Conversation
The Claude agent runner was not populating the Usage field on CodexEvents, so token counts were always zero in the dashboard and API. Add extractClaudeUsage() to parse token data from both shapes Claude emits: - result events: top-level "usage" field - assistant events: nested "message.usage" field Wire the extracted usage into the CodexEvent forwarded to the orchestrator, matching the existing behaviour in the Codex runner. Also add tests for extractClaudeUsage and dashboard token count rendering. Co-Authored-By: Claude Sonnet 4.6 <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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
CodexEvents without populating theUsagefield, so token counts were always zero in the dashboard and APIextractClaudeUsage()to parse token data from the two shapes Claude's--output-format stream-jsonemits: top-levelusageonresultevents and nestedmessage.usageonassistanteventsCodexEventforwarded to the orchestrator, matching the existing behaviour in the Codex runnerTest plan
TestExtractClaudeUsage_ResultEvent— parses usage fromresulteventsTestExtractClaudeUsage_AssistantEvent— parses usage fromassistanteventsTestExtractClaudeUsage_NoUsage— returns nil for events with no usageTestExtractClaudeUsage_ZeroTokens— returns nil when both counts are zeroTestExtractClaudeUsage_InvalidJSON— returns nil for malformed inputTestExtractClaudeUsage_WithCacheTokens— ignores cache fields, sums input+outputTestDashboardShowsTokenCounts— verifies aggregate and per-session token counts appear in the dashboard HTMLCloses ZYX-79
🤖 Generated with Claude Code