blackroad-operating-system/.github/workflows/health-check.yml

name: Production Health Check

on:
  schedule:
    # Run every hour
    - cron: '0 * * * *'
  workflow_dispatch:

jobs:
  health-check:
    runs-on: ubuntu-latest

    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Check service health
        run: |
          echo "Checking health endpoints..."

          # Read service URLs from environment or config
          SERVICES=(
            "https://api.blackroad.io/health"
            "https://agents.blackroad.io/health"
            "https://monitoring.blackroad.io/health"
          )

          FAILED=0
          for url in "${SERVICES[@]}"; do
            echo "Testing: $url"
            if curl -f -s -o /dev/null -w "%{http_code}" "$url" | grep -q "200"; then
              echo "✅ $url is healthy"
            else
              echo "❌ $url is unhealthy"
              FAILED=$((FAILED + 1))
            fi
          done

          if [ $FAILED -gt 0 ]; then
            echo "⚠️  $FAILED service(s) failed health check (may be offline/unreachable)"
            echo "::warning::$FAILED service(s) failed health check"
          else
            echo "✅ All services healthy"
          fi

      - name: Notify on failure
        if: failure()
        run: |
          echo "Health check failed! Notification would be sent here."
          # Add Slack/Discord/email notification here