GET /health

{
  "status": "healthy",
  "timestamp": "2024-01-15T10:30:00Z",
  "version": "0.1.0",
  "uptime": "15d 6h 30m 45s",
  "services": {
    "database": "healthy",
    "websocket": "healthy",
    "monitoring": "healthy"
  }
}

{
  "status": "healthy",
  "timestamp": "2024-01-15T10:30:00Z",
  "version": "0.1.0",
  "uptime": "15d 6h 30m 45s",
  "services": {
    "database": "healthy",
    "websocket": "healthy",
    "monitoring": "healthy",
    "scheduler": "healthy"
  },
  "metrics": {
    "activeConnections": 15,
    "memoryUsage": "45.2MB",
    "cpuUsage": "12.5%"
  }
}

{
  "status": "degraded",
  "timestamp": "2024-01-15T10:30:00Z",
  "version": "0.1.0",
  "uptime": "15d 6h 30m 45s",
  "services": {
    "database": "healthy",
    "websocket": "healthy",
    "monitoring": "unhealthy",
    "scheduler": "healthy"
  },
  "issues": [
    {
      "service": "monitoring",
      "status": "unhealthy",
      "message": "Metrics collection service not responding",
      "impact": "Metrics and monitoring functionality degraded"
    }
  ],
  "metrics": {
    "activeConnections": 15,
    "memoryUsage": "45.2MB",
    "cpuUsage": "12.5%"
  }
}

{
  "status": "unhealthy",
  "timestamp": "2024-01-15T10:30:00Z",
  "version": "0.1.0",
  "uptime": "15d 6h 30m 45s",
  "services": {
    "database": "unhealthy",
    "websocket": "healthy",
    "monitoring": "unhealthy",
    "scheduler": "unhealthy"
  },
  "issues": [
    {
      "service": "database",
      "status": "unhealthy",
      "message": "Database connection failed",
      "impact": "All data operations unavailable"
    },
    {
      "service": "scheduler",
      "status": "unhealthy",
      "message": "Scheduler service not running",
      "impact": "Scheduled jobs not executing"
    }
  ],
  "recommendations": [
    "Check database connectivity",
    "Restart scheduler service",
    "Review application logs for errors"
  ]
}

# Simple health check (returns 200 if healthy)
curl -f http://localhost:3000/health

# Get detailed health information
curl http://localhost:3000/health | jq .

# Check specific service
curl http://localhost:3000/health | jq '.services.database'

# Prometheus configuration
scrape_configs:
  - job_name: 'o1-health'
    static_configs:
      - targets: ['localhost:3000']
    metrics_path: '/health'
    params:
      format: ['prometheus']

{
  "status": "unhealthy",
  "error": "Service unavailable",
  "message": "Health check endpoint not accessible",
  "timestamp": "2024-01-15T10:30:00Z"
}

# Nginx configuration
upstream o1_backend {
  server localhost:3000;
}

server {
  location /health {
    proxy_pass http://o1_backend/health;
    proxy_next_upstream error timeout invalid_header;
    proxy_connect_timeout 2s;
    proxy_read_timeout 5s;
  }
}

# Dockerfile health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
  CMD curl -f http://localhost:3000/health || exit 1

# Kubernetes deployment
apiVersion: apps/v1
kind: Deployment
spec:
  template:
    spec:
      containers:
        - name: o1-backend
          livenessProbe:
            httpGet:
              path: /health
              port: 3000
            initialDelaySeconds: 30
            periodSeconds: 10
          readinessProbe:
            httpGet:
              path: /health
              port: 3000
            initialDelaySeconds: 5
            periodSeconds: 5

# Check service logs
docker-compose logs backend

# Verify dependencies
curl http://localhost:3000/health

# Check database connectivity
psql -h localhost -U o1 -d o1

# Check memory usage
top -p $(pgrep -f "node.*o1")

# Monitor connections
netstat -an | grep :3000 | wc -l

# Check for memory leaks
node --inspect-brk server.js

# Check port availability
netstat -tulpn | grep :3000

# Test connectivity
telnet localhost 3000

# Check firewall rules
ufw status