Files
codex/codex-rs/app-server-protocol/schema/json/v2/TurnStartParams.json
T
Hung 9018f3a3b0 Preserve file-backed audio in tool outputs (#60735)
## Why

Converting message content to tool output previously reduced file-backed audio to a text file ID, losing its audio type.

## What changed

- Allow `input_audio` tool output items to carry either `audio_url` or `file_id`, preserving both forms during content conversion.
- Account for file-backed tool audio in history estimates and output truncation, and prepare only inline audio data.
- Reject uploaded audio in raw function and custom tool output injection, extending the existing requirement to submit uploaded audio through typed turn input.
- Regenerate app-server schemas and TypeScript/Python types while preserving the Python inline audio class name.

## Testing

Add coverage for tool audio wire-format round trips, repeated file audio sharing text and audio output budgets, and rejection of raw uploaded audio injection across messages and tool outputs. Extend Python SDK coverage for the inline tool audio shape.

GitOrigin-RevId: f4704466e6151662d2c8b8dc3f5ca2ab2f5710a2
2026-11-11 06:41:15 +00:00

966 lines
24 KiB
JSON
Generated

{
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"AbsolutePathBuf": {
"description": "A path that is guaranteed to be absolute and normalized (though it is not guaranteed to be canonicalized or exist on the filesystem).\n\nIMPORTANT: When deserializing an `AbsolutePathBuf`, a base path must be set using [AbsolutePathBufGuard::new]. If no base path is set, the deserialization will fail unless the path being deserialized is already absolute.",
"type": "string"
},
"AdditionalContextEntry": {
"properties": {
"kind": {
"$ref": "#/definitions/AdditionalContextKind"
},
"name": {
"description": "Optional name for untrusted context, used to label its tool output.",
"type": [
"string",
"null"
]
},
"value": {
"type": "string"
}
},
"required": [
"kind",
"value"
],
"type": "object"
},
"AdditionalContextKind": {
"enum": [
"untrusted",
"application"
],
"type": "string"
},
"ApprovalsReviewer": {
"description": "Configures who approval requests are routed to for review. Examples include sandbox escapes, blocked network access, MCP approval prompts, and ARC escalations. Defaults to `user`. `auto_review` uses a carefully prompted subagent to gather relevant context and apply a risk-based decision framework before approving or denying the request. The legacy value `guardian_subagent` is accepted for compatibility.",
"enum": [
"user",
"auto_review",
"guardian_subagent"
],
"type": "string"
},
"AskForApproval": {
"oneOf": [
{
"enum": [
"untrusted",
"on-request",
"never"
],
"type": "string"
},
{
"additionalProperties": false,
"properties": {
"granular": {
"properties": {
"mcp_elicitations": {
"type": "boolean"
},
"request_permissions": {
"default": false,
"type": "boolean"
},
"rules": {
"type": "boolean"
},
"sandbox_approval": {
"type": "boolean"
},
"skill_approval": {
"default": false,
"type": "boolean"
}
},
"required": [
"mcp_elicitations",
"rules",
"sandbox_approval"
],
"type": "object"
}
},
"required": [
"granular"
],
"title": "GranularAskForApproval",
"type": "object"
}
]
},
"ByteRange": {
"properties": {
"end": {
"format": "uint",
"minimum": 0.0,
"type": "integer"
},
"start": {
"format": "uint",
"minimum": 0.0,
"type": "integer"
}
},
"required": [
"end",
"start"
],
"type": "object"
},
"CollaborationMode": {
"description": "Collaboration mode for a Codex session.",
"properties": {
"mode": {
"$ref": "#/definitions/ModeKind"
},
"settings": {
"$ref": "#/definitions/Settings"
}
},
"required": [
"mode",
"settings"
],
"type": "object"
},
"CyberAccessProgram": {
"description": "Requested cyber treatment for an OpenAI model turn. Authorization and model-tier restrictions remain server-owned.",
"enum": [
"standard",
"daybreakBlue",
"daybreakRed"
],
"type": "string"
},
"FunctionCallOutputBody": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"$ref": "#/definitions/FunctionCallOutputContentItem"
},
"type": "array"
}
]
},
"FunctionCallOutputContentItem": {
"description": "Responses API compatible content items that can be returned by a tool call. This is a subset of ContentItem with the types we support as function call outputs.",
"oneOf": [
{
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"input_text"
],
"title": "InputTextFunctionCallOutputContentItemType",
"type": "string"
}
},
"required": [
"text",
"type"
],
"title": "InputTextFunctionCallOutputContentItem",
"type": "object"
},
{
"anyOf": [
{
"properties": {
"image_url": {
"type": "string"
}
},
"required": [
"image_url"
],
"title": "ImageUrlFunctionCallOutputContentItem",
"type": "object"
},
{
"properties": {
"file_id": {
"type": "string"
}
},
"required": [
"file_id"
],
"title": "FileIdFunctionCallOutputContentItem",
"type": "object"
}
],
"properties": {
"detail": {
"anyOf": [
{
"$ref": "#/definitions/ImageDetail"
},
{
"type": "null"
}
]
},
"type": {
"enum": [
"input_image"
],
"title": "InputImageFunctionCallOutputContentItemType",
"type": "string"
}
},
"required": [
"type"
],
"title": "InputImageFunctionCallOutputContentItem",
"type": "object"
},
{
"anyOf": [
{
"properties": {
"audio_url": {
"type": "string"
}
},
"required": [
"audio_url"
],
"title": "AudioUrlFunctionCallOutputContentItem",
"type": "object"
},
{
"properties": {
"file_id": {
"type": "string"
}
},
"required": [
"file_id"
],
"title": "FileIdFunctionCallOutputContentItem",
"type": "object"
}
],
"description": "Inline audio data or an uploaded file loaded by the Responses API.",
"properties": {
"type": {
"enum": [
"input_audio"
],
"title": "InputAudioFunctionCallOutputContentItemType",
"type": "string"
}
},
"required": [
"type"
],
"title": "InputAudioFunctionCallOutputContentItem",
"type": "object"
},
{
"properties": {
"encrypted_content": {
"type": "string"
},
"type": {
"enum": [
"encrypted_content"
],
"title": "EncryptedContentFunctionCallOutputContentItemType",
"type": "string"
}
},
"required": [
"encrypted_content",
"type"
],
"title": "EncryptedContentFunctionCallOutputContentItem",
"type": "object"
}
]
},
"ImageDetail": {
"enum": [
"auto",
"low",
"high",
"original"
],
"type": "string"
},
"LegacyAppPathString": {
"type": "string"
},
"ModeKind": {
"description": "Initial collaboration mode to use when the TUI starts.",
"enum": [
"plan",
"default"
],
"type": "string"
},
"MultiAgentMode": {
"description": "Controls the effective multi-agent delegation instructions for a turn. `custom` means the configured mode hint defines the policy instead of a built-in policy.",
"oneOf": [
{
"enum": [
"explicitRequestOnly",
"proactive"
],
"type": "string"
},
{
"additionalProperties": false,
"properties": {
"custom": {
"type": "string"
}
},
"required": [
"custom"
],
"title": "CustomMultiAgentMode",
"type": "object"
}
]
},
"NetworkAccess": {
"enum": [
"restricted",
"enabled"
],
"type": "string"
},
"Personality": {
"description": "Deprecated: `friendly` and `pragmatic` no longer select a style.",
"enum": [
"none",
"friendly",
"pragmatic"
],
"type": "string"
},
"ReasoningEffort": {
"description": "A non-empty reasoning effort value advertised by the model.",
"minLength": 1,
"type": "string"
},
"ReasoningSummary": {
"description": "A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. See https://platform.openai.com/docs/guides/reasoning?api-mode=responses#reasoning-summaries",
"oneOf": [
{
"enum": [
"auto",
"concise",
"detailed"
],
"type": "string"
},
{
"description": "Option to disable reasoning summaries.",
"enum": [
"none"
],
"type": "string"
}
]
},
"SandboxPolicy": {
"oneOf": [
{
"properties": {
"type": {
"enum": [
"dangerFullAccess"
],
"title": "DangerFullAccessSandboxPolicyType",
"type": "string"
}
},
"required": [
"type"
],
"title": "DangerFullAccessSandboxPolicy",
"type": "object"
},
{
"properties": {
"networkAccess": {
"default": false,
"type": "boolean"
},
"type": {
"enum": [
"readOnly"
],
"title": "ReadOnlySandboxPolicyType",
"type": "string"
}
},
"required": [
"type"
],
"title": "ReadOnlySandboxPolicy",
"type": "object"
},
{
"properties": {
"networkAccess": {
"allOf": [
{
"$ref": "#/definitions/NetworkAccess"
}
],
"default": "restricted"
},
"type": {
"enum": [
"externalSandbox"
],
"title": "ExternalSandboxSandboxPolicyType",
"type": "string"
}
},
"required": [
"type"
],
"title": "ExternalSandboxSandboxPolicy",
"type": "object"
},
{
"properties": {
"excludeSlashTmp": {
"default": false,
"type": "boolean"
},
"excludeTmpdirEnvVar": {
"default": false,
"type": "boolean"
},
"networkAccess": {
"default": false,
"type": "boolean"
},
"type": {
"enum": [
"workspaceWrite"
],
"title": "WorkspaceWriteSandboxPolicyType",
"type": "string"
},
"writableRoots": {
"default": [],
"items": {
"$ref": "#/definitions/AbsolutePathBuf"
},
"type": "array"
}
},
"required": [
"type"
],
"title": "WorkspaceWriteSandboxPolicy",
"type": "object"
}
]
},
"Settings": {
"description": "Settings for a collaboration mode.",
"properties": {
"developer_instructions": {
"type": [
"string",
"null"
]
},
"model": {
"type": "string"
},
"reasoning_effort": {
"anyOf": [
{
"$ref": "#/definitions/ReasoningEffort"
},
{
"type": "null"
}
]
}
},
"required": [
"model"
],
"type": "object"
},
"TextElement": {
"properties": {
"byteRange": {
"allOf": [
{
"$ref": "#/definitions/ByteRange"
}
],
"description": "Byte range in the parent `text` buffer that this element occupies."
},
"placeholder": {
"description": "Optional human-readable placeholder for the element, displayed in the UI.",
"type": [
"string",
"null"
]
}
},
"required": [
"byteRange"
],
"type": "object"
},
"TurnEnvironmentParams": {
"properties": {
"cwd": {
"$ref": "#/definitions/LegacyAppPathString"
},
"environmentId": {
"type": "string"
},
"runtimeWorkspaceRoots": {
"description": "Environment-native runtime workspace roots. Omitted defaults to `cwd`.",
"items": {
"$ref": "#/definitions/LegacyAppPathString"
},
"type": [
"array",
"null"
]
}
},
"required": [
"cwd",
"environmentId"
],
"type": "object"
},
"TurnToolOutput": {
"properties": {
"name": {
"type": "string"
},
"namespace": {
"type": [
"string",
"null"
]
},
"output": {
"$ref": "#/definitions/FunctionCallOutputBody"
},
"retain": {
"description": "Requests retention of this output in the thread's model history.",
"type": "boolean"
}
},
"required": [
"name",
"output"
],
"type": "object"
},
"UserInput": {
"oneOf": [
{
"properties": {
"text": {
"type": "string"
},
"text_elements": {
"default": [],
"description": "UI-defined spans within `text` used to render or persist special elements.",
"items": {
"$ref": "#/definitions/TextElement"
},
"type": "array"
},
"type": {
"enum": [
"text"
],
"title": "TextUserInputType",
"type": "string"
}
},
"required": [
"text",
"type"
],
"title": "TextUserInput",
"type": "object"
},
{
"anyOf": [
{
"properties": {
"url": {
"type": "string"
}
},
"required": [
"url"
],
"title": "UrlUserInput",
"type": "object"
},
{
"properties": {
"fileId": {
"type": "string"
}
},
"required": [
"fileId"
],
"title": "FileIdUserInput",
"type": "object"
}
],
"properties": {
"detail": {
"anyOf": [
{
"$ref": "#/definitions/ImageDetail"
},
{
"type": "null"
}
],
"default": null
},
"type": {
"enum": [
"image"
],
"title": "ImageUserInputType",
"type": "string"
}
},
"required": [
"type"
],
"title": "ImageUserInput",
"type": "object"
},
{
"properties": {
"detail": {
"anyOf": [
{
"$ref": "#/definitions/ImageDetail"
},
{
"type": "null"
}
],
"default": null
},
"path": {
"type": "string"
},
"type": {
"enum": [
"localImage"
],
"title": "LocalImageUserInputType",
"type": "string"
}
},
"required": [
"path",
"type"
],
"title": "LocalImageUserInput",
"type": "object"
},
{
"anyOf": [
{
"properties": {
"url": {
"type": "string"
}
},
"required": [
"url"
],
"title": "UrlUserInput",
"type": "object"
},
{
"properties": {
"fileId": {
"type": "string"
}
},
"required": [
"fileId"
],
"title": "FileIdUserInput",
"type": "object"
}
],
"properties": {
"type": {
"enum": [
"audio"
],
"title": "AudioUserInputType",
"type": "string"
}
},
"required": [
"type"
],
"title": "AudioUserInput",
"type": "object"
},
{
"properties": {
"path": {
"type": "string"
},
"type": {
"enum": [
"localAudio"
],
"title": "LocalAudioUserInputType",
"type": "string"
}
},
"required": [
"path",
"type"
],
"title": "LocalAudioUserInput",
"type": "object"
},
{
"properties": {
"name": {
"type": "string"
},
"path": {
"type": "string"
},
"type": {
"enum": [
"skill"
],
"title": "SkillUserInputType",
"type": "string"
}
},
"required": [
"name",
"path",
"type"
],
"title": "SkillUserInput",
"type": "object"
},
{
"properties": {
"name": {
"type": "string"
},
"path": {
"type": "string"
},
"type": {
"enum": [
"mention"
],
"title": "MentionUserInputType",
"type": "string"
}
},
"required": [
"name",
"path",
"type"
],
"title": "MentionUserInput",
"type": "object"
}
]
}
},
"properties": {
"approvalPolicy": {
"anyOf": [
{
"$ref": "#/definitions/AskForApproval"
},
{
"type": "null"
}
],
"description": "Override the approval policy for this turn and subsequent turns."
},
"approvalsReviewer": {
"anyOf": [
{
"$ref": "#/definitions/ApprovalsReviewer"
},
{
"type": "null"
}
],
"description": "Override where approval requests are routed for review on this turn and subsequent turns."
},
"clientUserMessageId": {
"type": [
"string",
"null"
]
},
"cwd": {
"description": "Override the working directory for this turn and subsequent turns.",
"type": [
"string",
"null"
]
},
"disabledPluginIds": {
"description": "Replace this thread's disabled plugin IDs. Omitted/null preserves the list; [] clears it.",
"items": {
"type": "string"
},
"type": [
"array",
"null"
]
},
"effort": {
"anyOf": [
{
"$ref": "#/definitions/ReasoningEffort"
},
{
"type": "null"
}
],
"description": "Override the reasoning effort for this turn and subsequent turns."
},
"input": {
"items": {
"$ref": "#/definitions/UserInput"
},
"type": "array"
},
"model": {
"description": "Override the model for this turn and subsequent turns.",
"type": [
"string",
"null"
]
},
"outputSchema": {
"description": "Optional JSON Schema used to constrain the final assistant message for this turn."
},
"parentTurnId": {
"description": "ID of the turn that caused this new turn to start.\n\nSet this when starting work on behalf of another turn, such as delegated work in a different thread. Leave unset for work started directly by the user. Ignored when this request adds input to an active turn.",
"type": [
"string",
"null"
]
},
"personality": {
"anyOf": [
{
"$ref": "#/definitions/Personality"
},
{
"type": "null"
}
],
"description": "@deprecated `friendly` and `pragmatic` no longer select a style. Changing this does not rewrite the thread's existing instructions."
},
"rootTurnId": {
"description": "ID of the first turn in the chain of work that led to this new turn.\n\nWhen setting `parentTurnId`, set this to the parent turn's `rootTurnId` when known. This keeps descendant work attributed to the original turn. If omitted, the new turn becomes its own root. Ignored when this request adds input to an active turn.",
"type": [
"string",
"null"
]
},
"sandboxPolicy": {
"anyOf": [
{
"$ref": "#/definitions/SandboxPolicy"
},
{
"type": "null"
}
],
"description": "Override the sandbox policy for this turn and subsequent turns."
},
"serviceTier": {
"description": "Override the service tier for this turn and subsequent turns.",
"type": [
"string",
"null"
]
},
"serviceTierForTurn": {
"description": "Override the service tier only when this request starts a new turn. Use \"default\" for standard speed. Omitted or null inherits the thread's tier. Does not change the thread's tier or a turn being steered.",
"type": [
"string",
"null"
]
},
"summary": {
"anyOf": [
{
"$ref": "#/definitions/ReasoningSummary"
},
{
"type": "null"
}
],
"description": "Override the reasoning summary for this turn and subsequent turns."
},
"threadId": {
"type": "string"
},
"toolOutput": {
"anyOf": [
{
"$ref": "#/definitions/TurnToolOutput"
},
{
"type": "null"
}
]
},
"turnTrigger": {
"description": "Optional source classification for the caller that starts this turn. Ignored when this request steers an already-active turn.",
"type": [
"string",
"null"
]
}
},
"required": [
"input",
"threadId"
],
"title": "TurnStartParams",
"type": "object"
}