src/deployment/monitoring/prometheus.yml

# Prometheus configuration for Cyber-LLM monitoring
global:
  scrape_interval: 15s
  evaluation_interval: 15s
  external_labels:
    cluster: 'cyber-llm-production'
    environment: 'production'

rule_files:
  - "/etc/prometheus/rules/*.yml"

alerting:
  alertmanagers:
    - static_configs:
        - targets:
          - alertmanager:9093

scrape_configs:
  # Cyber-LLM API metrics
  - job_name: 'cyber-llm-api'
    metrics_path: '/metrics'
    scrape_interval: 30s
    static_configs:
      - targets: ['cyber-llm-api-service:8000']
    relabel_configs:
      - source_labels: [__address__]
        target_label: __param_target
      - source_labels: [__param_target]
        target_label: instance
      - target_label: __address__
        replacement: cyber-llm-api-service:8000

  # Kubernetes cluster metrics
  - job_name: 'kubernetes-apiservers'
    kubernetes_sd_configs:
      - role: endpoints
    scheme: https
    tls_config:
      ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
    bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
    relabel_configs:
      - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
        action: keep
        regex: default;kubernetes;https

  # Kubernetes node metrics
  - job_name: 'kubernetes-nodes'
    scheme: https
    tls_config:
      ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
    bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
    kubernetes_sd_configs:
      - role: node
    relabel_configs:
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
      - target_label: __address__
        replacement: kubernetes.default.svc:443
      - source_labels: [__meta_kubernetes_node_name]
        regex: (.+)
        target_label: __metrics_path__
        replacement: /api/v1/nodes/${1}/proxy/metrics

  # Kubernetes pods
  - job_name: 'kubernetes-pods'
    kubernetes_sd_configs:
      - role: pod
    relabel_configs:
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
        action: keep
        regex: true
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
        action: replace
        target_label: __metrics_path__
        regex: (.+)
      - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
        action: replace
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
        target_label: __address__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - source_labels: [__meta_kubernetes_namespace]
        action: replace
        target_label: kubernetes_namespace
      - source_labels: [__meta_kubernetes_pod_name]
        action: replace
        target_label: kubernetes_pod_name

  # GPU metrics (if nvidia-gpu-exporter is deployed)
  - job_name: 'gpu-metrics'
    static_configs:
      - targets: ['nvidia-gpu-exporter:9835']

  # Custom business metrics
  - job_name: 'cyber-llm-business-metrics'
    metrics_path: '/business-metrics'
    scrape_interval: 60s
    static_configs:
      - targets: ['cyber-llm-api-service:8000']