fix: record token usage once per stream to prevent inflated telemetry#1855
Merged
dgageot merged 1 commit intodocker:mainfrom Feb 26, 2026
Merged
fix: record token usage once per stream to prevent inflated telemetry#1855dgageot merged 1 commit intodocker:mainfrom
dgageot merged 1 commit intodocker:mainfrom
Conversation
Providers like Gemini emit usage metadata on every streaming chunk with cumulative token counts. The previous code ran telemetry.RecordTokenUsage (which uses +=) on every chunk, causing massively inflated telemetry token counts and cost. Move the session token updates and telemetry call out of the per-chunk loop into a recordUsage helper that runs exactly once, right before handleStream returns. The latest usage snapshot is still captured (last wins) so token counts remain accurate. Assisted-By: cagent
![docker-agent[bot]](https://avatars.githubusercontent.com/in/2787757?s=60&v=4){kind=small}
There was a problem hiding this comment.
Review Summary
✅ Approved - This PR correctly fixes the token usage inflation issue by moving the telemetry recording out of the per-chunk loop.
The refactoring is well-structured with the recordUsage helper function that uses a guard flag to ensure telemetry is recorded exactly once per stream. The logic properly handles multiple exit paths (early return on FinishReason and fallback at end of loop), and the latest usage snapshot is correctly captured for providers like Gemini that emit cumulative token counts on every chunk.
No bugs found in the changed code.
Member
|
Wasn't this already fixed once? |
rumpl
approved these changes
Feb 26, 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
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.
Providers like Gemini emit usage metadata on every streaming chunk with cumulative token counts. The previous code ran telemetry.RecordTokenUsage (which uses +=) on every chunk, causing massively inflated telemetry token counts and cost.
Move the session token updates and telemetry call out of the per-chunk loop into a recordUsage helper that runs exactly once, right before handleStream returns. The latest usage snapshot is still captured (last wins) so token counts remain accurate.
Assisted-By: cagent