ci-doctor: remove workflow_run, stop-after, and if#22615
Conversation
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> Agent-Logs-Url: https://github.com/github/gh-aw/sessions/f0ddb5f9-e40a-493e-8629-f17bcfda94c1
There was a problem hiding this comment.
Pull request overview
Removes unused/undesired frontmatter controls from the ci-doctor agentic workflow so it no longer triggers on workflow_run, no longer has a stop-time cutoff, and no longer relies on a top-level conditional.
Changes:
- Removed the
workflow_runtrigger from.github/workflows/ci-doctor.md. - Removed
stop-after: +1moand the top-levelif:condition from the workflow source and recompiled the generated lock workflow accordingly. - Updated the compiled workflow (
ci-doctor.lock.yml) to activate only on PR label events forci-doctorand to drop the stop-time enforcement step.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| .github/workflows/ci-doctor.md | Removes workflow_run, stop-after, and top-level if from the workflow frontmatter. |
| .github/workflows/ci-doctor.lock.yml | Recompiled output reflecting trigger/activation changes and removal of stop-time gating. |
Comments suppressed due to low confidence (1)
.github/workflows/ci-doctor.md:6
- With the
workflow_runtrigger removed from the frontmatter, the workflow'sworkflow_run-specific mode/steps in this file become unreachable (e.g., steps guarded byif: github.event_name == 'workflow_run'and the "CI Failure Investigation Mode" section later). Consider removing that mode/steps or updating the trigger/docs so the behavior is consistent and future readers aren’t misled.
on:
label_command:
name: ci-doctor
events: [pull_request]
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| @@ -1,21 +1,9 @@ | |||
| --- | |||
| description: Investigates failed CI workflows to identify root causes and patterns, creating issues with diagnostic information; also reviews PR check failures when the ci-doctor label is applied | |||
There was a problem hiding this comment.
After removing the workflow_run trigger, the workflow no longer automatically investigates failed CI runs. The frontmatter description still says it investigates failed CI workflows and creates issues; please update it to reflect the remaining PR label-triggered behavior (or reintroduce an appropriate trigger).
This issue also appears on line 3 of the same file.
| description: Investigates failed CI workflows to identify root causes and patterns, creating issues with diagnostic information; also reviews PR check failures when the ci-doctor label is applied | |
| description: Reviews PR CI and check failures when the ci-doctor label command is used, identifying root causes and patterns and creating issues with diagnostic information as needed |
Removes three frontmatter fields from the ci-doctor workflow:
workflow_runtrigger (and its sub-configuration)stop-after: +1moif:conditionRecompiled the lock file accordingly.