Emit a usage chunk on streamed completions#3
Merged
Conversation
Streaming chat completions ended with `[DONE]` and no token counts, so clients (opencode) could not report context-window consumption for a streamed turn — only non-streaming responses carried `usage`. The `.finished` stream event already carried the `Usage`; the streaming handler discarded it. Add `usage` to `ChatCompletionChunk` and emit an OpenAI-style trailing usage chunk (empty `choices`, populated `usage`) before `[DONE]`.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Add a token-
usageblock to streamed chat completions.Why
Streaming responses ended with
[DONE]and no token counts, so clients (opencode) could not report context-window consumption for a streamed turn. Only non-streaming responses carriedusage.How
The
.finishedstream event already carried theUsage— the streaming handler discarded it. Add an optionalusagetoChatCompletionChunkand emit an OpenAI-style trailing usage chunk (emptychoices, populatedusage) just before[DONE].usageis omitted on every other chunk.Verified
swift build+ 28 tests pass; the routes streaming test now asserts the stream carriesprompt_tokens.