fix(openai): handle interleaved streaming chunks in tool call #6312
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
…t accumulation Some OpenAI-compatible APIs send interleaved chunks with content:null between tool_calls chunks during streaming. This caused premature termination of argument accumulation, resulting in empty tool call arguments. Changes: - Remove early done=true when chunk has no tool_calls - Accept any finish_reason (not just 'tool_calls') to mark completion Signed-off-by: rabi <[email protected]>
michaelneale
approved these changes
Jan 5, 2026
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Outdated suggestions cannot be applied.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
Some OpenAI-compatible APIs send interleaved chunks with content:null between tool_calls chunks during streaming. This caused premature termination of argument accumulation, resulting in empty tool call arguments.
Changes:
Type of Change
AI Assistance
Testing
Tested with vllm and open source models