[CI] Add cross-job fast-fail health check (Layer 3) (#21341)

2026-03-24 16:58:56 -07:00
parent 1046dbe038
commit 3937a07b17
5 changed files with 105 additions and 0 deletions
@@ -0,0 +1,42 @@
+name: Check Stage Health
+description: Fail fast if any job in the current workflow run has already failed. Auto-skips for scheduled runs.
+
+inputs:
+  github-token:
+    description: 'GitHub token for API calls'
+    required: false
+    default: ${{ github.token }}
+
+runs:
+  using: composite
+  steps:
+    - name: Check stage health
+      uses: actions/github-script@v7
+      with:
+        github-token: ${{ inputs.github-token }}
+        script: |
+          // Skip for scheduled runs — they should collect all failures, not fast-fail
+          if (context.eventName === 'schedule') {
+            core.info('Skipping health check for scheduled run');
+            return;
+          }
+
+          const jobs = await github.paginate(github.rest.actions.listJobsForWorkflowRun, {
+            owner: context.repo.owner,
+            repo: context.repo.repo,
+            run_id: context.runId,
+            per_page: 100,
+          });
+          // Find jobs that failed from a real error, not from fast-fail cascade
+          const rootCauseFailures = jobs.filter(j => {
+            if (j.status !== 'completed' || j.conclusion !== 'failure') return false;
+            // If the failing step is the health check, it's a cascade — skip it
+            const failedStep = (j.steps || []).find(s => s.conclusion === 'failure');
+            if (failedStep && (failedStep.name.includes('check-stage-health') || failedStep.name.includes('Check stage health'))) {
+              return false;
+            }
+            return true;
+          });
+          if (rootCauseFailures.length > 0) {
+            core.setFailed(`Fast-fail: skipping — root cause job(s): ${rootCauseFailures.map(j => j.name).join(', ')}`);
+          }