fix: report full per-prompt token usage - #353
Open
zfy0701 wants to merge 1 commit into
Open
Conversation
This was referenced Aug 2, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
PromptResponse.usagefrom the cumulative token delta across the complete ACP promptusage_update.usedand quota metadata based on the latest response for context-status compatibilityWhy
Codex app-server reports both the latest model response usage and cumulative session usage. The adapter currently returns only the latest response, so tool-heavy prompts with multiple model calls substantially under-report their per-turn usage.
The ACP maintainers' direction in claude-agent-acp#390 is that
PromptResponse.usageis per-turn. Taking the cumulative total at prompt completion minus its value at prompt start preserves that contract without double-counting across prompts.Validation
npm test— 334 passed, 28 skippednpm run typechecknpm run buildCreated by Codex . GPT-5.6 Sol