[CI] Rename basic CI stage-a/b/c -> base-a/b/c for symmetry with extra CI (#25420)

2026-05-15 18:26:55 -07:00
parent d0c38329b2
commit b7d62bd724
473 changed files with 745 additions and 746 deletions
@@ -0,0 +1,98 @@
+name: Check PR Test Health
+description: Fail fast if any job in the current workflow run has already failed, or if the lint check (from lint.yml) has failed. Auto-skips for scheduled runs. The jobs-failed check (but not the lint check) is bypassed when the PR carries the `bypass-fastfail` label.
+
+inputs:
+  github-token:
+    description: 'GitHub token for API calls'
+    required: false
+    default: ${{ github.token }}
+
+runs:
+  using: composite
+  steps:
+    - name: Check PR test health
+      uses: actions/github-script@v7
+      env:
+        SKIP_PR_TEST_HEALTH_CHECK: ${{ env.SKIP_PR_TEST_HEALTH_CHECK }}
+      with:
+        github-token: ${{ inputs.github-token }}
+        script: |
+          // Skip when explicitly requested via env var (e.g. release branch cut)
+          if (process.env.SKIP_PR_TEST_HEALTH_CHECK === 'true') {
+            core.info('Skipping health check (SKIP_PR_TEST_HEALTH_CHECK=true)');
+            return;
+          }
+
+          // 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;
+          }
+
+          // Check lint status from the separate Lint workflow (lint.yml).
+          // listJobsForWorkflowRun only sees jobs within the SAME run, so we use
+          // checks.listForRef which queries by commit SHA across ALL workflows.
+          const ref = context.payload.pull_request?.head?.sha || context.sha;
+          const { data } = await github.rest.checks.listForRef({
+            owner: context.repo.owner,
+            repo: context.repo.repo,
+            ref: ref,
+            check_name: 'lint',
+          });
+          const lintRun = data.check_runs.find(
+            cr => cr.app?.slug === 'github-actions'
+          );
+          if (lintRun?.status === 'completed' && lintRun?.conclusion === 'failure') {
+            core.setFailed('Fast-fail: lint check failed');
+            return;
+          }
+
+          // Skip the jobs-failed check when the PR carries the bypass-fastfail label.
+          // Lint check above still runs.
+          let labels = [];
+          if (context.payload.pull_request?.labels) {
+            labels = context.payload.pull_request.labels.map(l => l.name);
+          } else {
+            const { data: prs } = await github.rest.repos.listPullRequestsAssociatedWithCommit({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              commit_sha: ref,
+            });
+            if (prs.length > 0) {
+              labels = prs[0].labels.map(l => l.name);
+            }
+          }
+          if (labels.includes('bypass-fastfail')) {
+            core.info('Skipping jobs-failed check (bypass-fastfail label present)');
+            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;
+            // h20 runners are flaky (dirty GPU state from prior runs); their failures
+            // should not cascade fast-fail to other stages. j.name shape from
+            // listJobsForWorkflowRun: "<job-key>" + optional " / <reusable-job>"
+            // + optional " (<matrix>)". Split off the base job key before exact
+            // match so we cover both inline + reusable forms without confusing
+            // 'h20' with the 'h200' prefix.
+            const baseName = j.name.split(/[ /]/)[0];
+            if (baseName === 'base-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-pr-test-health') || failedStep.name.includes('Check PR test health'))) {
+              return false;
+            }
+            return true;
+          });
+          if (rootCauseFailures.length > 0) {
+            core.setFailed(`Fast-fail: skipping — root cause job(s): ${rootCauseFailures.map(j => j.name).join(', ')}`);
+          }