ci: cancel superseded blacksmith testboxes#34
Conversation
|
Codex review: found issues before merge. Reviewed June 24, 2026, 9:13 AM ET / 13:13 UTC. Summary Reproducibility: yes. from source inspection: the workflow is manually dispatched with a per-session Review metrics: 1 noteworthy metric.
Merge readiness Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch. Rank-up moves:
Risk before merge
Maintainer options:
Next step before merge
Security Review findings
Review detailsBest possible solution: Preserve independent Testbox sessions unless maintainers explicitly approve a one-active-session-per-ref policy; if cancellation is still desired, key it on an explicit supersession/session identity rather than only Do we have a high-confidence way to reproduce the issue? Yes from source inspection: the workflow is manually dispatched with a per-session Is this the best way to solve the issue? No, not as-is: a ref-only key is too broad for a session-oriented Full review comments:
Overall correctness: patch is incorrect AGENTS.md: not found in the target repository. Codex review notes: model internal, reasoning high; reviewed against 18fb855c8ccd. Label changesLabel changes:
Label justifications:
Evidence reviewedWhat I checked:
Likely related people:
What the crustacean ranks mean
Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics. How this review workflow works
|
What changed
Why
The org shares GitHub's runner-registration budget. ClawBench is currently green and low-volume, but the Testbox workflow should still avoid stacking stale Blacksmith runner registrations when repeated runs target the same ref.
Evidence
ruby -e 'require "yaml"; ARGV.each { |f| YAML.load_file(f) }' .github/workflows/ci-check-testbox.ymlgit diff --check