# Default values for aitbc-monitoring.

# Prometheus configuration
prometheus:
  enabled: true
  server:
    enabled: true
    global:
      scrape_interval: 15s
      evaluation_interval: 15s
    retention: 30d
    persistentVolume:
      enabled: true
      size: 100Gi
    resources:
      limits:
        cpu: 2000m
        memory: 4Gi
      requests:
        cpu: 1000m
        memory: 2Gi
    service:
      type: ClusterIP
      port: 9090
    serviceMonitors:
      enabled: true
      selector:
        release: monitoring
  alertmanager:
    enabled: false
    config:
      global:
        resolve_timeout: 5m
      route:
        group_by: ['alertname']
        group_wait: 10s
        group_interval: 10s
        repeat_interval: 1h
        receiver: 'web.hook'
      receivers:
      - name: 'web.hook'
        webhook_configs:
        - url: 'http://127.0.0.1:5001/'

# Grafana configuration
grafana:
  enabled: true
  adminPassword: admin
  persistence:
    enabled: true
    size: 20Gi
  resources:
    limits:
      cpu: 1000m
      memory: 2Gi
    requests:
      cpu: 500m
      memory: 1Gi
  service:
    type: ClusterIP
    port: 3000
  datasources:
    datasources.yaml:
      apiVersion: 1
      datasources:
        - name: Prometheus
          type: prometheus
          url: http://prometheus-server:9090
          access: proxy
          isDefault: true
  dashboardProviders:
    dashboardproviders.yaml:
      apiVersion: 1
      providers:
        - name: 'default'
          orgId: 1
          folder: ''
          type: file
          disableDeletion: false
          editable: true
          options:
            path: /var/lib/grafana/dashboards/default

# Service monitors for AITBC services
serviceMonitors:
  coordinator:
    enabled: true
    interval: 30s
    path: /metrics
    port: http
  blockchainNode:
    enabled: true
    interval: 30s
    path: /metrics
    port: http
  walletDaemon:
    enabled: true
    interval: 30s
    path: /metrics
    port: http

# Alert rules
alertRules:
  enabled: true
  groups:
    - name: aitbc.rules
      rules:
        - alert: HighErrorRate
          expr: rate(marketplace_errors_total[5m]) / rate(marketplace_requests_total[5m]) > 0.1
          for: 5m
          labels:
            severity: warning
          annotations:
            summary: "High error rate detected"
            description: "Error rate is above 10% for 5 minutes"
        
        - alert: CoordinatorDown
          expr: up{job="coordinator"} == 0
          for: 1m
          labels:
            severity: critical
          annotations:
            summary: "Coordinator is down"
            description: "Coordinator API has been down for more than 1 minute"