# Wordly.art - Prometheus Alert Rules

groups:
  # Application alerts
  - name: wordly_app
    rules:
      - alert: BackendDown
        expr: up{job="wordly-backend"} == 0
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "Wordly backend is down"
          description: "Backend has been down for more than 2 minutes."

      - alert: HighErrorRate
        expr: rate(http_requests_total{status=~"5.."}[5m]) / rate(http_requests_total[5m]) > 0.1
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High error rate detected"
          description: "More than 10% of requests are returning 5xx errors."

      - alert: SlowTranslations
        expr: histogram_quantile(0.95, rate(translation_duration_seconds_bucket[5m])) > 120
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "Translations are slow"
          description: "95th percentile translation time is over 120 seconds."

      - alert: HighTranslationQueue
        expr: translation_queue_size > 20
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Translation queue is backing up"
          description: "More than 20 translations queued."

  # System alerts
  - name: wordly_system
    rules:
      - 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"
          description: "Server memory usage is above 90%."

      - alert: DiskSpaceLow
        expr: (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) < 0.15
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "Low disk space"
          description: "Less than 15% disk space remaining on /."

      - alert: DiskSpaceCritical
        expr: (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) < 0.05
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "Critical disk space"
          description: "Less than 5% disk space remaining on /."

      - alert: HighCPUUsage
        expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 85
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "High CPU usage"
          description: "CPU usage is above 85% for 10 minutes."

  # Docker alerts
  - name: wordly_docker
    rules:
      - alert: ContainerRestarted
        expr: increase(container_restart_count[1h]) > 2
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Container restarting"
          description: "Container {{ $labels.name }} has restarted more than 2 times in the last hour."

      - alert: ContainerOOM
        expr: increase(container_oom_events_total[1h]) > 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Container OOM killed"
          description: "Container {{ $labels.name }} was OOM killed."