Port the observability platform to k3s and ship czy logs to it

k8s/ is now a faithful port of the mentor's Ansible Grafana stack
(Prometheus, Alertmanager, Loki, Tempo, Alloy, Grafana, node-exporter)
for the ledgerline-observability namespace on falken: same versions and
configs, one *.vione.cloud ingress per tool behind Traefik basic auth,
secrets generated by create-secrets.sh into gitignored files.

Two fixes over the Ansible role, both verified live: Tempo's
metrics-generator needs traces_storage or it runs no processors, and
Prometheus needs exemplar-storage to keep exemplars.

Ledgerline stays on czy; an Alloy agent in the Traefik override ships
its container logs to Loki. Roadmap and CLAUDE.md now point at k8s/.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

k8s/grafana/datasources.yml

@@ -0,0 +1,53 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    uid: prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    editable: true
+    jsonData:
+      exemplarTraceIdDestinations:
+        - datasourceUid: tempo
+          name: trace_id
+
+  - name: Loki
+    uid: loki
+    type: loki
+    access: proxy
+    url: http://loki:3100
+    editable: true
+    jsonData:
+      derivedFields:
+        - datasourceUid: tempo
+          matcherRegex: 'trace[_-]?id["=: ]+([a-fA-F0-9]+)'
+          name: TraceID
+          url: '$${__value.raw}'
+
+  - name: Tempo
+    uid: tempo
+    type: tempo
+    access: proxy
+    url: http://tempo:3200
+    editable: true
+    jsonData:
+      tracesToLogsV2:
+        datasourceUid: loki
+        filterByTraceID: true
+        spanStartTimeShift: -1m
+        spanEndTimeShift: 1m
+      serviceMap:
+        datasourceUid: prometheus
+      nodeGraph:
+        enabled: true
+
+  - name: Alertmanager
+    uid: alertmanager
+    type: alertmanager
+    access: proxy
+    url: http://alertmanager:9093
+    editable: true
+    jsonData:
+      implementation: prometheus

k8s/grafana/deployment.yaml

@@ -0,0 +1,60 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: grafana
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: grafana
+  template:
+    metadata:
+      labels:
+        app: grafana
+    spec:
+      containers:
+        - name: grafana
+          image: grafana/grafana:12.1.1
+          ports:
+            - containerPort: 3000
+          env:
+            - name: GF_SECURITY_ADMIN_USER
+              valueFrom:
+                secretKeyRef:
+                  name: grafana-admin
+                  key: admin-user
+            - name: GF_SECURITY_ADMIN_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: grafana-admin
+                  key: admin-password
+            - name: GF_USERS_ALLOW_SIGN_UP
+              value: "false"
+            - name: GF_FEATURE_TOGGLES_ENABLE
+              value: traceqlEditor
+            - name: GF_SERVER_ROOT_URL
+              value: https://grafana.vione.cloud
+          readinessProbe:
+            httpGet:
+              path: /api/health
+              port: 3000
+          resources:
+            requests:
+              cpu: 20m
+              memory: 128Mi
+            limits:
+              memory: 512Mi
+          volumeMounts:
+            - name: data
+              mountPath: /var/lib/grafana
+            - name: datasources
+              mountPath: /etc/grafana/provisioning/datasources
+      volumes:
+        - name: data
+          persistentVolumeClaim:
+            claimName: grafana-data
+        - name: datasources
+          configMap:
+            name: grafana-datasources

k8s/grafana/ingress.yaml

@@ -0,0 +1,24 @@
+# Grafana has its own login, so no basic-auth middleware here.
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: grafana
+  annotations:
+    cert-manager.io/cluster-issuer: letsencrypt-prod
+spec:
+  ingressClassName: traefik
+  tls:
+    - hosts:
+        - grafana.vione.cloud
+      secretName: grafana-tls
+  rules:
+    - host: grafana.vione.cloud
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: grafana
+                port:
+                  number: 3000

k8s/grafana/kustomization.yaml

@@ -0,0 +1,15 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - deployment.yaml
+  - pvc.yaml
+  - service.yaml
+  - ingress.yaml
+
+# Datasources only, as in the Ansible role. Dashboard provisioning is the
+# Phase 6 deliverable and belongs in this directory.
+configMapGenerator:
+  - name: grafana-datasources
+    files:
+      - datasources.yml

k8s/grafana/pvc.yaml

@@ -0,0 +1,11 @@
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: grafana-data
+spec:
+  storageClassName: local-path
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 2Gi

k8s/grafana/service.yaml

@@ -0,0 +1,12 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: grafana
+spec:
+  type: ClusterIP
+  selector:
+    app: grafana
+  ports:
+    - name: http
+      port: 3000
+      targetPort: 3000