groups:
  - name: scheduler-worker
    interval: 30s
    rules:
      - alert: SchedulerPlannerFailuresHigh
        expr: sum(rate(scheduler_planner_runs_total{status="failed"}[5m]))
          /
          sum(rate(scheduler_planner_runs_total[5m])) > 0.05
        for: 10m
        labels:
          severity: critical
          service: scheduler-worker
        annotations:
          summary: "Planner failure ratio above 5%"
          description: "More than 5% of planning runs are failing. Inspect scheduler logs and ImpactIndex connectivity before queues back up."
      - alert: SchedulerPlannerLatencyHigh
        expr: histogram_quantile(0.95, sum by (le) (rate(scheduler_planner_latency_seconds_bucket[5m]))) > 45
        for: 10m
        labels:
          severity: warning
          service: scheduler-worker
        annotations:
          summary: "Planner latency p95 above 45s"
          description: "Planning latency p95 stayed above 45 seconds for 10 minutes. Check ImpactIndex, Mongo, or external selectors to prevent missed SLAs."
      - alert: SchedulerRunnerBacklogGrowing
        expr: max_over_time(scheduler_runner_backlog[15m]) > 500
        for: 15m
        labels:
          severity: warning
          service: scheduler-worker
        annotations:
          summary: "Runner backlog above 500 images"
          description: "Runner backlog exceeded 500 images over the last 15 minutes. Verify runner workers, scanner availability, and rate limits."
      - alert: SchedulerRunStuck
        expr: sum(scheduler_runs_active) > 0 and max_over_time(scheduler_runs_active[30m]) == min_over_time(scheduler_runs_active[30m])
        for: 30m
        labels:
          severity: warning
          service: scheduler-worker
        annotations:
          summary: "Scheduler runs stuck without progress"
          description: "Active runs count has remained flat for 30 minutes. Investigate stuck segments or scanner timeouts."