claude-flow-novice/monitoring/alerts/error-rate-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: error_rate_alerts
    interval: 30s
    rules:
      - alert: HighErrorRate
        expr: |
          (sum(rate(http_requests_total{status=~"5.."}[5m])) / sum(rate(http_requests_total[5m]))) > 0.01
        for: 5m
        labels:
          severity: critical
          component: integration
        annotations:
          summary: "High error rate detected"
          description: "Error rate is {{ $value | humanizePercentage }} (threshold: 1%)"
          runbook_url: "docs/INCIDENT_RESPONSE.md"

      - alert: ErrorRateWarning
        expr: |
          (sum(rate(http_requests_total{status=~"5.."}[5m])) / sum(rate(http_requests_total[5m]))) > 0.001
        for: 10m
        labels:
          severity: warning
          component: integration
        annotations:
          summary: "Elevated error rate detected"
          description: "Error rate is {{ $value | humanizePercentage }} (threshold: 0.1%)"

      - alert: DatabaseErrorRate
        expr: |
          (sum(rate(db_queries_failed_total[5m])) / sum(rate(db_queries_total[5m]))) > 0.01
        for: 5m
        labels:
          severity: critical
          component: database
        annotations:
          summary: "High database error rate"
          description: "Database error rate is {{ $value | humanizePercentage }}"
          runbook_url: "docs/ROLLBACK_RUNBOOK.md"

      - alert: CoordinationProtocolErrors
        expr: |
          (sum(rate(coordination_protocol_errors_total[5m])) / sum(rate(coordination_messages_total[5m]))) > 0.05
        for: 5m
        labels:
          severity: high
          component: coordination
        annotations:
          summary: "High coordination protocol error rate"
          description: "Protocol error rate is {{ $value | humanizePercentage }} (threshold: 5%)"

      - alert: IntegrationPointFailures
        expr: |
          sum(rate(integration_point_failures_total[5m])) > 5
        for: 5m
        labels:
          severity: high
          component: integration
        annotations:
          summary: "Integration point failures detected"
          description: "{{ $value }} integration point failures per second"

      - alert: SkillExecutionFailures
        expr: |
          (sum(rate(skill_executions_failed_total[5m])) / sum(rate(skill_executions_total[5m]))) > 0.05
        for: 10m
        labels:
          severity: warning
          component: skill_deployment
        annotations:
          summary: "Elevated skill execution failure rate"
          description: "Skill failure rate is {{ $value | humanizePercentage }}"

      - alert: DataValidationErrors
        expr: |
          sum(rate(data_validation_errors_total[5m])) > 10
        for: 5m
        labels:
          severity: critical
          component: data_integrity
        annotations:
          summary: "Data validation errors detected"
          description: "{{ $value }} validation errors per second - possible data corruption"
          runbook_url: "docs/INCIDENT_RESPONSE.md"

      - alert: TransactionRollbacks
        expr: |
          sum(rate(db_transactions_rolled_back_total[5m])) > 50
        for: 10m
        labels:
          severity: high
          component: database
        annotations:
          summary: "High transaction rollback rate"
          description: "{{ $value }} transactions rolled back per second"

      - alert: ArtifactStorageErrors
        expr: |
          (sum(rate(artifact_storage_errors_total[5m])) / sum(rate(artifact_storage_operations_total[5m]))) > 0.01
        for: 5m
        labels:
          severity: high
          component: artifact_storage
        annotations:
          summary: "Artifact storage errors detected"
          description: "{{ $value | humanizePercentage }} of operations failed"

      - alert: MetricCollectionErrors
        expr: |
          sum(rate(metrics_collection_errors_total[5m])) > 100
        for: 10m
        labels:
          severity: warning
          component: metrics
        annotations:
          summary: "Metrics collection failures"
          description: "{{ $value }} metric collection errors per second"