Merge feature/onboard-pihole (first WS-APPS onboarding)

apps/kustomization.yaml

@@ -0,0 +1,9 @@
+---
+# Onboarded services (WS-APPS). Each app is rendered from its catalog/ ServiceDefinition by
+# catalog/render.py and committed here; the `apps` Flux Kustomization (clusters/base/apps.yaml,
+# dependsOn platform-config) reconciles this directory. Image-automation CRs are omitted for now
+# (--no-image-automation) until the Flux image controllers are installed.
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - pihole.yaml

apps/pihole.yaml

@@ -0,0 +1,174 @@
+---
+# Namespace (trust zone; default-deny + policies apply)
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: pihole
+  labels:
+    homelab.keithjackson.dev/app-namespace: 'true'
+    gateway-access: shared
+  annotations:
+    homelab.keithjackson.dev/backup-policy: daily-offcluster
+---
+# Default-deny baseline (R-NET-01): deny all, allow only DNS
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: default-deny
+  namespace: pihole
+  labels:
+    homelab.keithjackson.dev/baseline: default-deny
+spec:
+  podSelector: {}
+  policyTypes:
+  - Ingress
+  - Egress
+  ingress: []
+  egress:
+  - to:
+    - namespaceSelector:
+        matchLabels:
+          kubernetes.io/metadata.name: kube-system
+    ports:
+    - protocol: UDP
+      port: 53
+    - protocol: TCP
+      port: 53
+---
+# PVC pihole-config (R-STATE)
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: pihole-config
+  namespace: pihole
+  labels:
+    app.kubernetes.io/name: pihole
+spec:
+  accessModes:
+  - ReadWriteOnce
+  storageClassName: longhorn
+  resources:
+    requests:
+      storage: 2Gi
+---
+# Deployment (R-PLAT-02)
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: pihole
+  namespace: pihole
+  labels:
+    app.kubernetes.io/name: pihole
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: pihole
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: pihole
+        homelab.keithjackson.dev/egress-class: internet
+        homelab.keithjackson.dev/auth-mode: forward-auth
+      annotations:
+        homelab.keithjackson.dev/auth-mode: forward-auth
+        homelab.keithjackson.dev/auth-groups: platform-admins
+    spec:
+      containers:
+      - name: pihole
+        image: pihole/pihole
+        ports:
+        - containerPort: 80
+        volumeMounts:
+        - name: config
+          mountPath: /data/config
+      volumes:
+      - name: config
+        persistentVolumeClaim:
+          claimName: pihole-config
+---
+# Service
+apiVersion: v1
+kind: Service
+metadata:
+  name: pihole
+  namespace: pihole
+  labels:
+    app.kubernetes.io/name: pihole
+spec:
+  selector:
+    app.kubernetes.io/name: pihole
+  ports:
+  - name: port-80
+    port: 80
+    targetPort: 80
+---
+# HTTPRoute pihole-80 (R-TLS/R-DNS)
+apiVersion: gateway.networking.k8s.io/v1
+kind: HTTPRoute
+metadata:
+  name: pihole-80
+  namespace: pihole
+  labels:
+    app.kubernetes.io/name: pihole
+  annotations:
+    homelab.keithjackson.dev/auth-mode: forward-auth
+    homelab.keithjackson.dev/auth-groups: platform-admins
+spec:
+  parentRefs:
+  - name: shared
+    namespace: gateway
+    sectionName: https
+  hostnames:
+  - pihole.home.keithjackson.dev
+  rules:
+  - matches:
+    - path:
+        type: PathPrefix
+        value: /
+    backendRefs:
+    - name: pihole
+      port: 80
+---
+# ServiceMonitor (R-OBS-01)
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: pihole
+  namespace: pihole
+  labels:
+    release: kube-prometheus-stack
+    app.kubernetes.io/name: pihole
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: pihole
+  namespaceSelector:
+    matchNames:
+    - pihole
+  endpoints:
+  - port: metrics
+    interval: 30s
+---
+# PrometheusRule SLI alerts (R-OBS-01)
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: pihole-slis
+  namespace: pihole
+  labels:
+    release: kube-prometheus-stack
+    app.kubernetes.io/name: pihole
+spec:
+  groups:
+  - name: pihole.slis
+    rules:
+    - alert: pihole-down
+      expr: up{job="pihole"} == 0
+      for: 5m
+      labels:
+        severity: critical
+        service: pihole
+      annotations:
+        summary: pihole is down
+        description: 'pihole has been unreachable for 5m (SLI: up).'

catalog/render.py

@@ -580,8 +580,14 @@ def r_virtualmachine(s: dict) -> dict:
 # =============================================================================
 # Top-level render + emit
 # =============================================================================
-def render(sd: dict) -> list:
+def render(sd: dict, image_automation: bool = True) -> list:
-    """Return an ordered list of (header_comment, resource_dict) for a ServiceDefinition."""
+    """Return an ordered list of (header_comment, resource_dict) for a ServiceDefinition.
+
+    image_automation=False omits the Flux ImageRepository/ImagePolicy CRs — used when
+    onboarding apps before the Flux image-reflector/-automation controllers are installed
+    (their CRDs would otherwise be missing and the apps Kustomization would fail). The L1
+    render goldens use the default (True), so their expected output is unchanged.
+    """
     s = apply_defaults(sd)
     if s["kind"] not in ("container", "vm"):
         raise ValueError(f"unknown kind: {s['kind']!r}")
@@ -620,8 +626,9 @@ def render(sd: dict) -> list:
     if pr:
         docs.append(("PrometheusRule SLI alerts (R-OBS-01)", pr))
 
-    for res in r_image_automation(s):
+    if image_automation:
-        docs.append((f"Flux {res['kind']} (R-UPD)", res))
+        for res in r_image_automation(s):
+            docs.append((f"Flux {res['kind']} (R-UPD)", res))
 
     return docs
 
@@ -645,8 +652,8 @@ def load_sd(path: Path) -> dict:
         return yaml.safe_load(fh)
 
 
-def render_file(path: Path) -> str:
+def render_file(path: Path, image_automation: bool = True) -> str:
-    return emit(render(load_sd(path)))
+    return emit(render(load_sd(path), image_automation=image_automation))
 
 
 # =============================================================================
@@ -745,16 +752,21 @@ def main(argv=None) -> int:
     ap.add_argument("--all", metavar="DIR", help="Render every *.yaml ServiceDefinition in DIR")
     ap.add_argument("-o", "--out-dir", help="With --all: write <name>.yaml files into this dir")
     ap.add_argument("--selftest", action="store_true", help="Run the built-in self-test")
+    ap.add_argument("--no-image-automation", action="store_true",
+                    help="Omit Flux ImageRepository/ImagePolicy CRs (for onboarding before the "
+                         "image-reflector/-automation controllers are installed)")
     args = ap.parse_args(argv)
 
     if args.selftest:
         return _selftest()
 
+    image_automation = not args.no_image_automation
+
     if args.all:
         src = Path(args.all)
         files = sorted(p for p in src.glob("*.yaml") if p.name != "render.py")
         for f in files:
-            text = render_file(f)
+            text = render_file(f, image_automation=image_automation)
             if args.out_dir:
                 outdir = Path(args.out_dir)
                 outdir.mkdir(parents=True, exist_ok=True)
@@ -766,7 +778,7 @@ def main(argv=None) -> int:
 
     if not args.input:
         ap.error("provide a ServiceDefinition file, --all DIR, or --selftest")
-    sys.stdout.write(render_file(Path(args.input)))
+    sys.stdout.write(render_file(Path(args.input), image_automation=image_automation))
     return 0