# =============================================================================
# Prometheus (TASK-0135, phase-15) — Deployment + PVC + Service, ns `monitoring`.
#
# Config is generated into `prometheus-config` by kustomization.yaml FROM
# infrastructure/observability/prometheus/ (single source of truth):
#   /etc/prometheus/prometheus.yml                 (scrape + rule_files + alerting)
#   /etc/prometheus/rules/recording-rules.yaml
#   /etc/prometheus/rules/alerts.yaml
# Retention 7 d (the 14-day cert alert needs >14 d of history for its
# avg_over_time-free expr, but 7 d is the staging default — bump if the
# dashboards' 30 d views matter).
# Image pinned: prom/prometheus:v2.51.0 (the 2.51 LTS line — classic text
# format + the rule files above are 2.x syntax).
# =============================================================================
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: prometheus-data
  namespace: monitoring
  labels:
    app.kubernetes.io/name: prometheus
    app.kubernetes.io/part-of: ai-software-factory
spec:
  accessModes: ["ReadWriteOnce"]
  resources:
    requests:
      storage: 10Gi
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus
  namespace: monitoring
  labels:
    app.kubernetes.io/name: prometheus
    app.kubernetes.io/part-of: ai-software-factory
spec:
  replicas: 1
  selector:
    matchLabels:
      app.kubernetes.io/name: prometheus
  strategy:
    type: Recreate
  template:
    metadata:
      labels:
        app.kubernetes.io/name: prometheus
    spec:
      securityContext:
        runAsNonRoot: true
        runAsUser: 65534  # the `prom` user in the official image
        runAsGroup: 65534
        fsGroup: 65534
      containers:
        - name: prometheus
          image: prom/prometheus:v2.51.0
          imagePullPolicy: IfNotPresent
          args:
            - --config.file=/etc/prometheus/prometheus.yml
            - --storage.tsdb.path=/prometheus
            - --storage.tsdb.retention.time=7d
            - --web.enable-lifecycle
          ports:
            - containerPort: 9090
              name: http
          volumeMounts:
            - name: config
              mountPath: /etc/prometheus
              readOnly: true
            - name: data
              mountPath: /prometheus
          readinessProbe:
            httpGet:
              path: /-/ready
              port: 9090
            initialDelaySeconds: 10
            periodSeconds: 10
          livenessProbe:
            httpGet:
              path: /-/healthy
              port: 9090
            initialDelaySeconds: 30
            periodSeconds: 15
          resources:
            requests:
              cpu: 250m
              memory: 512Mi
            limits:
              cpu: "1"
              memory: 2Gi
      volumes:
        - name: config
          configMap:
            name: prometheus-config  # name rewritten to the hashed name by kustomize
        - name: data
          persistentVolumeClaim:
            claimName: prometheus-data
---
apiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: monitoring
  labels:
    app.kubernetes.io/name: prometheus
    app.kubernetes.io/part-of: ai-software-factory
spec:
  selector:
    app.kubernetes.io/name: prometheus
  ports:
    - name: http
      port: 9090
      targetPort: 9090