[CI] Exclude flaky h20 stage from check-stage-health root cause set (#24374)

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-04 11:41:25 -07:00
parent 6dd7aebb36
commit 8ffd39e140
1 changed files with 6 additions and 0 deletions
@@ -56,6 +56,12 @@ runs:
          // 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;
+            // h20 runners are flaky (dirty GPU state from prior runs); their failures
+            // should not cascade fast-fail to other stages. Exact match avoids
+            // accidentally matching the h200 job names.
+            if (j.name === 'stage-c-test-8-gpu-h20') {
+              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'))) {