[agents] Reject unpaired function outputs in Chat Completions - #4699
Merged
Conversation
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
openai/openai-python#3738 makes Responses function-output call IDs optional. These outputs can represent unpaired external context, while Chat Completions tool messages still need to identify the call they answer.
This pull request preserves unpaired outputs on the Responses path and gives callers an actionable error when they try to convert them to Chat Completions, directing them to a Responses model. Existing outputs with a call ID are unchanged. This lets the Agents SDK adopt the updated Python SDK types before that PR lands without inventing IDs, dropping context, or silently changing message roles.
The check stays inside the Chat Completions converter and applies to both streaming and non-streaming requests, regardless of strict feature validation.