sglang/.github/actions/check-pr-test-health/action.yml

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-fail-fast` label (or `highest-priority`, which implies it).

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@v8
      env:
        SKIP_PR_TEST_HEALTH_CHECK: ${{ env.SKIP_PR_TEST_HEALTH_CHECK }}
      with:
        github-token: ${{ inputs.github-token }}
        script: |
          core.info(`[health-check] START -- event=${context.eventName}, runId=${context.runId}`);

          // Skip when explicitly requested via env var (e.g. release branch cut)
          if (process.env.SKIP_PR_TEST_HEALTH_CHECK === 'true') {
            core.info('[health-check] SKIP: SKIP_PR_TEST_HEALTH_CHECK=true');
            return;
          }

          // Skip for scheduled runs -- they should collect all failures, not fail-fast
          if (context.eventName === 'schedule') {
            core.info('[health-check] SKIP: 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;
          core.info(`[health-check] Checking lint for ref=${ref}`);
          const { data } = await github.rest.checks.listForRef({
            owner: context.repo.owner,
            repo: context.repo.repo,
            ref: ref,
            check_name: 'lint',
          });
          const lintRun = data.check_runs.find(
            cr => cr.app?.slug === 'github-actions'
          );
          core.info(`[health-check] Lint check: status=${lintRun?.status}, conclusion=${lintRun?.conclusion}`);
          if (lintRun?.status === 'completed' && lintRun?.conclusion === 'failure') {
            core.setFailed('Fail-fast: lint check failed');
            return;
          }

          // The lint check above is never bypassed; only sibling failures are.
          const { resolveCiLabels } = require(
            `${process.env.GITHUB_WORKSPACE}/.github/scripts/ci-labels.cjs`
          );
          const axes = await resolveCiLabels(github, context);
          core.info(`[health-check] PR labels: [${axes.labels.join(', ')}]`);
          if (axes.bypassFailFast) {
            core.info('[health-check] SKIP jobs-failed check: bypass-fail-fast 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,
          });
          core.info(`[health-check] Total jobs in run: ${jobs.length}`);
          const failedJobs = jobs.filter(j => j.status === 'completed' && j.conclusion === 'failure');
          core.info(`[health-check] Failed jobs (before filtering): ${failedJobs.map(j => `${j.name}(${j.conclusion})`).join(', ') || 'none'}`);

          // Find jobs that failed from a real error, not from fail-fast 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 fail-fast 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') {
              core.info(`[health-check] Filtered out h20 job: ${j.name}`);
              return false;
            }
            // multimodal-gen NPU tests should not cascade fail-fast to perf/accuracy stages.
            if (baseName === 'multimodal-gen-test-1-npu-a3' || baseName === 'multimodal-gen-test-2-npu-a3') {
              core.info(`[health-check] Filtered out multimodal-gen NPU job: ${j.name}`);
              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'))) {
              core.info(`[health-check] Filtered out cascade failure: ${j.name} (failed step: ${failedStep.name})`);
              return false;
            }
            return true;
          });
          core.info(`[health-check] Root cause failures (after filtering): ${rootCauseFailures.map(j => j.name).join(', ') || 'none'}`);

          if (rootCauseFailures.length > 0) {
            core.setFailed(`Fail-fast: skipping — root cause job(s): ${rootCauseFailures.map(j => j.name).join(', ')}`);
          } else {
            core.info('[health-check] PASS: no root cause failures detected');
          }