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
This commit is contained in:
Curtis 'Fjord' Hawthorne
2026-02-26 18:17:46 -08:00
committed by GitHub
parent f90e97e414
commit 7e980d7db6
20 changed files with 688 additions and 177 deletions

View File

@@ -1340,7 +1340,7 @@
"type": "string"
},
"output": {
"type": "string"
"$ref": "#/definitions/FunctionCallOutputPayload"
},
"type": {
"enum": [

View File

@@ -4822,7 +4822,7 @@
"type": "string"
},
"output": {
"type": "string"
"$ref": "#/definitions/FunctionCallOutputPayload"
},
"type": {
"enum": [

View File

@@ -11421,7 +11421,7 @@
"type": "string"
},
"output": {
"type": "string"
"$ref": "#/definitions/v2/FunctionCallOutputPayload"
},
"type": {
"enum": [

View File

@@ -565,7 +565,7 @@
"type": "string"
},
"output": {
"type": "string"
"$ref": "#/definitions/FunctionCallOutputPayload"
},
"type": {
"enum": [

View File

@@ -615,7 +615,7 @@
"type": "string"
},
"output": {
"type": "string"
"$ref": "#/definitions/FunctionCallOutputPayload"
},
"type": {
"enum": [

View File

@@ -15,4 +15,4 @@ export type ResponseItem = { "type": "message", role: string, content: Array<Con
/**
* Set when using the Responses API.
*/
call_id: string | null, status: LocalShellStatus, action: LocalShellAction, } | { "type": "function_call", name: string, arguments: string, call_id: string, } | { "type": "function_call_output", call_id: string, output: FunctionCallOutputPayload, } | { "type": "custom_tool_call", status?: string, call_id: string, name: string, input: string, } | { "type": "custom_tool_call_output", call_id: string, output: string, } | { "type": "web_search_call", status?: string, action?: WebSearchAction, } | { "type": "ghost_snapshot", ghost_commit: GhostCommit, } | { "type": "compaction", encrypted_content: string, } | { "type": "other" };
call_id: string | null, status: LocalShellStatus, action: LocalShellAction, } | { "type": "function_call", name: string, arguments: string, call_id: string, } | { "type": "function_call_output", call_id: string, output: FunctionCallOutputPayload, } | { "type": "custom_tool_call", status?: string, call_id: string, name: string, input: string, } | { "type": "custom_tool_call_output", call_id: string, output: FunctionCallOutputPayload, } | { "type": "web_search_call", status?: string, action?: WebSearchAction, } | { "type": "ghost_snapshot", ghost_commit: GhostCommit, } | { "type": "compaction", encrypted_content: string, } | { "type": "other" };