# kube-prometheus-stack Helm Values — Auto-generated by hmcmkit
# helm install monitoring prometheus-community/kube-prometheus-stack -f values.yaml

prometheus:
  prometheusSpec:
    retention: 15d
    resources:
      requests: { cpu: "500m", memory: "1Gi" }
      limits: { cpu: "1", memory: "2Gi" }
    serviceMonitorSelector: {}
    podMonitorSelector: {}

grafana:
  enabled: true
  adminPassword: "${GRAFANA_ADMIN_PASSWORD}"
  dashboardProviders:
    dashboardproviders.yaml:
      apiVersion: 1
      providers:
        - name: default
          folder: ''
          type: file
          options:
            path: /var/lib/grafana/dashboards/default
  datasources:
    datasources.yaml:
      apiVersion: 1
      datasources:
        - name: Prometheus
          type: prometheus
          url: http://monitoring-kube-prometheus-prometheus:9090
          isDefault: true
        - name: Loki
          type: loki
          url: http://loki:3100
        - name: Tempo
          type: tempo
          url: http://tempo:3100
        - name: Sentry
          type: sentry
          url: "${SENTRY_API_URL}"
          jsonData:
            orgSlug: "${SENTRY_ORG_SLUG}"
          secureJsonData:
            authToken: "${SENTRY_AUTH_TOKEN}"

  # Pre-built dashboards
  dashboards:
    default:
      service-health:
        json: |
          # Service Health Dashboard — Error Rate + Latency + Sentry Issues
          # Auto-generated by hmcmkit enterprise
      error-tracking:
        json: |
          # Error Tracking Dashboard — Sentry integration
          # Panels: Unresolved issues, Error rate trend, Top errors, Affected users

alertmanager:
  config:
    route:
      receiver: 'slack-notifications'
      group_by: ['alertname', 'namespace']
      group_wait: 30s
      group_interval: 5m
      repeat_interval: 4h
      routes:
        - match:
            severity: critical
          receiver: 'pagerduty-critical'
        - match:
            severity: warning
          receiver: 'slack-notifications'
    receivers:
      - name: 'slack-notifications'
        slack_configs:
          - api_url: "${SLACK_WEBHOOK_URL}"
            channel: '#error-alerts'
            title: '[{{ .Status }}] {{ .CommonLabels.alertname }}'
            text: '{{ .CommonAnnotations.description }}'
      - name: 'pagerduty-critical'
        pagerduty_configs:
          - service_key: "${PAGERDUTY_SERVICE_KEY}"
            severity: critical
      - name: 'self-healing-webhook'
        webhook_configs:
          - url: "${SELF_HEALING_WEBHOOK_URL}"
            send_resolved: true

  # Custom PrometheusRules for Self-Healing triggers
  additionalPrometheusRules:
    - name: self-healing-rules
      groups:
        - name: error-detection
          rules:
            - alert: HighErrorRate
              expr: rate(http_requests_total{status=~"5.."}[5m]) / rate(http_requests_total[5m]) > 0.01
              for: 2m
              labels:
                severity: warning
              annotations:
                description: "Error rate > 1% for {{ $labels.service }} — Self-Healing candidate"
            - alert: CriticalErrorRate
              expr: rate(http_requests_total{status=~"5.."}[5m]) / rate(http_requests_total[5m]) > 0.05
              for: 2m
              labels:
                severity: critical
              annotations:
                description: "Error rate > 5% for {{ $labels.service }} — Auto-Rollback triggered"
            - alert: HighLatency
              expr: histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m])) > 0.5
              for: 5m
              labels:
                severity: warning
              annotations:
                description: "P95 latency > 500ms for {{ $labels.service }}"