fix(ai-adapters): parse OpenAI reasoning alias chunks#1482
Merged
Conversation
Support OpenAI-compatible stream chunks that emit thinking text under choices[0].delta.reasoning by mapping it into unified reasoning_content. Add a focused SSE fixture covering a real-style assistant role/content prelude, reasoning alias chunks, final text, usage, and ThinkingChunk emission.
wsp1911
marked this pull request as ready for review
July 9, 2026 07:28
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Support OpenAI-compatible Chat Completions stream chunks that emit thinking text under
choices[0].delta.reasoning.Fixes #
Type and Areas
Type:
bug fix
Areas:
AI adapters, Rust stream parsing, tests
Motivation / Impact
Some OpenAI-compatible providers stream reasoning text as
delta.reasoninginstead ofdelta.reasoning_content. This PR maps that alias into the unifiedreasoning_contentpath so downstream thinking accumulation and ThinkingChunk emission work consistently.The added SSE fixture also covers a real-style leading assistant role chunk with empty content, confirming it is harmless while subsequent reasoning alias chunks are parsed.
Verification
pnpm run fmt:rscargo test -p bitfun-ai-adapters parses_reasoning_alias_chunkcargo test -p bitfun-ai-adapters openai_fixture_parses_reasoning_alias_into_thinkingReviewer Notes
reasoning_contentremains the first-priority field. The newreasoningalias is only used whenreasoning_contentis absent, before falling back to MiniMaxreasoning_details.Checklist