fix(openaicompat): echo reasoning_content on assistant messages #72
Merged
vietanh85 merged 1 commit intoMay 27, 2026
Merged
Conversation
…k thinking-mode multi-turn round-trips When a DeepSeek thinking-mode model returns reasoning_content alongside tool_calls, the next request must echo that reasoning_content back or the API 400s. ConvertMessages now collects PartReasoning parts from assistant messages and sets m["reasoning_content"] on the wire map, concatenating multiple parts with newline (same as joinText does for PartText). Also adds TestConvertMessages_AssistantReasoningRoundtrip to cover the exact multi-turn message shape that was breaking. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Contributor
|
/zenflow-review |
Contributor
zenflow reviewLGTM - no issues found by either reviewer. |
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This fixes DeepSeek thinking-mode multi-turn round-trips.
When a DeepSeek thinking-mode model returns reasoning_content alongside tool_calls, the next request must echo that reasoning_content back or the API 400s. ConvertMessages now collects PartReasoning parts from assistant messages and sets m["reasoning_content"] on the wire map, concatenating multiple parts with newline (same as joinText does for PartText).
Also adds TestConvertMessages_AssistantReasoningRoundtrip to cover the exact multi-turn message shape that was breaking.
Related issues
Fixes #71