Files
codex/codex-rs/app-server-protocol/schema/json/v2/RawResponseItemCompletedNotification.json
Curtis 'Fjord' Hawthorne 7e980d7db6 Support multimodal custom tool outputs (#12948)
## Summary

This changes `custom_tool_call_output` to use the same output payload
shape as `function_call_output`, so freeform tools can return either
plain text or structured content items.

The main goal is to let `js_repl` return image content from nested
`view_image` calls in its own `custom_tool_call_output`, instead of
relying on a separate injected message.

## What changed

- Changed `custom_tool_call_output.output` from `string` to
`FunctionCallOutputPayload`
- Updated freeform tool plumbing to preserve structured output bodies
- Updated `js_repl` to aggregate nested tool content items and attach
them to the outer `js_repl` result
- Removed the old `js_repl` special case that injected `view_image`
results as a separate pending user image message
- Updated normalization/history/truncation paths to handle multimodal
`custom_tool_call_output`
- Regenerated app-server protocol schema artifacts

## Behavior

Direct `view_image` calls still return a `function_call_output` with
image content.

When `view_image` is called inside `js_repl`, the outer `js_repl`
`custom_tool_call_output` now carries:
- an `input_text` item if the JS produced text output
- one or more `input_image` items from nested tool results

So the nested image result now stays inside the `js_repl` tool output
instead of being injected as a separate message.

## Compatibility

This is intended to be backward-compatible for resumed conversations.

Older histories that stored `custom_tool_call_output.output` as a plain
string still deserialize correctly, and older histories that used the
previous injected-image-message flow also continue to resume.

Added regression coverage for resuming a pre-change rollout containing:
- string-valued `custom_tool_call_output`
- legacy injected image message history


#### [git stack](https://github.com/magus/git-stack-cli)
- 👉 `1` https://github.com/openai/codex/pull/12948
2026-02-26 18:17:46 -08:00

803 lines
19 KiB
JSON

{
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"ContentItem": {
"oneOf": [
{
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"input_text"
],
"title": "InputTextContentItemType",
"type": "string"
}
},
"required": [
"text",
"type"
],
"title": "InputTextContentItem",
"type": "object"
},
{
"properties": {
"image_url": {
"type": "string"
},
"type": {
"enum": [
"input_image"
],
"title": "InputImageContentItemType",
"type": "string"
}
},
"required": [
"image_url",
"type"
],
"title": "InputImageContentItem",
"type": "object"
},
{
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"output_text"
],
"title": "OutputTextContentItemType",
"type": "string"
}
},
"required": [
"text",
"type"
],
"title": "OutputTextContentItem",
"type": "object"
}
]
},
"FunctionCallOutputBody": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"$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"
},
{
"properties": {
"image_url": {
"type": "string"
},
"type": {
"enum": [
"input_image"
],
"title": "InputImageFunctionCallOutputContentItemType",
"type": "string"
}
},
"required": [
"image_url",
"type"
],
"title": "InputImageFunctionCallOutputContentItem",
"type": "object"
}
]
},
"FunctionCallOutputPayload": {
"description": "The payload we send back to OpenAI when reporting a tool call result.\n\n`body` serializes directly as the wire value for `function_call_output.output`. `success` remains internal metadata for downstream handling.",
"properties": {
"body": {
"$ref": "#/definitions/FunctionCallOutputBody"
},
"success": {
"type": [
"boolean",
"null"
]
}
},
"required": [
"body"
],
"type": "object"
},
"GhostCommit": {
"description": "Details of a ghost commit created from a repository state.",
"properties": {
"id": {
"type": "string"
},
"parent": {
"type": [
"string",
"null"
]
},
"preexisting_untracked_dirs": {
"items": {
"type": "string"
},
"type": "array"
},
"preexisting_untracked_files": {
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"id",
"preexisting_untracked_dirs",
"preexisting_untracked_files"
],
"type": "object"
},
"LocalShellAction": {
"oneOf": [
{
"properties": {
"command": {
"items": {
"type": "string"
},
"type": "array"
},
"env": {
"additionalProperties": {
"type": "string"
},
"type": [
"object",
"null"
]
},
"timeout_ms": {
"format": "uint64",
"minimum": 0.0,
"type": [
"integer",
"null"
]
},
"type": {
"enum": [
"exec"
],
"title": "ExecLocalShellActionType",
"type": "string"
},
"user": {
"type": [
"string",
"null"
]
},
"working_directory": {
"type": [
"string",
"null"
]
}
},
"required": [
"command",
"type"
],
"title": "ExecLocalShellAction",
"type": "object"
}
]
},
"LocalShellStatus": {
"enum": [
"completed",
"in_progress",
"incomplete"
],
"type": "string"
},
"MessagePhase": {
"description": "Classifies an assistant message as interim commentary or final answer text.\n\nProviders do not emit this consistently, so callers must treat `None` as \"phase unknown\" and keep compatibility behavior for legacy models.",
"oneOf": [
{
"description": "Mid-turn assistant text (for example preamble/progress narration).\n\nAdditional tool calls or assistant output may follow before turn completion.",
"enum": [
"commentary"
],
"type": "string"
},
{
"description": "The assistant's terminal answer text for the current turn.",
"enum": [
"final_answer"
],
"type": "string"
}
]
},
"ReasoningItemContent": {
"oneOf": [
{
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"reasoning_text"
],
"title": "ReasoningTextReasoningItemContentType",
"type": "string"
}
},
"required": [
"text",
"type"
],
"title": "ReasoningTextReasoningItemContent",
"type": "object"
},
{
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"title": "TextReasoningItemContentType",
"type": "string"
}
},
"required": [
"text",
"type"
],
"title": "TextReasoningItemContent",
"type": "object"
}
]
},
"ReasoningItemReasoningSummary": {
"oneOf": [
{
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"summary_text"
],
"title": "SummaryTextReasoningItemReasoningSummaryType",
"type": "string"
}
},
"required": [
"text",
"type"
],
"title": "SummaryTextReasoningItemReasoningSummary",
"type": "object"
}
]
},
"ResponseItem": {
"oneOf": [
{
"properties": {
"content": {
"items": {
"$ref": "#/definitions/ContentItem"
},
"type": "array"
},
"end_turn": {
"type": [
"boolean",
"null"
]
},
"id": {
"type": [
"string",
"null"
],
"writeOnly": true
},
"phase": {
"anyOf": [
{
"$ref": "#/definitions/MessagePhase"
},
{
"type": "null"
}
]
},
"role": {
"type": "string"
},
"type": {
"enum": [
"message"
],
"title": "MessageResponseItemType",
"type": "string"
}
},
"required": [
"content",
"role",
"type"
],
"title": "MessageResponseItem",
"type": "object"
},
{
"properties": {
"content": {
"default": null,
"items": {
"$ref": "#/definitions/ReasoningItemContent"
},
"type": [
"array",
"null"
]
},
"encrypted_content": {
"type": [
"string",
"null"
]
},
"id": {
"type": "string",
"writeOnly": true
},
"summary": {
"items": {
"$ref": "#/definitions/ReasoningItemReasoningSummary"
},
"type": "array"
},
"type": {
"enum": [
"reasoning"
],
"title": "ReasoningResponseItemType",
"type": "string"
}
},
"required": [
"id",
"summary",
"type"
],
"title": "ReasoningResponseItem",
"type": "object"
},
{
"properties": {
"action": {
"$ref": "#/definitions/LocalShellAction"
},
"call_id": {
"description": "Set when using the Responses API.",
"type": [
"string",
"null"
]
},
"id": {
"description": "Legacy id field retained for compatibility with older payloads.",
"type": [
"string",
"null"
],
"writeOnly": true
},
"status": {
"$ref": "#/definitions/LocalShellStatus"
},
"type": {
"enum": [
"local_shell_call"
],
"title": "LocalShellCallResponseItemType",
"type": "string"
}
},
"required": [
"action",
"status",
"type"
],
"title": "LocalShellCallResponseItem",
"type": "object"
},
{
"properties": {
"arguments": {
"type": "string"
},
"call_id": {
"type": "string"
},
"id": {
"type": [
"string",
"null"
],
"writeOnly": true
},
"name": {
"type": "string"
},
"type": {
"enum": [
"function_call"
],
"title": "FunctionCallResponseItemType",
"type": "string"
}
},
"required": [
"arguments",
"call_id",
"name",
"type"
],
"title": "FunctionCallResponseItem",
"type": "object"
},
{
"properties": {
"call_id": {
"type": "string"
},
"output": {
"$ref": "#/definitions/FunctionCallOutputPayload"
},
"type": {
"enum": [
"function_call_output"
],
"title": "FunctionCallOutputResponseItemType",
"type": "string"
}
},
"required": [
"call_id",
"output",
"type"
],
"title": "FunctionCallOutputResponseItem",
"type": "object"
},
{
"properties": {
"call_id": {
"type": "string"
},
"id": {
"type": [
"string",
"null"
],
"writeOnly": true
},
"input": {
"type": "string"
},
"name": {
"type": "string"
},
"status": {
"type": [
"string",
"null"
]
},
"type": {
"enum": [
"custom_tool_call"
],
"title": "CustomToolCallResponseItemType",
"type": "string"
}
},
"required": [
"call_id",
"input",
"name",
"type"
],
"title": "CustomToolCallResponseItem",
"type": "object"
},
{
"properties": {
"call_id": {
"type": "string"
},
"output": {
"$ref": "#/definitions/FunctionCallOutputPayload"
},
"type": {
"enum": [
"custom_tool_call_output"
],
"title": "CustomToolCallOutputResponseItemType",
"type": "string"
}
},
"required": [
"call_id",
"output",
"type"
],
"title": "CustomToolCallOutputResponseItem",
"type": "object"
},
{
"properties": {
"action": {
"anyOf": [
{
"$ref": "#/definitions/WebSearchAction"
},
{
"type": "null"
}
]
},
"id": {
"type": [
"string",
"null"
],
"writeOnly": true
},
"status": {
"type": [
"string",
"null"
]
},
"type": {
"enum": [
"web_search_call"
],
"title": "WebSearchCallResponseItemType",
"type": "string"
}
},
"required": [
"type"
],
"title": "WebSearchCallResponseItem",
"type": "object"
},
{
"properties": {
"ghost_commit": {
"$ref": "#/definitions/GhostCommit"
},
"type": {
"enum": [
"ghost_snapshot"
],
"title": "GhostSnapshotResponseItemType",
"type": "string"
}
},
"required": [
"ghost_commit",
"type"
],
"title": "GhostSnapshotResponseItem",
"type": "object"
},
{
"properties": {
"encrypted_content": {
"type": "string"
},
"type": {
"enum": [
"compaction"
],
"title": "CompactionResponseItemType",
"type": "string"
}
},
"required": [
"encrypted_content",
"type"
],
"title": "CompactionResponseItem",
"type": "object"
},
{
"properties": {
"type": {
"enum": [
"other"
],
"title": "OtherResponseItemType",
"type": "string"
}
},
"required": [
"type"
],
"title": "OtherResponseItem",
"type": "object"
}
]
},
"WebSearchAction": {
"oneOf": [
{
"properties": {
"queries": {
"items": {
"type": "string"
},
"type": [
"array",
"null"
]
},
"query": {
"type": [
"string",
"null"
]
},
"type": {
"enum": [
"search"
],
"title": "SearchWebSearchActionType",
"type": "string"
}
},
"required": [
"type"
],
"title": "SearchWebSearchAction",
"type": "object"
},
{
"properties": {
"type": {
"enum": [
"open_page"
],
"title": "OpenPageWebSearchActionType",
"type": "string"
},
"url": {
"type": [
"string",
"null"
]
}
},
"required": [
"type"
],
"title": "OpenPageWebSearchAction",
"type": "object"
},
{
"properties": {
"pattern": {
"type": [
"string",
"null"
]
},
"type": {
"enum": [
"find_in_page"
],
"title": "FindInPageWebSearchActionType",
"type": "string"
},
"url": {
"type": [
"string",
"null"
]
}
},
"required": [
"type"
],
"title": "FindInPageWebSearchAction",
"type": "object"
},
{
"properties": {
"type": {
"enum": [
"other"
],
"title": "OtherWebSearchActionType",
"type": "string"
}
},
"required": [
"type"
],
"title": "OtherWebSearchAction",
"type": "object"
}
]
}
},
"properties": {
"item": {
"$ref": "#/definitions/ResponseItem"
},
"threadId": {
"type": "string"
},
"turnId": {
"type": "string"
}
},
"required": [
"item",
"threadId",
"turnId"
],
"title": "RawResponseItemCompletedNotification",
"type": "object"
}