Skip to content

fix: remove double-counted write_actions from partially_reducible evidence; rename Minutes → Action Minutes #23075

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mnkiefer merged 2 commits into from
Mar 26, 2026
+2 −2
Merged

fix: remove double-counted write_actions from partially_reducible evidence; rename Minutes → Action Minutes #23075

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9b8ae0f
Initial plan
Copilot Mar 26, 2026
1809d29
fix: remove double-counted write_actions from partially_reducible evi…
Copilot Mar 26, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion pkg/cli/audit_agentic_analysis.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -278,7 +278,7 @@ func buildAgenticAssessments(processedRun ProcessedRun, metrics MetricsData, too
Kind: "partially_reducible",
Severity: severity,
Summary: fmt.Sprintf("About %d%% of this run's turns appear to be data-gathering that could move to deterministic steps.", deterministicPct),
Evidence: fmt.Sprintf("agentic_fraction=%.2f turns=%d write_actions=%d", fingerprint.AgenticFraction, metrics.Turns, writeCount),
Evidence: fmt.Sprintf("agentic_fraction=%.2f turns=%d", fingerprint.AgenticFraction, metrics.Turns),
Copy link

Copilot AI Mar 26, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

write_actions was removed from this evidence string due to the write count being double-counted, but writeCount is still computed as len(createdItems) + processedRun.Run.SafeItemsCount earlier in buildAgenticAssessments (and also in buildBehaviorFingerprint). Since SafeItemsCount is set from len(extractCreatedItemsFromManifest(...)) and createdItems is derived from the same manifest, this sums the same signal twice and can misclassify ActuationStyle / ResourceProfile and inflate other evidence (e.g. resource_heavy_for_domain). Suggest deriving writeCount from a single source (e.g. SafeItemsCount with fallback to len(createdItems) if needed) and reusing it consistently.

Copilot uses AI. Check for mistakes.
Recommendation: "Move data-fetching work to frontmatter steps: (pre-agent) writing to /tmp/gh-aw/agent/ or post-steps: (post-agent) to reduce inference cost. See the Deterministic & Agentic Patterns guide.",
})
}
Expand Down
2 changes: 1 addition & 1 deletion pkg/cli/logs_report.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,7 @@ type RunData struct {
Status string `json:"status" console:"header:Status"`
Conclusion string `json:"conclusion,omitempty" console:"-"`
Duration string `json:"duration,omitempty" console:"header:Duration,omitempty"`
ActionMinutes float64 `json:"action_minutes,omitempty" console:"header:Minutes,omitempty"`
ActionMinutes float64 `json:"action_minutes,omitempty" console:"header:Action Minutes,omitempty"`
TokenUsage int `json:"token_usage,omitempty" console:"header:Tokens,format:number,omitempty"`
EstimatedCost float64 `json:"estimated_cost,omitempty" console:"header:Cost ($),format:cost,omitempty"`
Turns int `json:"turns,omitempty" console:"header:Turns,omitempty"`
Expand Down
Loading