sglang/.github/workflows/amd-ci-job-monitor.yml

name: AMD CI Job Monitor

on:
  schedule:
    - cron: '0 0 * * *'  # Daily at midnight UTC
  pull_request:
    paths:
      - '.github/workflows/amd-ci-job-monitor.yml'
      - 'scripts/ci/utils/query_job_status.py'
  workflow_dispatch:
    inputs:
      hours:
        description: 'Time window in hours'
        required: false
        default: '24'
        type: string
      job_filter:
        description: 'Job name filter (leave empty for all AMD jobs)'
        required: false
        type: string

jobs:
  # Single job filter mode
  custom-report:
    name: Custom Job Report
    if: ${{ inputs.job_filter }}
    runs-on: ubuntu-latest
    env:
      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.10'

      - name: Install dependencies
        run: pip install tabulate

      - name: Generate Custom Job Report
        timeout-minutes: 30
        run: |
          python scripts/ci/utils/query_job_status.py \
            --repo ${{ github.repository }} \
            --job "${{ inputs.job_filter }}" \
            --workflow "pr-test-amd.yml" \
            --hours ${{ inputs.hours || '24' }} \
            --summary

  # Parse workflow files to get job names dynamically
  parse-workflows:
    name: Parse Workflow Jobs
    if: ${{ !inputs.job_filter }}
    runs-on: ubuntu-latest
    outputs:
      pr_jobs: ${{ steps.parse.outputs.pr_jobs }}
      nightly_jobs: ${{ steps.parse.outputs.nightly_jobs }}
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Parse workflow files
        id: parse
        run: |
          # Parse pr-test-amd.yml and extract job names (exclude utility jobs)
          # Excluded: call-gate, check-changes, pr-test-amd-finish, cancel, check-all-jobs
          pr_jobs=$(yq -r '.jobs | keys | .[]' .github/workflows/pr-test-amd.yml | \
            grep -v -E '^(call-gate|check-changes|pr-test-amd-finish|cancel|check-all-jobs)$' | \
            jq -R -s -c 'split("\n") | map(select(length > 0))')
          echo "pr_jobs=$pr_jobs" >> $GITHUB_OUTPUT
          echo "PR jobs: $pr_jobs"

          # Parse nightly-test-amd.yml and extract job names (exclude utility jobs)
          # Excluded: check-all-jobs
          nightly_jobs=$(yq -r '.jobs | keys | .[]' .github/workflows/nightly-test-amd.yml | \
            grep -v -E '^(check-all-jobs)$' | \
            jq -R -s -c 'split("\n") | map(select(length > 0))')
          echo "nightly_jobs=$nightly_jobs" >> $GITHUB_OUTPUT
          echo "Nightly jobs: $nightly_jobs"

  # PR CI reports using dynamic matrix
  pr-ci-reports:
    name: PR - ${{ matrix.job_name }}
    needs: parse-workflows
    if: ${{ !inputs.job_filter }}
    runs-on: ubuntu-latest
    strategy:
      fail-fast: false
      matrix:
        job_name: ${{ fromJson(needs.parse-workflows.outputs.pr_jobs) }}
    env:
      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.10'

      - name: Install dependencies
        run: pip install tabulate

      - name: Generate Report
        timeout-minutes: 15
        run: |
          python scripts/ci/utils/query_job_status.py \
            --repo ${{ github.repository }} \
            --job "${{ matrix.job_name }}" \
            --workflow "pr-test-amd.yml" \
            --hours ${{ inputs.hours || '24' }} \
            --summary

  # Nightly AMD test reports using dynamic matrix
  nightly-reports:
    name: Nightly - ${{ matrix.job_name }}
    needs: parse-workflows
    if: ${{ !inputs.job_filter }}
    runs-on: ubuntu-latest
    strategy:
      fail-fast: false
      matrix:
        job_name: ${{ fromJson(needs.parse-workflows.outputs.nightly_jobs) }}
    env:
      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.10'

      - name: Install dependencies
        run: pip install tabulate

      - name: Generate Nightly Report
        timeout-minutes: 15
        run: |
          python scripts/ci/utils/query_job_status.py \
            --repo ${{ github.repository }} \
            --job "${{ matrix.job_name }}" \
            --workflow "nightly-test-amd.yml" \
            --hours ${{ inputs.hours || '24' }} \
            --summary