infrastructure/alerts/alerts.yml

groups:
  - name: fred-ml
    rules:
      - alert: FredMLHighErrorRate
        expr: rate(http_requests_total{status=~"5.."}[5m]) > 0.1
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "High error rate detected"
          description: "Error rate is {{ $value }} errors per second"

      - alert: FredMLHighResponseTime
        expr: histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m])) > 2
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: "High response time detected"
          description: "95th percentile response time is {{ $value }} seconds"

      - alert: FredMLDown
        expr: up{job="fred-ml"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "FredML service is down"
          description: "FredML service has been down for more than 1 minute"

      - alert: FredMLHighMemoryUsage
        expr: (container_memory_usage_bytes{container="fred-ml"} / container_spec_memory_limit_bytes{container="fred-ml"}) > 0.8
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High memory usage detected"
          description: "Memory usage is {{ $value | humanizePercentage }}"

      - alert: FredMLHighCPUUsage
        expr: rate(container_cpu_usage_seconds_total{container="fred-ml"}[5m]) > 0.8
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High CPU usage detected"
          description: "CPU usage is {{ $value | humanizePercentage }}"

      - alert: FredMLAPIRateLimit
        expr: increase(fred_api_rate_limit_exceeded_total[5m]) > 0
        for: 1m
        labels:
          severity: warning
        annotations:
          summary: "FRED API rate limit exceeded"
          description: "API rate limit has been exceeded in the last 5 minutes"