groups:
  - name: infrastructure
    rules:
      - alert: InstanceDown
        expr: up == 0
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "Instance {{ $labels.instance }} down"
          description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."

      - alert: HighMemoryUsage
        expr: (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes > 0.9
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High memory usage on {{ $labels.instance }}"
          description: "Memory usage is above 90% on {{ $labels.instance }}"

      - alert: HighCPUUsage
        expr: 100 - (avg by(instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High CPU usage on {{ $labels.instance }}"
          description: "CPU usage is above 80% on {{ $labels.instance }}"

  - name: application
    rules:
      - alert: HighErrorRate
        expr: rate(http_requests_total{status=~"5.."}[5m]) / rate(http_requests_total[5m]) > 0.1
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "High error rate on {{ $labels.job }}"
          description: "Error rate is above 10% on {{ $labels.job }}"

      - alert: SlowResponseTime
        expr: histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m])) > 1
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Slow response time on {{ $labels.job }}"
          description: "95th percentile response time is above 1 second on {{ $labels.job }}"

  - name: database
    rules:
      - alert: PostgreSQLDown
        expr: up{job="postgres"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "PostgreSQL is down"
          description: "PostgreSQL database is not responding"

      - alert: Neo4jDown
        expr: up{job="neo4j"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Neo4j is down"
          description: "Neo4j graph database is not responding"

      - alert: QdrantDown
        expr: up{job="qdrant"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Qdrant is down"
          description: "Qdrant vector database is not responding"

      - alert: RedisDown
        expr: up{job="redis"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Redis is down"
          description: "Redis cache is not responding"