build(deps): bump actions/stale from 10 to 11 - #134
Conversation
Bumps [actions/stale](https://github.com/actions/stale) from 10 to 11. - [Release notes](https://github.com/actions/stale/releases) - [Changelog](https://github.com/actions/stale/blob/main/CHANGELOG.md) - [Commits](actions/stale@v10...v11) --- updated-dependencies: - dependency-name: actions/stale dependency-version: '11' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com>
|
Codex review: needs maintainer review before merge. Reviewed August 2, 2026, 12:08 PM ET / 16:08 UTC. ClawSweeper reviewWhat this changesUpdates all three scheduled stale-policy jobs in Merge readiness⛔ Blocked until real behavior proof is added - 5 items remain Keep this PR open for a maintainer-controlled behavior check. Current main still uses Priority: P3 Review scores
Verification
How this fits togetherGitcrawl’s scheduled stale workflow runs three policies against repository issues and pull requests. Each policy sends its configured exemption, staleness, and closure rules to the external flowchart LR
A[Scheduled or manual trigger] --> B[Stale workflow]
B --> C[Unassigned-item policy]
B --> D[Assigned-issue policy]
B --> E[Assigned-PR policy]
C --> F[External stale action]
D --> F
E --> F
F --> G[GitHub labels and closures]
Decision needed
Why: A version-only diff cannot establish the behavior of the external action that will label and close real repository items; accepting a production run as the first behavior test is an operational choice reserved for the repository owner. Before merge
Findings
Agent review detailsSecurityNeeds attention: The code diff is narrow, but it changes executable third-party automation that has write access to issues and pull requests, so live behavior validation is required before merge. Review metrics
Merge-risk optionsMaintainer options:
Technical reviewBest possible solution: Validate the three v11 policies in a disposable repository with representative exempt, assigned, stale, and closure cases, retain redacted run evidence, then merge only if the observed labels and closures match the current policy contract. Do we have a high-confidence way to reproduce the issue? Not applicable: this is a dependency-update PR rather than a reported product bug. The relevant evidence gap is an after-fix controlled run of the external stale-action policies. Is this the best way to solve the issue? No: a version-only update is not sufficient proof for a write-capable major automation change. Controlled policy validation is the narrowest safe path because it tests the real labeling and closure outcomes without changing Gitcrawl code. AGENTS.md: not found in the target repository. Codex review notes: model internal, reasoning high; reviewed against bbaf5ca9cdab. LabelsLabel changes:
Label justifications:
EvidenceSecurity concerns:
What I checked:
Likely related people:
Rank-up movesOptional improvements that raise the rating; they are not merge blockers.
Rating scale
Overall follows the weaker of proof and patch quality. Workflow
HistoryReview history (20 earlier review cycles; latest 8 shown)
|
|
Triaged separately from #136 and intentionally left open. This is a write-capable major automation update: repository-local build and syntax checks cannot prove the actual labeling and closing decisions produced by Recommendation: do not land yet. Peter should either run the three existing policies in a controlled disposable repository with representative assigned, exempt, stale, and closure cases, or explicitly accept the next scheduled production run as the first behavior test. I prefer controlled validation; if that is not worth the operational setup, defer on v10 rather than claiming unearned proof. |
Bumps actions/stale from 10 to 11.
Release notes
Sourced from actions/stale's releases.
... (truncated)
Changelog
Sourced from actions/stale's changelog.
... (truncated)
Commits
4391f3dFix 24 high severity vulnerabilities by overriding brace-expansion to 5.0.8 (...eaf9131refactor: update imports to use ES module syntax and improve test structure (...Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting
@dependabot rebase.Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR:
@dependabot rebasewill rebase this PR@dependabot recreatewill recreate this PR, overwriting any edits that have been made to it@dependabot show <dependency name> ignore conditionswill show all of the ignore conditions of the specified dependency@dependabot ignore this major versionwill close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)@dependabot ignore this minor versionwill close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)@dependabot ignore this dependencywill close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)