# Alert rules surfaced in Grafana's alerting UI (no Alertmanager needed at
# this scale — Grafana can route them later via email/Telegram).
groups:
  - name: erp-availability
    rules:
      - alert: ErpApiDown
        expr: up{job="erp-api"} == 0
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "ERP API is not scraping (down or /metrics failing)"

      - alert: ErpApiHighErrorRate
        expr: |
          sum(rate(http_requests_total{job="erp-api", status=~"5.."}[5m]))
            / clamp_min(sum(rate(http_requests_total{job="erp-api"}[5m])), 0.001) > 0.05
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "ERP API 5xx rate above 5% for 5 minutes"

      - alert: ErpApiSlowRequests
        expr: |
          histogram_quantile(0.95,
            sum(rate(http_request_duration_seconds_bucket{job="erp-api"}[5m])) by (le)) > 2
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "ERP API p95 latency above 2s for 10 minutes"

  - name: host
    rules:
      - alert: HostDiskAlmostFull
        expr: (node_filesystem_avail_bytes{mountpoint="/", fstype!~"tmpfs|overlay"} / node_filesystem_size_bytes{mountpoint="/", fstype!~"tmpfs|overlay"}) < 0.1
        for: 15m
        labels:
          severity: critical
        annotations:
          summary: "Root filesystem below 10% free (deploy builds will fail)"

      - alert: HostMemoryPressure
        expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes < 0.1
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "Host RAM below 10% available (check monitoring stack limits)"

      - alert: PostgresTooManyConnections
        expr: sum(pg_stat_activity_count) > 80
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "PostgreSQL connection count above 80"