Aethero_App/monitoring/aetheros_rules.yml

groups:
  - name: AetheroOS Alerts
    rules:
      # Agent Health Alerts
      - alert: AgentDown
        expr: up{job=~"aetheros_agents.*"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Agent {{ $labels.agent_id }} is down"
          description: "Agent {{ $labels.agent_id }} has been down for more than 1 minute"

      - alert: HighAgentLatency
        expr: rate(aetheros_agent_response_time_seconds_sum[5m]) / rate(aetheros_agent_response_time_seconds_count[5m]) > 2
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High latency for {{ $labels.agent_id }}"
          description: "Agent {{ $labels.agent_id }} has response time > 2s for 5 minutes"

      # Reflection Quality Alerts
      - alert: LowReflectionQuality
        expr: aetheros_reflection_quality_score < 0.7
        for: 15m
        labels:
          severity: warning
        annotations:
          summary: "Low reflection quality detected"
          description: "Reflection quality score has been below 0.7 for 15 minutes"

      - alert: ReflectionProcessingStalled
        expr: rate(aetheros_reflections_processed_total[15m]) == 0
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "Reflection processing has stalled"
          description: "No reflections have been processed in the last 15 minutes"

      # Memory System Alerts
      - alert: HighMemoryLatency
        expr: histogram_quantile(0.95, sum(rate(aetheros_mem_latency_bucket[5m])) by (le)) > 0.5
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High memory system latency"
          description: "95th percentile of memory operations taking >500ms"

      - alert: HighMemoryErrorRate
        expr: rate(aetheros_mem_operations_error_total[5m]) / rate(aetheros_mem_operations_total[5m]) > 0.01
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High memory operation error rate"
          description: "Memory operation error rate > 1% for 5 minutes"

      # Pipeline Execution Alerts
      - alert: LowPipelineSuccessRate
        expr: sum(rate(aetheros_pipeline_executions_success[5m])) / sum(rate(aetheros_pipeline_executions_total[5m])) < 0.95
        for: 15m
        labels:
          severity: critical
        annotations:
          summary: "Low pipeline success rate"
          description: "Pipeline success rate below 95% for 15 minutes"

      - alert: LongPipelineDuration
        expr: histogram_quantile(0.95, sum(rate(aetheros_pipeline_duration_seconds_bucket[5m])) by (le)) > 300
        for: 15m
        labels:
          severity: warning
        annotations:
          summary: "Long pipeline execution times"
          description: "95th percentile of pipeline executions taking >5 minutes"

      # Resource Usage Alerts
      - alert: HighCPUUsage
        expr: rate(process_cpu_seconds_total{job=~"aetheros_agents.*"}[5m]) > 0.8
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "High CPU usage for {{ $labels.agent_id }}"
          description: "Agent {{ $labels.agent_id }} CPU usage >80% for 10 minutes"

      - alert: HighMemoryUsage
        expr: process_resident_memory_bytes{job=~"aetheros_agents.*"} / node_memory_MemTotal_bytes > 0.8
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "High memory usage for {{ $labels.agent_id }}"
          description: "Agent {{ $labels.agent_id }} memory usage >80% for 10 minutes"

      # System Health Alerts
      - alert: HighErrorRate
        expr: sum(rate(aetheros_error_total[5m])) by (agent_id) > 0.05
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High error rate for {{ $labels.agent_id }}"
          description: "Error rate >5% for {{ $labels.agent_id }} over 5 minutes"

      - alert: SystemOverload
        expr: sum(rate(aetheros_agent_queue_size[5m])) by (agent_id) > 1000
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "System overload for {{ $labels.agent_id }}"
          description: "Queue size >1000 for {{ $labels.agent_id }} over 5 minutes"