# Basic health check
curl http://localhost:12005/api/health

# Example response
{
  "status": "healthy",
  "timestamp": "2025-11-10T18:00:00.000Z",
  "checks": {
    "service": true,
    "database": true
  }
}

# .env configuration
METRICS_ALLOWED_IPS="127.0.0.1,::1,172.17.0.0/16,172.18.0.0/16,185.96.168.253/32"

# HEAD request for load balancers
curl -I http://localhost:12005/api/health

# Returns:
# 200 OK - healthy
# 503 Service Unavailable - unhealthy

# Access metrics (requires IP whitelist)
curl http://localhost:12005/api/metrics

# Filter specific metrics
curl http://localhost:12005/api/metrics | grep pluggedin_http

# Development (permissive for Docker)
METRICS_ALLOWED_IPS="127.0.0.1,::1,172.17.0.0/16,172.18.0.0/16"

# Production (restrictive)
METRICS_ALLOWED_IPS="127.0.0.1,::1,172.17.0.0/16,172.18.0.0/16,185.96.168.253/32"

scrape_configs:
  - job_name: 'pluggedin-app'
    metrics_path: '/api/metrics'
    scheme: 'https'  # or 'http' for local
    static_configs:
      - targets: ['plugged.in']  # or 'localhost:12005'
        labels:
          service: 'pluggedin-app'
          environment: 'production'
    scrape_interval: 30s
    scrape_timeout: 10s

groups:
  - name: pluggedin_app_health
    interval: 30s
    rules:
      - alert: PluggedinAppDown
        expr: up{job="pluggedin-app"} == 0
        for: 2m
        labels:
          severity: critical
          service: pluggedin-app
          category: availability
        annotations:
          summary: "Plugged.in application is down"
          description: "No metrics are being scraped for 2+ minutes"

      - alert: PluggedinAppDatabaseDown
        expr: pluggedin_http_errors_total{path="/api/health", status_code="503"} > 0
        for: 3m
        labels:
          severity: critical
          service: pluggedin-app
          category: database
        annotations:
          summary: "Database connection lost"
          description: "Health check returning 503 due to database issues"

  - name: pluggedin_app_performance
    interval: 30s
    rules:
      - alert: HighMemoryUsage
        expr: (pluggedin_nodejs_heap_size_used_bytes / pluggedin_nodejs_heap_size_total_bytes) > 0.80
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "High memory usage (>80%)"

      - alert: HighEventLoopLag
        expr: pluggedin_nodejs_eventloop_lag_seconds > 0.1
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High event loop lag (>100ms)"

      - alert: HighLatency
        expr: histogram_quantile(0.95, rate(pluggedin_http_request_duration_seconds_bucket[5m])) > 2
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "P95 latency > 2s"

# Application uptime
time() - pluggedin_process_start_time_seconds

# Memory usage percentage
(pluggedin_nodejs_heap_size_used_bytes / pluggedin_nodejs_heap_size_total_bytes) * 100

# Request rate (requests/sec)
rate(pluggedin_http_requests_total[5m])

# Error rate percentage
(rate(pluggedin_http_errors_total[5m]) / rate(pluggedin_http_requests_total[5m])) * 100

# P95 latency by endpoint
histogram_quantile(0.95,
  sum by (path, le) (rate(pluggedin_http_request_duration_seconds_bucket[5m]))
)

# Active connections trend
rate(pluggedin_nodejs_active_handles[5m])