From 8ffd39e1402ddc45aad3212af69a26d0c2aae555 Mon Sep 17 00:00:00 2001 From: Kangyan-Zhou Date: Mon, 4 May 2026 11:41:25 -0700 Subject: [PATCH] [CI] Exclude flaky h20 stage from check-stage-health root cause set (#24374) Co-authored-by: Claude Opus 4.7 (1M context) --- .github/actions/check-stage-health/action.yml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/.github/actions/check-stage-health/action.yml b/.github/actions/check-stage-health/action.yml index 536b3ad3f..8fbf44d17 100644 --- a/.github/actions/check-stage-health/action.yml +++ b/.github/actions/check-stage-health/action.yml @@ -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'))) {