groups:
  - name: signals-pipeline
    rules:
      - alert: SignalsScoringLatencyP95High
        expr: histogram_quantile(0.95, sum(rate(signals_reachability_scoring_duration_seconds_bucket[5m])) by (le)) > 2
        for: 10m
        labels:
          severity: warning
          service: signals
        annotations:
          summary: "Signals scoring latency high (p95)"
          description: "Reachability scoring p95 exceeds 2s for 10m"

      - alert: SignalsCacheMissRateHigh
        expr: |
          clamp_min(rate(signals_cache_misses_total[5m]), 0)
          / clamp_min(rate(signals_cache_hits_total[5m]) + rate(signals_cache_misses_total[5m]), 1) > 0.3
        for: 10m
        labels:
          severity: warning
          service: signals
        annotations:
          summary: "Signals cache miss rate high"
          description: "Cache miss ratio >30% over 10m; investigate Redis or key churn."

      - alert: SignalsCacheDown
        expr: signals_cache_available == 0
        for: 2m
        labels:
          severity: critical
          service: signals
        annotations:
          summary: "Signals cache unavailable"
          description: "Redis cache reported unavailable for >2m"

      - alert: SignalsSensorStaleness
        expr: time() - max(signals_sensor_last_seen_timestamp_seconds) by (sensor) > 900
        for: 5m
        labels:
          severity: warning
          service: signals
        annotations:
          summary: "Signals sensor stale"
          description: "No updates from sensor for >15 minutes"

      - alert: SignalsIngestionErrorRate
        expr: clamp_min(rate(signals_ingestion_failures_total[5m]), 0) / clamp_min(rate(signals_ingestion_total[5m]), 1) > 0.05
        for: 5m
        labels:
          severity: critical
          service: signals
        annotations:
          summary: "Signals ingestion failures elevated"
          description: "Ingestion failure ratio above 5% over 5m"