name: CI Failure Monitor

on:
  schedule:
    - cron: '0 */12 * * *' # Every 12 hour
  workflow_dispatch:

concurrency:
  group: ci-failure-monitor-${{ github.ref }}
  cancel-in-progress: true

permissions:
  contents: read
  actions: read

jobs:
  failure-analysis:
    if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.14'

      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install requests slack_sdk

      - name: Run Failure Analysis
        env:
          GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
          GH_PAT_FOR_RUNNER_ADMIN: ${{ secrets.GH_PAT_FOR_RUNNER_ADMIN }}
          PYTHONUNBUFFERED: 1
          PYTHONIOENCODING: utf-8
        run: |
          cd scripts/ci_monitor
          python ci_failures_analysis.py \
            --token $GITHUB_TOKEN \
            --limit 100 \
            --output ci_failure_analysis_$(date +%Y%m%d_%H%M%S).json

      - name: Upload Analysis Results
        uses: actions/upload-artifact@v4
        with:
          name: ci-failure-analysis-${{ github.run_number }}
          path: |
            scripts/ci_monitor/ci_failure_analysis_*.json
          retention-days: 7

      - name: Send Slack Notification
        if: always()
        env:
          SGLANG_DIFFUSION_SLACK_TOKEN: ${{ secrets.SGLANG_DIFFUSION_SLACK_TOKEN }}
        run: |
          cd scripts/ci_monitor
          LATEST_REPORT=$(ls -t ci_failure_analysis_*.json | head -1)

          if [ ! -f "$LATEST_REPORT" ]; then
            echo "No report found, so skipping Slack notification"
            exit 0
          fi

          if [ -n "$SGLANG_DIFFUSION_SLACK_TOKEN" ]; then
            python3 post_ci_failures_to_slack.py --report-file "$LATEST_REPORT"
          else
            echo "SGLANG_DIFFUSION_SLACK_TOKEN not configured, skipping notification"
          fi