fix(openai): enable usage metadata in streaming responses #1253
+97
−1
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 stream_options parameter with include_usage=True to OpenAI streaming API calls. Without this option, the OpenAI API does not return token usage statistics (prompt_tokens, completion_tokens, total_tokens) in streaming mode, causing usage_metadata to always be None. This change enables proper token counting for streaming responses, which is required for usage tracking and monitoring. Added unit tests to verify: - stream_options is passed correctly in streaming calls - Usage metadata is properly propagated from streaming responses Signed-off-by: skhedim <sebastien.khedim@gmail.com>
Contributor
There was a problem hiding this comment.
Pull request overview
This pull request enables usage metadata tracking in OpenAI streaming responses by adding the stream_options={"include_usage": True} parameter to streaming API calls.
Changes:
- Modified OpenAI streaming implementation to include
stream_optionsparameter for usage metadata - Added comprehensive unit tests to verify the parameter is passed correctly and usage metadata is properly propagated
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
python/packages/kagent-adk/src/kagent/adk/models/_openai.py |
Added stream_options={"include_usage": True} parameter to streaming API call to enable usage metadata in responses |
python/packages/kagent-adk/tests/unittests/models/test_openai.py |
Added two new tests: one verifying stream_options is passed correctly, and another verifying usage metadata propagation from streaming responses |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
supreme-gg-gg
approved these changes
Jan 29, 2026
Contributor
supreme-gg-gg
left a comment
supreme-gg-gg
left a comment
There was a problem hiding this comment.
Makes sense, good catch 👍
EItanya
approved these changes
Jan 29, 2026
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.
What this PR does
Adds
stream_options={"include_usage": True}to OpenAI streaming API calls to enable token usage metadata in streaming responses.Problem
Without this parameter, the OpenAI API does not return token usage statistics (
prompt_tokens,completion_tokens,total_tokens) in streaming mode, causingusage_metadatato always beNone. This breaks token counting and usage tracking features.Solution
Pass
stream_optionswithinclude_usage=Truewhen calling the OpenAI chat completions API in streaming mode. This feature is available in the OpenAI API since November 2023.Testing
Added unit tests to verify:
stream_optionsis passed correctly in streaming callsRelated Issue
Fixes token counting not working in streaming mode (usage_metadata is always None).