Fix finish_reason stop when tracking usage#2641
Merged
dgageot merged 1 commit intodocker:mainfrom May 6, 2026
Merged
Conversation
Member
Author
There was a problem hiding this comment.
Assessment: 🟡 NEEDS ATTENTION
This PR correctly implements the happy-path for stream_options.include_usage: the usage chunk is emitted after the stop chunk and before [DONE], Choices serializes as "choices":[] (no omitempty), and the OpenAPI schema is updated. Two medium-severity interoperability concerns with the OpenAI streaming protocol were found.
4d04f1a to
ef58ef7
Compare
krissetto
previously approved these changes
May 5, 2026
| @@ -251,9 +251,6 @@ func runAgentLoop(ctx context.Context, rt runtime.Runtime, sess *session.Session | |||
| // returning nil when nothing is known so we can omit the field entirely | |||
Contributor
There was a problem hiding this comment.
so was it intentional, or should we remove/adjust this part of the comment?
|
|
||
| if req.Stream { | ||
| err := s.streamChatCompletion(c, rt, sess, model) | ||
| err := s.streamChatCompletion(c, rt, sess, model, req.StreamOptions != nil && req.StreamOptions.IncludeUsage) |
Contributor
There was a problem hiding this comment.
i gotta say she's a beauty :) can we maybe make a var? it's not entirely sure what it is at a glance
Member
Author
There was a problem hiding this comment.
I'll just change it so that StreamOptions is not a pointer
ef58ef7 to
64ef8a4
Compare
The server now correctly sends usage at the end of the stream the same way openai's API does. Signed-off-by: Djordje Lukic <djordje.lukic@docker.com>
64ef8a4 to
5daf796
Compare
dgageot
approved these changes
May 6, 2026
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.

The server now correctly sends usage at the end of the stream the same way openai's API does.