groups:
  - name: critical
    rules:
      - alert: MementoAppDown
        expr: up{job="memento-app"} == 0
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "Memento app is DOWN"

      - alert: PostgresDown
        expr: up{job="postgres"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "PostgreSQL is DOWN"

      - alert: RedisDown
        expr: up{job="redis"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Redis is DOWN"

      - alert: DiskSpaceLow
        expr: (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) < 0.15
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Disk space below 15%"

      - alert: HighMemoryUsage
        expr: (1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) > 0.90
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Memory usage above 90%"

      - alert: PostgresConnectionsHigh
        expr: pg_stat_activity_count > 80
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "PostgreSQL connections above 80"

      - alert: PostgresSlowQueries
        expr: pg_stat_statements_mean_exec_seconds > 5
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "PostgreSQL slow queries detected"

      - alert: HighErrorRate
        expr: rate(http_requests_total{status=~"5.."}[5m]) > 0.05
        for: 3m
        labels:
          severity: warning
        annotations:
          summary: "HTTP 5xx error rate above 5%"

      - alert: ContainerRestarted
        expr: increase(container_restart_count[1h]) > 0
        for: 1m
        labels:
          severity: warning
        annotations:
          summary: "Container restarted in the last hour"