fix(conversations): skip persisting empty reasoning items (#3268)#3323
Draft
GopalGB wants to merge 1 commit intoopenai:mainfrom
Draft
fix(conversations): skip persisting empty reasoning items (#3268)#3323GopalGB wants to merge 1 commit intoopenai:mainfrom
GopalGB wants to merge 1 commit intoopenai:mainfrom
Conversation
Reasoning items with an empty summary list cause a 400 from the Conversations API. Encrypted-reasoning turns frequently produce these (model emits no visible summary). run_item_to_input_item now returns None for such items so they are omitted from the model input, matching the existing tool_approval_item pattern.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Closes #3268.
`run_item_to_input_item` now returns `None` for reasoning items whose `summary` list is empty, so they are omitted from model input (matching the existing `tool_approval_item` pattern).
Why
Encrypted-reasoning turns frequently produce items with no visible summary (`{"type": "reasoning", "summary": []}`). The Conversations API rejects these with a 400, breaking session resume on any agent that uses encrypted reasoning. The fix skips them at the conversion boundary rather than letting the empty payload reach the API.
Change
Test plan