fix(openai): keep streamed choices separate - #1853
Open
1fanwang wants to merge 5 commits into
Open
Conversation
Signed-off-by: 1fanwang <1fannnw@gmail.com>
…stream-multiple-choices
Signed-off-by: 1fanwang <1fannnw@gmail.com>
Signed-off-by: 1fanwang <1fannnw@gmail.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
OpenAI streams with
n > 1return separate choices to the application, but Langfuse merges their recorded content and tool arguments. This keeps each choice separate in index order and preserves the single-choice output shape.The parser accumulates streamed deltas by choice index, which keeps tool-call indexes local to each choice. The sync and async regressions decode the actual exported OTLP payload after consuming an interleaved HTTP stream, including its usage-only final chunk.
Fixes langfuse/langfuse#16998
Type of change
Verification
The run used Python 3.12.13, Langfuse 4.15.1, OpenAI 2.29.0 and HTTPX 0.28.1. Both endpoints run locally; this is not a live-provider or deployed-server result.
Raw logs
Before, on the baseline:
After, both sync and async clients printed this decoded ingestion payload:
Checklist
code_review.md..env.templateif needed.