IN("in")` + + - `NIN("nin")` + + - `Value value` + + The value to compare against the attribute key; supports string, number, or boolean types. + + - `String` + + - `double` + + - `boolean` + + - `List` + + - `String` + + - `double` + + - `class CompoundFilter:` + + Combine multiple filters using `and` or `or`. + + - `List filters` + + 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. + + - `JsonValue` + + - `Type type` + + Type of operation: `and` or `or`. + + - `AND("and")` + + - `OR("or")` + + - `Optional maxNumResults` + + The maximum number of results to return. This number should be between 1 and 50 inclusive. + + - `Optional rankingOptions` + + Ranking options for search. + + - `Optional hybridSearch` + + Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. + + - `double embeddingWeight` + + The weight of the embedding in the reciprocal ranking fusion. + + - `double textWeight` + + The weight of the text in the reciprocal ranking fusion. + + - `Optional ranker` + + The ranker to use for the file search. + + - `AUTO("auto")` + + - `DEFAULT_2024_11_15("default-2024-11-15")` + + - `Optional scoreThreshold` + + 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). + + - `JsonValue; type "computer"constant` + + The type of the computer tool. Always `computer`. + + - `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). + + - `long displayHeight` + + The height of the computer display. + + - `long displayWidth` + + The width of the computer display. + + - `Environment environment` + + The type of computer environment to control. + + - `WINDOWS("windows")` + + - `MAC("mac")` + + - `LINUX("linux")` + + - `UBUNTU("ubuntu")` + + - `BROWSER("browser")` + + - `JsonValue; type "computer_use_preview"constant` + + The type of the computer use tool. Always `computer_use_preview`. + + - `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 type` + + The type of the web search tool. One of `web_search` or `web_search_2025_08_26`. + + - `WEB_SEARCH("web_search")` + + - `WEB_SEARCH_2025_08_26("web_search_2025_08_26")` + + - `Optional filters` + + Filters for the search. + + - `Optional> allowedDomains` + + 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"]` + + - `Optional searchContextSize` + + 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("low")` + + - `MEDIUM("medium")` + + - `HIGH("high")` + + - `Optional userLocation` + + The approximate location of the user. + + - `Optional city` + + Free text input for the city of the user, e.g. `San Francisco`. + + - `Optional country` + + The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. + + - `Optional region` + + Free text input for the region of the user, e.g. `California`. + + - `Optional timezone` + + The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. + + - `Optional type` + + The type of location approximation. Always `approximate`. + + - `APPROXIMATE("approximate")` + + - `Mcp` + + - `String serverLabel` + + A label for this MCP server, used to identify it in tool calls. + + - `JsonValue; type "mcp"constant` + + The type of the MCP tool. Always `mcp`. + + - `MCP("mcp")` + + - `Optional allowedTools` + + List of allowed tool names or a filter object. + + - `List` + + - `class McpToolFilter:` + + A filter object to specify which tools are allowed. + + - `Optional readOnly` + + 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. + + - `Optional> toolNames` + + List of allowed tool names. + + - `Optional authorization` + + 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. + + - `Optional connectorId` + + 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_dropbox")` + + - `CONNECTOR_GMAIL("connector_gmail")` + + - `CONNECTOR_GOOGLECALENDAR("connector_googlecalendar")` + + - `CONNECTOR_GOOGLEDRIVE("connector_googledrive")` + + - `CONNECTOR_MICROSOFTTEAMS("connector_microsoftteams")` + + - `CONNECTOR_OUTLOOKCALENDAR("connector_outlookcalendar")` + + - `CONNECTOR_OUTLOOKEMAIL("connector_outlookemail")` + + - `CONNECTOR_SHAREPOINT("connector_sharepoint")` + + - `Optional deferLoading` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Optional headers` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `Optional requireApproval` + + 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. + + - `Optional always` + + A filter object to specify which tools are allowed. + + - `Optional readOnly` + + 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. + + - `Optional> toolNames` + + List of allowed tool names. + + - `Optional never` + + A filter object to specify which tools are allowed. + + - `Optional readOnly` + + 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. + + - `Optional> toolNames` + + List of allowed tool names. + + - `enum McpToolApprovalSetting:` + + 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("always")` + + - `NEVER("never")` + + - `Optional serverDescription` + + Optional description of the MCP server, used to provide more context. + + - `Optional serverUrl` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + + - `CodeInterpreter` + + - `Container container` + + 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` + + - `class CodeInterpreterToolAuto:` + + Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on. + + - `JsonValue; type "auto"constant` + + Always `auto`. + + - `AUTO("auto")` + + - `Optional> fileIds` + + An optional list of uploaded files to make available to your code. + + - `Optional memoryLimit` + + The memory limit for the code interpreter container. + + - `_1G("1g")` + + - `_4G("4g")` + + - `_16G("16g")` + + - `_64G("64g")` + + - `Optional networkPolicy` + + Network access policy for the container. + + - `class ContainerNetworkPolicyDisabled:` + + - `JsonValue; type "disabled"constant` + + Disable outbound network access. Always `disabled`. + + - `DISABLED("disabled")` + + - `class ContainerNetworkPolicyAllowlist:` + + - `List allowedDomains` + + A list of allowed domains when type is `allowlist`. + + - `JsonValue; type "allowlist"constant` + + Allow outbound network access only to specified domains. Always `allowlist`. + + - `ALLOWLIST("allowlist")` + + - `Optional> domainSecrets` + + Optional domain-scoped secrets for allowlisted domains. + + - `String domain` + + The domain associated with the secret. + + - `String name` + + The name of the secret to inject for the domain. + + - `String value` + + The secret value to inject for the domain. + + - `JsonValue; type "code_interpreter"constant` + + The type of the code interpreter tool. Always `code_interpreter`. + + - `CODE_INTERPRETER("code_interpreter")` + + - `ImageGeneration` + + - `JsonValue; type "image_generation"constant` + + The type of the image generation tool. Always `image_generation`. + + - `IMAGE_GENERATION("image_generation")` + + - `Optional action` + + Whether to generate a new image or edit an existing image. Default: `auto`. + + - `GENERATE("generate")` + + - `EDIT("edit")` + + - `AUTO("auto")` + + - `Optional background` + + 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("transparent")` + + - `OPAQUE("opaque")` + + - `AUTO("auto")` + + - `Optional inputFidelity` + + 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("high")` + + - `LOW("low")` + + - `Optional inputImageMask` + + Optional mask for inpainting. Contains `image_url` + (string, optional) and `file_id` (string, optional). + + - `Optional fileId` + + File ID for the mask image. + + - `Optional imageUrl` + + Base64-encoded mask image. + + - `Optional model` + + The image generation model to use. Default: `gpt-image-1`. + + - `GPT_IMAGE_1("gpt-image-1")` + + - `GPT_IMAGE_1_MINI("gpt-image-1-mini")` + + - `GPT_IMAGE_2("gpt-image-2")` + + - `GPT_IMAGE_2_2026_04_21("gpt-image-2-2026-04-21")` + + - `GPT_IMAGE_1_5("gpt-image-1.5")` + + - `CHATGPT_IMAGE_LATEST("chatgpt-image-latest")` + + - `Optional moderation` + + Moderation level for the generated image. Default: `auto`. + + - `AUTO("auto")` + + - `LOW("low")` + + - `Optional outputCompression` + + Compression level for the output image. Default: 100. + + - `Optional outputFormat` + + The output format of the generated image. One of `png`, `webp`, or + `jpeg`. Default: `png`. + + - `PNG("png")` + + - `WEBP("webp")` + + - `JPEG("jpeg")` + + - `Optional partialImages` + + Number of partial images to generate in streaming mode, from 0 (default value) to 3. + + - `Optional quality` + + The quality of the generated image. One of `low`, `medium`, `high`, + or `auto`. Default: `auto`. + + - `LOW("low")` + + - `MEDIUM("medium")` + + - `HIGH("high")` + + - `AUTO("auto")` + + - `Optional size` + + 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("1024x1024")` + + - `_1024X1536("1024x1536")` + + - `_1536X1024("1536x1024")` + + - `AUTO("auto")` + + - `JsonValue;` + + - `JsonValue; type "local_shell"constant` + + The type of the local shell tool. Always `local_shell`. + + - `LOCAL_SHELL("local_shell")` + + - `class FunctionShellTool:` + + A tool that allows the model to execute shell commands. + + - `JsonValue; type "shell"constant` + + The type of the shell tool. Always `shell`. + + - `SHELL("shell")` + + - `Optional environment` + + - `class ContainerAuto:` + + - `JsonValue; type "container_auto"constant` + + Automatically creates a container for this request + + - `CONTAINER_AUTO("container_auto")` + + - `Optional> fileIds` + + An optional list of uploaded files to make available to your code. + + - `Optional memoryLimit` + + The memory limit for the container. + + - `_1G("1g")` + + - `_4G("4g")` + + - `_16G("16g")` + + - `_64G("64g")` + + - `Optional networkPolicy` + + Network access policy for the container. + + - `class ContainerNetworkPolicyDisabled:` + + - `class ContainerNetworkPolicyAllowlist:` + + - `Optional> skills` + + An optional list of skills referenced by id or inline data. + + - `class SkillReference:` + + - `String skillId` + + The ID of the referenced skill. + + - `JsonValue; type "skill_reference"constant` + + References a skill created with the /v1/skills endpoint. + + - `SKILL_REFERENCE("skill_reference")` + + - `Optional version` + + Optional skill version. Use a positive integer or 'latest'. Omit for default. + + - `class InlineSkill:` + + - `String description` + + The description of the skill. + + - `String name` + + The name of the skill. + + - `InlineSkillSource source` + + Inline skill payload + + - `String data` + + Base64-encoded skill zip bundle. + + - `JsonValue; mediaType "application/zip"constant` + + The media type of the inline skill payload. Must be `application/zip`. + + - `APPLICATION_ZIP("application/zip")` + + - `JsonValue; type "base64"constant` + + The type of the inline skill source. Must be `base64`. + + - `BASE64("base64")` + + - `JsonValue; type "inline"constant` + + Defines an inline skill for this request. + + - `INLINE("inline")` + + - `class LocalEnvironment:` + + - `JsonValue; type "local"constant` + + Use a local computer environment. + + - `LOCAL("local")` + + - `Optional> skills` + + An optional list of skills. + + - `String description` + + The description of the skill. + + - `String name` + + The name of the skill. + + - `String path` + + The path to the directory containing the skill. + + - `class ContainerReference:` + + - `String containerId` + + The ID of the referenced container. + + - `JsonValue; type "container_reference"constant` + + References a container created with the /v1/containers endpoint + + - `CONTAINER_REFERENCE("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) + + - `String name` + + The name of the custom tool, used to identify it in tool calls. + + - `JsonValue; type "custom"constant` + + The type of the custom tool. Always `custom`. + + - `CUSTOM("custom")` + + - `Optional deferLoading` + + Whether this tool should be deferred and discovered via tool search. + + - `Optional description` + + Optional description of the custom tool, used to provide more context. + + - `Optional format` + + The input format for the custom tool. Default is unconstrained text. + + - `JsonValue;` + + - `JsonValue; type "text"constant` + + Unconstrained text format. Always `text`. + + - `TEXT("text")` + + - `Grammar` + + - `String definition` + + The grammar definition. + + - `Syntax syntax` + + The syntax of the grammar definition. One of `lark` or `regex`. + + - `LARK("lark")` + + - `REGEX("regex")` + + - `JsonValue; type "grammar"constant` + + Grammar format. Always `grammar`. + + - `GRAMMAR("grammar")` + + - `class NamespaceTool:` + + Groups function/custom tools under a shared namespace. + + - `String description` + + A description of the namespace shown to the model. + + - `String name` + + The namespace name used in tool calls (for example, `crm`). + + - `List tools` + + The function/custom tools available inside this namespace. + + - `class Function:` + + - `String name` + + - `JsonValue; type "function"constant` + + - `FUNCTION("function")` + + - `Optional deferLoading` + + Whether this function should be deferred and discovered via tool search. + + - `Optional description` + + - `Optional parameters` + + - `Optional strict` + + - `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) + + - `JsonValue; type "namespace"constant` + + The type of the tool. Always `namespace`. + + - `NAMESPACE("namespace")` + + - `class ToolSearchTool:` + + Hosted or BYOT tool search configuration for deferred tools. + + - `JsonValue; type "tool_search"constant` + + The type of the tool. Always `tool_search`. + + - `TOOL_SEARCH("tool_search")` + + - `Optional description` + + Description shown to the model for a client-executed tool search tool. + + - `Optional execution` + + Whether tool search is executed by the server or by the client. + + - `SERVER("server")` + + - `CLIENT("client")` + + - `Optional parameters` + + 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 type` + + 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")` + + - `WEB_SEARCH_PREVIEW_2025_03_11("web_search_preview_2025_03_11")` + + - `Optional> searchContentTypes` + + - `TEXT("text")` + + - `IMAGE("image")` + + - `Optional searchContextSize` + + 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("low")` + + - `MEDIUM("medium")` + + - `HIGH("high")` + + - `Optional userLocation` + + The user's location. + + - `JsonValue; type "approximate"constant` + + The type of location approximation. Always `approximate`. + + - `APPROXIMATE("approximate")` + + - `Optional city` + + Free text input for the city of the user, e.g. `San Francisco`. + + - `Optional country` + + The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. + + - `Optional region` + + Free text input for the region of the user, e.g. `California`. + + - `Optional timezone` + + 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. + + - `JsonValue; type "apply_patch"constant` + + The type of the tool. Always `apply_patch`. + + - `APPLY_PATCH("apply_patch")` + + - `JsonValue; type "tool_search_output"constant` + + The type of the item. Always `tool_search_output`. + + - `TOOL_SEARCH_OUTPUT("tool_search_output")` + + - `Optional createdBy` + + The identifier of the actor that created the item. + + - `AdditionalTools` + + - `String id` + + The unique ID of the additional tools item. + + - `Role role` + + The role that provided the additional tools. + + - `UNKNOWN("unknown")` + + - `USER("user")` + + - `ASSISTANT("assistant")` + + - `SYSTEM("system")` + + - `CRITIC("critic")` + + - `DISCRIMINATOR("discriminator")` + + - `DEVELOPER("developer")` + + - `TOOL("tool")` + + - `List tools` + + 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). + + - `Mcp` + + - `CodeInterpreter` + + - `ImageGeneration` + + - `JsonValue;` + + - `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. + + - `JsonValue; type "additional_tools"constant` + + The type of the item. Always `additional_tools`. + + - `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). + + - `String id` + + The unique ID of the compaction item. + + - `String encryptedContent` + + The encrypted content that was produced by compaction. + + - `JsonValue; type "compaction"constant` + + The type of the item. Always `compaction`. + + - `COMPACTION("compaction")` + + - `Optional createdBy` + + The identifier of the actor that created the item. + + - `ImageGenerationCall` + + - `String id` + + The unique ID of the image generation call. + + - `Optional result` + + The generated image encoded in base64. + + - `Status status` + + The status of the image generation call. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `GENERATING("generating")` + + - `FAILED("failed")` + + - `JsonValue; type "image_generation_call"constant` + + The type of the image generation call. Always `image_generation_call`. + + - `IMAGE_GENERATION_CALL("image_generation_call")` + + - `class ResponseCodeInterpreterToolCall:` + + A tool call to run code. + + - `String id` + + The unique ID of the code interpreter tool call. + + - `Optional code` + + The code to run, or null if not available. + + - `String containerId` + + The ID of the container used to run the code. + + - `Optional> outputs` + + 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. + + - `String logs` + + The logs output from the code interpreter. + + - `JsonValue; type "logs"constant` + + The type of the output. Always `logs`. + + - `LOGS("logs")` + + - `class Image:` + + The image output from the code interpreter. + + - `JsonValue; type "image"constant` + + The type of the output. Always `image`. + + - `IMAGE("image")` + + - `String url` + + The URL of the image output from the code interpreter. + + - `Status status` + + The status of the code interpreter tool call. Valid values are `in_progress`, `completed`, `incomplete`, `interpreting`, and `failed`. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `INTERPRETING("interpreting")` + + - `FAILED("failed")` + + - `JsonValue; type "code_interpreter_call"constant` + + The type of the code interpreter tool call. Always `code_interpreter_call`. + + - `CODE_INTERPRETER_CALL("code_interpreter_call")` + + - `LocalShellCall` + + - `String id` + + The unique ID of the local shell call. + + - `Action action` + + Execute a shell command on the server. + + - `List command` + + The command to run. + + - `Env env` + + Environment variables to set for the command. + + - `JsonValue; type "exec"constant` + + The type of the local shell action. Always `exec`. + + - `EXEC("exec")` + + - `Optional timeoutMs` + + Optional timeout in milliseconds for the command. + + - `Optional user` + + Optional user to run the command as. + + - `Optional workingDirectory` + + Optional working directory to run the command in. + + - `String callId` + + The unique ID of the local shell tool call generated by the model. + + - `Status status` + + The status of the local shell call. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `JsonValue; type "local_shell_call"constant` + + The type of the local shell call. Always `local_shell_call`. + + - `LOCAL_SHELL_CALL("local_shell_call")` + + - `LocalShellCallOutput` + + - `String id` + + The unique ID of the local shell tool call generated by the model. + + - `String output` + + A JSON string of the output of the local shell tool call. + + - `JsonValue; type "local_shell_call_output"constant` + + The type of the local shell tool call output. Always `local_shell_call_output`. + + - `LOCAL_SHELL_CALL_OUTPUT("local_shell_call_output")` + + - `Optional status` + + The status of the item. One of `in_progress`, `completed`, or `incomplete`. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `class ResponseFunctionShellToolCall:` + + A tool call that executes one or more shell commands in a managed environment. + + - `String id` + + The unique ID of the shell tool call. Populated when this item is returned via API. + + - `Action action` + + The shell commands and limits that describe how to run the tool call. + + - `List commands` + + - `Optional maxOutputLength` + + Optional maximum number of characters to return from each command. + + - `Optional timeoutMs` + + Optional timeout in milliseconds for the commands. + + - `String callId` + + The unique ID of the shell tool call generated by the model. + + - `Optional environment` + + Represents the use of a local environment to perform shell actions. + + - `class ResponseLocalEnvironment:` + + Represents the use of a local environment to perform shell actions. + + - `JsonValue; type "local"constant` + + The environment type. Always `local`. + + - `LOCAL("local")` + + - `class ResponseContainerReference:` + + Represents a container created with /v1/containers. + + - `String containerId` + + - `JsonValue; type "container_reference"constant` + + The environment type. Always `container_reference`. + + - `CONTAINER_REFERENCE("container_reference")` + + - `Status status` + + The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `JsonValue; type "shell_call"constant` + + The type of the item. Always `shell_call`. + + - `SHELL_CALL("shell_call")` + + - `Optional createdBy` + + The ID of the entity that created this tool call. + + - `class ResponseFunctionShellToolCallOutput:` + + The output of a shell tool call that was emitted. + + - `String id` + + The unique ID of the shell call output. Populated when this item is returned via API. + + - `String callId` + + The unique ID of the shell tool call generated by the model. + + - `Optional maxOutputLength` + + The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. + + - `List output` + + An array of shell call output contents + + - `Outcome outcome` + + Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk. + + - `JsonValue;` + + - `JsonValue; type "timeout"constant` + + The outcome type. Always `timeout`. + + - `TIMEOUT("timeout")` + + - `class Exit:` + + Indicates that the shell commands finished and returned an exit code. + + - `long exitCode` + + Exit code from the shell process. + + - `JsonValue; type "exit"constant` + + The outcome type. Always `exit`. + + - `EXIT("exit")` + + - `String stderr` + + The standard error output that was captured. + + - `String stdout` + + The standard output that was captured. + + - `Optional createdBy` + + The identifier of the actor that created the item. + + - `Status status` + + The status of the shell call output. One of `in_progress`, `completed`, or `incomplete`. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `JsonValue; type "shell_call_output"constant` + + The type of the shell call output. Always `shell_call_output`. + + - `SHELL_CALL_OUTPUT("shell_call_output")` + + - `Optional createdBy` + + The identifier of the actor that created the item. + + - `class ResponseApplyPatchToolCall:` + + A tool call that applies file diffs by creating, deleting, or updating files. + + - `String id` + + The unique ID of the apply patch tool call. Populated when this item is returned via API. + + - `String callId` + + The unique ID of the apply patch tool call generated by the model. + + - `Operation operation` + + 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. + + - `String diff` + + Diff to apply. + + - `String path` + + Path of the file to create. + + - `JsonValue; type "create_file"constant` + + Create a new file with the provided diff. + + - `CREATE_FILE("create_file")` + + - `class DeleteFile:` + + Instruction describing how to delete a file via the apply_patch tool. + + - `String path` + + Path of the file to delete. + + - `JsonValue; type "delete_file"constant` + + Delete the specified file. + + - `DELETE_FILE("delete_file")` + + - `class UpdateFile:` + + Instruction describing how to update a file via the apply_patch tool. + + - `String diff` + + Diff to apply. + + - `String path` + + Path of the file to update. + + - `JsonValue; type "update_file"constant` + + Update an existing file with the provided diff. + + - `UPDATE_FILE("update_file")` + + - `Status status` + + The status of the apply patch tool call. One of `in_progress` or `completed`. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `JsonValue; type "apply_patch_call"constant` + + The type of the item. Always `apply_patch_call`. + + - `APPLY_PATCH_CALL("apply_patch_call")` + + - `Optional createdBy` + + The ID of the entity that created this tool call. + + - `class ResponseApplyPatchToolCallOutput:` + + The output emitted by an apply patch tool call. + + - `String id` + + The unique ID of the apply patch tool call output. Populated when this item is returned via API. + + - `String callId` + + The unique ID of the apply patch tool call generated by the model. + + - `Status status` + + The status of the apply patch tool call output. One of `completed` or `failed`. + + - `COMPLETED("completed")` + + - `FAILED("failed")` + + - `JsonValue; type "apply_patch_call_output"constant` + + The type of the item. Always `apply_patch_call_output`. + + - `APPLY_PATCH_CALL_OUTPUT("apply_patch_call_output")` + + - `Optional createdBy` + + The ID of the entity that created this tool call output. + + - `Optional output` + + Optional textual output returned by the apply patch tool. + + - `McpCall` + + - `String id` + + The unique ID of the tool call. + + - `String arguments` + + A JSON string of the arguments passed to the tool. + + - `String name` + + The name of the tool that was run. + + - `String serverLabel` + + The label of the MCP server running the tool. + + - `JsonValue; type "mcp_call"constant` + + The type of the item. Always `mcp_call`. + + - `MCP_CALL("mcp_call")` + + - `Optional approvalRequestId` + + 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. + + - `Optional error` + + The error from the tool call, if any. + + - `Optional output` + + The output from the tool call. + + - `Optional status` + + The status of the tool call. One of `in_progress`, `completed`, `incomplete`, `calling`, or `failed`. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `CALLING("calling")` + + - `FAILED("failed")` + + - `McpListTools` + + - `String id` + + The unique ID of the list. + + - `String serverLabel` + + The label of the MCP server. + + - `List tools` + + The tools available on the server. + + - `JsonValue inputSchema` + + The JSON schema describing the tool's input. + + - `String name` + + The name of the tool. + + - `Optional annotations` + + Additional annotations about the tool. + + - `Optional description` + + The description of the tool. + + - `JsonValue; type "mcp_list_tools"constant` + + The type of the item. Always `mcp_list_tools`. + + - `MCP_LIST_TOOLS("mcp_list_tools")` + + - `Optional error` + + Error message if the server could not list tools. + + - `McpApprovalRequest` + + - `String id` + + The unique ID of the approval request. + + - `String arguments` + + A JSON string of arguments for the tool. + + - `String name` + + The name of the tool to run. + + - `String serverLabel` + + The label of the MCP server making the request. + + - `JsonValue; type "mcp_approval_request"constant` + + The type of the item. Always `mcp_approval_request`. + + - `MCP_APPROVAL_REQUEST("mcp_approval_request")` + + - `McpApprovalResponse` + + - `String id` + + The unique ID of the approval response + + - `String approvalRequestId` + + The ID of the approval request being answered. + + - `boolean approve` + + Whether the request was approved. + + - `JsonValue; type "mcp_approval_response"constant` + + The type of the item. Always `mcp_approval_response`. + + - `MCP_APPROVAL_RESPONSE("mcp_approval_response")` + + - `Optional reason` + + Optional reason for the decision. + + - `class ResponseCustomToolCall:` + + A call to a custom tool created by the model. + + - `String callId` + + An identifier used to map this custom tool call to a tool call output. + + - `String input` + + The input for the custom tool call generated by the model. + + - `String name` + + The name of the custom tool being called. + + - `JsonValue; type "custom_tool_call"constant` + + The type of the custom tool call. Always `custom_tool_call`. + + - `CUSTOM_TOOL_CALL("custom_tool_call")` + + - `Optional id` + + The unique ID of the custom tool call in the OpenAI platform. + + - `Optional namespace` + + 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. + + - `String id` + + The unique ID of the custom tool call output item. + + - `Status status` + + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + + - `IN_PROGRESS("in_progress")` + + - `COMPLETED("completed")` + + - `INCOMPLETE("incomplete")` + + - `Optional createdBy` + + The identifier of the actor that created the item. + + - `ResponseUsage usage` + + Token accounting for the compaction pass, including cached, reasoning, and total tokens. + + - `long inputTokens` + + The number of input tokens. + + - `InputTokensDetails inputTokensDetails` + + A detailed breakdown of the input tokens. + + - `long cachedTokens` + + The number of tokens that were retrieved from the cache. + [More on prompt caching](https://platform.openai.com/docs/guides/prompt-caching). + + - `long outputTokens` + + The number of output tokens. + + - `OutputTokensDetails outputTokensDetails` + + A detailed breakdown of the output tokens. + + - `long reasoningTokens` + + The number of reasoning tokens. + + - `long totalTokens` + + The total number of tokens used. + +### Example + +```java +package com.openai.example; + +import com.openai.client.OpenAIClient; +import com.openai.client.okhttp.OpenAIOkHttpClient; +import com.openai.models.responses.CompactedResponse; +import com.openai.models.responses.ResponseCompactParams; + +public final class Main { + private Main() {} + + public static void main(String[] args) { + OpenAIClient client = OpenAIOkHttpClient.fromEnv(); + + ResponseCompactParams params = ResponseCompactParams.builder() + .model(ResponseCompactParams.Model.GPT_5_4) + .build(); + CompactedResponse compactedResponse = client.responses().compact(params); + } +} +``` + +#### 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 + } +} +```