fix(usage): Count Codex cached tokens once in token totals - #110
Merged
Merged
Conversation
Use harness-aware totals in run usage and query buckets. Expose worker and orchestrator totals while keeping the statusline fallback for older daemons. Co-Authored-By: Codex <noreply@anthropic.com>
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Codex reports
cached_input_tokensas part ofinput_tokens. Pricing already handled that (cachedInInputFor), but token totals did not:queryUsageand the statuslinetokfield computedinput + output + cached, so Codex cache was counted twice. On the rollout cited in the orchestrator-usage spec (input 8.36M, cached 8.12M) that shows about 16.5M tokens instead of about 8.4M.totalTokensFor(agent, usage)next tocachedInInputFor: cached is added only when the harness keeps it outside inputqueryUsagetotals and every bucket use itRunUsageSummaryexposestotalTokensfor workers and fororchestratorrunUsage.totalTokenswhen valid and falls back to the old sum for an older daemonOrchestrator tokens on the statusline are a separate feature (spec in progress).
Test plan
npx vitest run tests/pricing.test.ts tests/usage.test.ts tests/usage-query.test.ts tests/usage-daemon.test.ts tests/usage-cli.test.ts tests/statusline.test.ts: 6 files, 74 tests passednpx tsc --noEmit -p .: cleantests/pricing.test.tsfails (1 of 21)