Add support for OpenAI reasoning/thinking events in ChatOpenAIResponses #421
Conversation
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
- Add handler for response.output_item.added with reasoning type - Add handler for response.reasoning.delta to stream thinking content - Add handler for response.output_item.done for reasoning completion - Enhanced response.output_text.delta to track output_index - Add content_part_for_api handler to omit thinking content when sending to API - Remove response.reasoning.delta from skippable events list - Add comprehensive test coverage for all reasoning event handlers - Add test for omitting thinking content in API conversion Thinking content is now properly streamed and accumulated separately from regular text content using output_index tracking. This prevents content type mismatches when OpenAI returns both reasoning and message output items in the same response.
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Outdated suggestions cannot be applied.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.
Thinking content is now properly streamed and accumulated separately from regular text content using output_index tracking. This prevents content type mismatches when OpenAI returns both reasoning and message output items in the same response.