groups:
  - name: linearvoid
    rules:
      - alert: ChatDown
        expr: up{job="chat"} == 0
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "Chat service is down"
          description: "Chat service has been unreachable for 2 minutes."

      - alert: PlayoutDown
        expr: up{job="playout"} == 0
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "Playout service is down"
          description: "Playout service has been unreachable for 2 minutes."

      - alert: RedisDown
        expr: linearvoid_chat_redis_up == 0
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: "Redis is unreachable"
          description: "Chat service cannot reach Redis. Rate limiting and presence tracking degraded."

      - alert: PlayoutSlateActive
        expr: linearvoid_playout_mode == 1
        for: 1m
        labels:
          severity: warning
        annotations:
          summary: "Playout in slate fallback mode"
          description: "Playout has switched to emergency slate. Check playout logs."

      - alert: HighChatLatency
        expr: histogram_quantile(0.95, sum(rate(linearvoid_chat_request_duration_seconds_bucket[5m])) by (le)) > 1
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Chat request latency is high"
          description: "Chat request p95 has been above 1s for 5 minutes. Check chat handlers and dependencies."

      - alert: PrometheusWALFailing
        expr: increase(prometheus_tsdb_wal_writes_failed_total[5m]) > 0
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Prometheus WAL writes failing"
          description: "Prometheus TSDB WAL write failures detected."

      - alert: HighCPU
        expr: 100 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "High CPU usage"
          description: "CPU usage above 80% for 10 minutes on {{ $labels.instance }}."

      - alert: LowCacheHitRatio
        expr: linearvoid_cache_hit_ratio < 0.9
        for: 15m
        labels:
          severity: warning
        annotations:
          summary: "Cloudflare cache hit ratio is below target"
          description: "Cache hit ratio has been below 90% for 15 minutes on {{ $labels.hostname }}."

      - alert: HighRedisMemoryUsage
        expr: linearvoid_chat_redis_memory_usage_ratio > 0.85
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "Redis memory usage is above target"
          description: "Redis memory usage has been above 85% for 10 minutes on {{ $labels.instance }}."

      - alert: LowDiskSpace
        expr: (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) * 100 < 10
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Low disk space"
          description: "Less than 10% disk space available on {{ $labels.instance }}."