{{ message }}
fix(ccusage): Fix underreporting output tokens#835
Closed
jstasiak wants to merge 1 commit into
Closed
Conversation
Claude Code writes multiple JSONL entries per API response during streaming. Each entry shares the same messageId:requestId hash, but output_tokens accumulates incrementally, starting near 0 and reaching the final count when the response completes. The old dedup logic kept the first entry per hash, resulting in using low output_tokens values for some responses. The impact of that varied. In my Claude Code sessions sometimes there was no difference at all (presumably because of no incremental response streaming), sometimes it made ~15% difference (in cost terms) in a given 5-hour block.
Author
|
It's more than likely that this fix, while being an improvement, is incomplete: #705 (comment) |
6 tasks
4 tasks
This was referenced May 12, 2026
Member
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Claude Code writes multiple JSONL entries per API response during streaming. Each entry shares the same messageId:requestId hash, but output_tokens accumulates incrementally, starting near 0 and reaching the final count when the response completes.
The old dedup logic kept the first entry per hash, resulting in using low output_tokens values for some responses. The impact of that varied.
In my Claude Code sessions sometimes there was no difference at all (presumably because of no incremental response streaming), sometimes it made ~15% difference (in cost terms) in a given 5-hour block.
Review note: I'm not sure the change to the
should deduplicate entries across sessionstest makes sense and matches the goals of the project. I figure we'll have a problem regardless of the way we assign tokens (session 1 vs session 2)? Is there something more sophisticated we can do here?Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.