dev-cluster/.github/workflows/health_monitor.yaml

name: Cluster Health Monitor

on:
  schedule:
    - cron: '0 * * * *'
  workflow_dispatch:

jobs:
  health-check:
    name: Monitor Cluster Endpoints
    runs-on: ubuntu-latest
    steps:
      - name: Check endpoints
        run: |
          # Simple and clean endpoint checker
          ENDPOINTS="${{ secrets.CLUSTER_ENDPOINTS }}"
          
          # Validate input
          if [[ -z "$ENDPOINTS" ]]; then
            echo "❌ No endpoints found in CLUSTER_ENDPOINTS secret"
            exit 1
          fi
          
          # Initialize counters
          total=0
          failed=0
          
          # Process each endpoint
          while IFS= read -r url; do
            # Skip empty lines and comments
            [[ -z "$url" || "$url" =~ ^[[:space:]]*# ]] && continue
            url=$(echo "$url" | xargs)
            [[ -z "$url" ]] && continue
            
            total=$((total + 1))
            echo "Testing: $url"
            
            # Get HTTP status code
            status=$(curl -sfLI --max-time 10 -o /dev/null -w "%{http_code}" "$url" 2>&1 || echo "000")
            
            # Accept 2xx, 3xx, 401, and 403 as healthy
            if [[ "$status" =~ ^(2|3|401|403) ]]; then
              echo "✅ OK (HTTP $status)"
            else
              echo "❌ FAILED (HTTP $status)"
              failed=$((failed + 1))
            fi
            echo ""
            
          done <<< "$ENDPOINTS"
          
          # Summary
          echo "📊 Summary: $((total - failed))/$total endpoints OK"
          
          # Exit with error if any failed
          if [[ $failed -gt 0 ]]; then
            echo "💥 $failed endpoint(s) failed!"
            exit 1
          else
            echo "🎉 All endpoints healthy!"
          fi