fix(openai): preserve Responses API tool call/output linkage#7759
fix(openai): preserve Responses API tool call/output linkage#7759DOsinga merged 1 commit intoblock:mainfrom
Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a010c098a4
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Use function call_id as the internal tool request id when replaying Responses API history, and always emit function_call_output payloads even when tool results are non-text so follow-up tool calls can use prior outputs reliably. Change-Id: Ifa830bda7352a37fee79d3306967f357c26ddb93 Signed-off-by: rabi <[email protected]>
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 0826206d30
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
* main: (270 commits) test(acp): align provider and server test parity (#7822) fix(acp): register MCP extensions when resuming a session (#7806) fix(goose): load .gitignore in prompt_manager for hint file filtering (#7795) fix: remap max_completion_tokens to max_tokens for OpenAI-compatible providers (#7765) fix(openai): preserve Responses API tool call/output linkage (#7759) chore(deps): bump @hono/node-server from 1.19.9 to 1.19.11 in /evals/open-model-gym/mcp-harness (#7687) fix: return ContextLengthExceeded when prompt exceeds effective KV cache size (#7815) feat: MCP Roots support (#7790) fix(google): use `includeThoughts/part.thought` for thinking handling (#7593) refactor: simplify tokenizer initialization — remove unnecessary Result wrapper (#7744) Fix model selector showing wrong model in tabs (#7784) Stop collecting goosed stderr after startup (#7814) fix: avoid word splitting by space for windows shell commands (#7781) (#7810) Simplify and make it not break on linux (#7813) Add preferred microphone selection (#7805) Remove dependency on posthog-rs (#7811) feat: load hints in nested subdirs (#7772) feat(acp): add read tool and delegate filesystem I/O to ACP clients (#7668) Support secret interpolation in streamable HTTP extension URLs (#7782) More logging for command injection classifier model training (#7779) ...
3 participants
Summary
Use function call_id as the internal tool request id when replaying Responses API history, and always emit
function_call_output payloads even when tool results are non-text so follow-up tool calls can use prior outputs reliably.
Type of Change
AI Assistance
Testing
Tested locally.