claude-flow-novice/monitoring/alerts/integration-health-alerts.yml

Claude Flow Novice - Advanced orchestration platform for multi-agent AI workflows with CFN Loop architecture Includes Local RuVector Accelerator and all CFN skills for complete functionality.

groups:
  - name: integration_health_alerts
    interval: 30s
    rules:
      - alert: DatabaseServiceDown
        expr: |
          up{job="database_service"} == 0
        for: 2m
        labels:
          severity: critical
          component: database_service
        annotations:
          summary: "Database service is down"
          description: "Database service is not responding"
          runbook_url: "docs/INCIDENT_RESPONSE.md"

      - alert: CoordinationServiceDown
        expr: |
          up{job="coordination_service"} == 0
        for: 2m
        labels:
          severity: critical
          component: coordination_service
        annotations:
          summary: "Coordination service is down"
          description: "Coordination service is not responding"
          runbook_url: "docs/INCIDENT_RESPONSE.md"

      - alert: ArtifactStorageDown
        expr: |
          up{job="artifact_storage"} == 0
        for: 2m
        labels:
          severity: critical
          component: artifact_storage
        annotations:
          summary: "Artifact storage service is down"
          description: "Artifact storage service is not responding"
          runbook_url: "docs/INCIDENT_RESPONSE.md"

      - alert: MetricsCollectionDown
        expr: |
          up{job="metrics_collector"} == 0
        for: 2m
        labels:
          severity: warning
          component: metrics
        annotations:
          summary: "Metrics collection service down"
          description: "Metrics collection service is not responding"

      - alert: RedisDown
        expr: |
          redis_up == 0
        for: 1m
        labels:
          severity: critical
          component: redis
        annotations:
          summary: "Redis is down"
          description: "Redis connection is down"
          runbook_url: "docs/INCIDENT_RESPONSE.md"

      - alert: DatabaseReplicationLag
        expr: |
          pg_replication_lag_seconds > 30
        for: 5m
        labels:
          severity: warning
          component: database
        annotations:
          summary: "Database replication lag high"
          description: "Replication lag is {{ $value | humanize }}s"
          impact: "Failover may take longer"

      - alert: SkillDeploymentFailure
        expr: |
          increase(skill_deployment_failures_total[5m]) > 0
        for: 2m
        labels:
          severity: high
          component: skill_deployment
        annotations:
          summary: "Skill deployment failure detected"
          description: "{{ $value }} skill deployment failures in last 5 minutes"

      - alert: IntegrationPointUnavailable
        expr: |
          integration_point_available == 0
        for: 5m
        labels:
          severity: critical
          component: integration
        annotations:
          summary: "Integration point unavailable"
          description: "Integration point {{ $labels.integration_point }} is unavailable"
          runbook_url: "docs/INCIDENT_RESPONSE.md"

      - alert: DataConsistencyIssues
        expr: |
          increase(data_consistency_violations_total[10m]) > 5
        for: 5m
        labels:
          severity: critical
          component: data_integrity
        annotations:
          summary: "Data consistency violations detected"
          description: "{{ $value }} consistency violations in last 10 minutes"
          runbook_url: "docs/INCIDENT_RESPONSE.md"

      - alert: StaleDatabaseSnapshot
        expr: |
          (time() - last_database_snapshot_timestamp) > 3600
        for: 10m
        labels:
          severity: warning
          component: database
        annotations:
          summary: "Database snapshot stale"
          description: "Last snapshot was {{ $value | humanize }}s ago"

      - alert: CoordinationMessageQueueBacklog
        expr: |
          redis_queue_size > 5000
        for: 10m
        labels:
          severity: high
          component: coordination
        annotations:
          summary: "Coordination message backlog building"
          description: "Queue depth: {{ $value }} messages"
          impact: "Processing may be delayed"

      - alert: HealthCheckFailures
        expr: |
          sum(rate(health_check_failures_total[5m])) > 5
        for: 5m
        labels:
          severity: high
          component: health_check
        annotations:
          summary: "Multiple health check failures"
          description: "{{ $value }} health checks failed per second"

      - alert: IntegrationPointLatencyDegradation
        expr: |
          (histogram_quantile(0.95, rate(integration_point_latency_seconds_bucket[5m])) / on(integration_point) histogram_quantile(0.95, rate(integration_point_latency_seconds_bucket[1h] offset 24h))) > 2
        for: 10m
        labels:
          severity: high
          component: integration
        annotations:
          summary: "Integration point latency degraded"
          description: "{{ $labels.integration_point }} latency doubled"

      - alert: ArtifactStorageBackendDown
        expr: |
          artifact_storage_backend_available == 0
        for: 2m
        labels:
          severity: critical
          component: artifact_storage
        annotations:
          summary: "Artifact storage backend unavailable"
          description: "Backend {{ $labels.backend }} is down"
          runbook_url: "docs/INCIDENT_RESPONSE.md"

      - alert: LoggingServiceDown
        expr: |
          up{job="logging_service"} == 0
        for: 2m
        labels:
          severity: warning
          component: logging
        annotations:
          summary: "Logging service is down"
          description: "Logging service is not responding"
          impact: "Log collection is disabled"

      - alert: SecurityValidationFailures
        expr: |
          sum(rate(security_validation_failures_total[5m])) > 10
        for: 5m
        labels:
          severity: high
          component: security
        annotations:
          summary: "Security validation failures"
          description: "{{ $value }} validation failures per second"

      - alert: IntegrationErrorBudgetExceeded
        expr: |
          (sum(rate(http_requests_total{status=~"5.."}[1h])) / sum(rate(http_requests_total[1h]))) > 0.001
        for: 30m
        labels:
          severity: warning
          component: integration
        annotations:
          summary: "Integration error budget consumed"
          description: "Error rate over 1 hour: {{ $value | humanizePercentage }}"
          impact: "Consider rollback if trend continues"