infra: export appset and mirror alert polish

StatefulSet/authentik-postgres has been eternally OutOfSync since ~Sprint 65
even though 'kubectl diff --server-side --field-manager=argocd-controller'
shows zero real change. The STS was created via ServerSideApply, so the live
object carries apiVersion/kind inside volumeClaimTemplates[]; git omitting
them makes ArgoCD's normalized diff disagree forever. Declare them in git.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

README.md

@@ -2,6 +2,22 @@
 
 Infrastructure manifests for ArgoCD. An `ApplicationSet` in `argocd` namespace watches the `apps/*` directories in this repo and creates one `Application` per subdir (prefixed `infra-<name>`).
 
+## Root GitOps ApplicationSet
+
+`argocd/applicationset-bluejay-infra.yaml` is the root of this GitOps tree, but
+it is **NOT self-managed** by ArgoCD. Apply it manually when the root generator
+or sync policy changes:
+
+```bash
+kubectl -n argocd apply -f argocd/applicationset-bluejay-infra.yaml
+```
+
+Keep the per-StatefulSet `ignoreDifferences` entries in that file synced with
+the live ApplicationSet. They intentionally cover `zabbix-postgres`,
+`guac-mysql`, `matrix-postgres`, and `authentik-postgres` so ArgoCD does not
+loop forever on server-side-apply `volumeClaimTemplates` status drift. Every new
+StatefulSet with `volumeClaimTemplates` needs its own entry appended.
+
 ## Adding a new service to the cluster
 
 Follow these steps in order. **Step 1 must run before step 3** — if you skip it, cert-manager HTTP-01 will silently fail for ~2h per cert (exponential backoff) until someone diagnoses the DNS.

apps/authentik/authentik.yaml

@@ -1,448 +1,453 @@
-# Authentik OIDC backend
+# Authentik OIDC backend
-# ArgoCD-managed. BlueJay Lab.
+# ArgoCD-managed. BlueJay Lab.
-#
+#
-# Stack:
+# Stack:
-#   - PostgreSQL 16 StatefulSet (single replica, Longhorn RWO 5Gi)
+#   - PostgreSQL 16 StatefulSet (single replica, Longhorn RWO 5Gi)
-#   - Redis 7 Deployment (no persistence — session/cache only)
+#   - Redis 7 Deployment (no persistence — session/cache only)
-#   - Authentik server + worker Deployments (image ghcr.io/goauthentik/server:2024.12.3)
+#   - Authentik server + worker Deployments (image ghcr.io/goauthentik/server:2024.12.3)
-#   - Media PVC shared between server + worker (Longhorn RWO 2Gi)
+#   - Media PVC shared between server + worker (Longhorn RWO 2Gi)
-#   - Certificate via step-ca-acme ClusterIssuer
+#   - Certificate via step-ca-acme ClusterIssuer
-#   - Traefik IngressRoute at id.iamworkin.lan
+#   - Traefik IngressRoute at id.iamworkin.lan
-#
+#
-# Secrets come from 1Password item "authentik-credentials" (IAmWorkin vault, id y6i74ch22q5wvm7znquq4nhhcu)
+# Secrets come from 1Password item "authentik-credentials" (IAmWorkin vault, id y6i74ch22q5wvm7znquq4nhhcu)
-# via the OnePasswordItem CRD, materialized into k8s Secret authentik/authentik-credentials.
+# via the OnePasswordItem CRD, materialized into k8s Secret authentik/authentik-credentials.
-#
+#
-# Why the discovery URL is /application/o/pimanager/ : Authentik issues per-application OIDC providers.
+# Why the discovery URL is /application/o/pimanager/ : Authentik issues per-application OIDC providers.
-# The pimanager OIDC application/provider is created after the cluster pods are healthy (manual or
+# The pimanager OIDC application/provider is created after the cluster pods are healthy (manual or
-# via API once the bootstrap token is available — see Notes substrate).
+# via API once the bootstrap token is available — see Notes substrate).
-
+
----
+---
-apiVersion: v1
+apiVersion: v1
-kind: Namespace
+kind: Namespace
-metadata:
+metadata:
-  name: authentik
+  name: authentik
-  labels:
+  labels:
-    app.kubernetes.io/part-of: bluejay-infra
+    app.kubernetes.io/part-of: bluejay-infra
-
+
----
+---
-# 1Password operator pulls the authentik-credentials item into a k8s Secret of the same name.
+# 1Password operator pulls the authentik-credentials item into a k8s Secret of the same name.
-# Field labels in 1P become Secret keys: AUTHENTIK_SECRET_KEY, POSTGRES_PASSWORD, REDIS_PASSWORD,
+# Field labels in 1P become Secret keys: AUTHENTIK_SECRET_KEY, POSTGRES_PASSWORD, REDIS_PASSWORD,
-# BOOTSTRAP_ADMIN_PASSWORD, BOOTSTRAP_ADMIN_TOKEN, BOOTSTRAP_ADMIN_EMAIL.
+# BOOTSTRAP_ADMIN_PASSWORD, BOOTSTRAP_ADMIN_TOKEN, BOOTSTRAP_ADMIN_EMAIL.
-apiVersion: onepassword.com/v1
+apiVersion: onepassword.com/v1
-kind: OnePasswordItem
+kind: OnePasswordItem
-metadata:
+metadata:
-  name: authentik-credentials
+  name: authentik-credentials
-  namespace: authentik
+  namespace: authentik
-spec:
+spec:
-  itemPath: "vaults/IAmWorkin/items/authentik-credentials"
+  itemPath: "vaults/IAmWorkin/items/authentik-credentials"
-
+
----
+---
-# Shared media volume for server + worker pods.
+# Shared media volume for server + worker pods.
-apiVersion: v1
+apiVersion: v1
-kind: PersistentVolumeClaim
+kind: PersistentVolumeClaim
-metadata:
+metadata:
-  name: authentik-media
+  name: authentik-media
-  namespace: authentik
+  namespace: authentik
-spec:
+spec:
-  storageClassName: longhorn
+  storageClassName: longhorn
-  accessModes: [ReadWriteOnce]
+  accessModes: [ReadWriteOnce]
-  resources:
+  resources:
-    requests:
+    requests:
-      storage: 2Gi
+      storage: 2Gi
-
+
----
+---
-# PostgreSQL 16 StatefulSet — Authentik's primary store.
+# PostgreSQL 16 StatefulSet — Authentik's primary store.
-apiVersion: apps/v1
+apiVersion: apps/v1
-kind: StatefulSet
+kind: StatefulSet
-metadata:
+metadata:
-  name: authentik-postgres
+  name: authentik-postgres
-  namespace: authentik
+  namespace: authentik
-  labels:
+  labels:
-    app: authentik-postgres
+    app: authentik-postgres
-    argocd.argoproj.io/instance: infra-authentik
+    argocd.argoproj.io/instance: infra-authentik
-spec:
+spec:
-  persistentVolumeClaimRetentionPolicy:
+  persistentVolumeClaimRetentionPolicy:
-    whenDeleted: Retain
+    whenDeleted: Retain
-    whenScaled: Retain
+    whenScaled: Retain
-  podManagementPolicy: OrderedReady
+  podManagementPolicy: OrderedReady
-  serviceName: authentik-postgres
+  serviceName: authentik-postgres
-  replicas: 1
+  replicas: 1
-  revisionHistoryLimit: 10
+  revisionHistoryLimit: 10
-  selector:
+  selector:
-    matchLabels:
+    matchLabels:
-      app: authentik-postgres
+      app: authentik-postgres
-  template:
+  template:
-    metadata:
+    metadata:
-      labels:
+      labels:
-        app: authentik-postgres
+        app: authentik-postgres
-    spec:
+    spec:
-      containers:
+      containers:
-        - name: postgres
+        - name: postgres
-          image: postgres:16-alpine
+          image: postgres:16-alpine
-          ports:
+          ports:
-            - containerPort: 5432
+            - containerPort: 5432
-              name: postgres
+              name: postgres
-          env:
+          env:
-            - name: POSTGRES_USER
+            - name: POSTGRES_USER
-              value: authentik
+              value: authentik
-            - name: POSTGRES_PASSWORD
+            - name: POSTGRES_PASSWORD
-              valueFrom:
+              valueFrom:
-                secretKeyRef:
+                secretKeyRef:
-                  name: authentik-credentials
+                  name: authentik-credentials
-                  key: POSTGRES_PASSWORD
+                  key: POSTGRES_PASSWORD
-            - name: POSTGRES_DB
+            - name: POSTGRES_DB
-              value: authentik
+              value: authentik
-            - name: POSTGRES_INITDB_ARGS
+            - name: POSTGRES_INITDB_ARGS
-              value: "--encoding=UTF-8 --lc-collate=C --lc-ctype=C"
+              value: "--encoding=UTF-8 --lc-collate=C --lc-ctype=C"
-            - name: PGDATA
+            - name: PGDATA
-              value: /var/lib/postgresql/data/pgdata
+              value: /var/lib/postgresql/data/pgdata
-          readinessProbe:
+          readinessProbe:
-            exec:
+            exec:
-              command: ["pg_isready", "-U", "authentik"]
+              command: ["pg_isready", "-U", "authentik"]
-            initialDelaySeconds: 5
+            initialDelaySeconds: 5
-            periodSeconds: 5
+            periodSeconds: 5
-          livenessProbe:
+          livenessProbe:
-            exec:
+            exec:
-              command: ["pg_isready", "-U", "authentik"]
+              command: ["pg_isready", "-U", "authentik"]
-            initialDelaySeconds: 30
+            initialDelaySeconds: 30
-            periodSeconds: 30
+            periodSeconds: 30
-          resources:
+          resources:
-            requests: { cpu: 100m, memory: 256Mi }
+            requests: { cpu: 100m, memory: 256Mi }
-            limits: { cpu: 1000m, memory: 1Gi }
+            limits: { cpu: 1000m, memory: 1Gi }
-          volumeMounts:
+          volumeMounts:
-            - name: pgdata
+            - name: pgdata
-              mountPath: /var/lib/postgresql/data
+              mountPath: /var/lib/postgresql/data
-  volumeClaimTemplates:
+  volumeClaimTemplates:
-    - metadata:
+    # apiVersion/kind included deliberately: this STS was created via ArgoCD ServerSideApply,
-        name: pgdata
+    # so the live object carries PVC TypeMeta inside volumeClaimTemplates; omitting it here
-      spec:
+    # leaves the app eternally OutOfSync even though kubectl SSA dry-run shows no change.
-        storageClassName: longhorn
+    - apiVersion: v1
-        accessModes: [ReadWriteOnce]
+      kind: PersistentVolumeClaim
-        volumeMode: Filesystem
+      metadata:
-        resources:
+        name: pgdata
-          requests:
+      spec:
-            storage: 5Gi
+        storageClassName: longhorn
-
+        accessModes: [ReadWriteOnce]
----
+        volumeMode: Filesystem
-apiVersion: v1
+        resources:
-kind: Service
+          requests:
-metadata:
+            storage: 5Gi
-  name: authentik-postgres
+
-  namespace: authentik
+---
-spec:
+apiVersion: v1
-  clusterIP: None
+kind: Service
-  selector:
+metadata:
-    app: authentik-postgres
+  name: authentik-postgres
-  ports:
+  namespace: authentik
-    - name: postgres
+spec:
-      port: 5432
+  clusterIP: None
-      targetPort: 5432
+  selector:
-
+    app: authentik-postgres
----
+  ports:
-# Redis 7 — session storage + Celery broker. No persistence needed (cache).
+    - name: postgres
-apiVersion: apps/v1
+      port: 5432
-kind: Deployment
+      targetPort: 5432
-metadata:
+
-  name: authentik-redis
+---
-  namespace: authentik
+# Redis 7 — session storage + Celery broker. No persistence needed (cache).
-  labels:
+apiVersion: apps/v1
-    app: authentik-redis
+kind: Deployment
-    argocd.argoproj.io/instance: infra-authentik
+metadata:
-spec:
+  name: authentik-redis
-  replicas: 1
+  namespace: authentik
-  strategy:
+  labels:
-    type: Recreate
+    app: authentik-redis
-  selector:
+    argocd.argoproj.io/instance: infra-authentik
-    matchLabels:
+spec:
-      app: authentik-redis
+  replicas: 1
-  template:
+  strategy:
-    metadata:
+    type: Recreate
-      labels:
+  selector:
-        app: authentik-redis
+    matchLabels:
-    spec:
+      app: authentik-redis
-      containers:
+  template:
-        - name: redis
+    metadata:
-          image: redis:7-alpine
+      labels:
-          args:
+        app: authentik-redis
-            - "--save"
+    spec:
-            - ""
+      containers:
-            - "--appendonly"
+        - name: redis
-            - "no"
+          image: redis:7-alpine
-            - "--requirepass"
+          args:
-            - "$(REDIS_PASSWORD)"
+            - "--save"
-          env:
+            - ""
-            - name: REDIS_PASSWORD
+            - "--appendonly"
-              valueFrom:
+            - "no"
-                secretKeyRef:
+            - "--requirepass"
-                  name: authentik-credentials
+            - "$(REDIS_PASSWORD)"
-                  key: REDIS_PASSWORD
+          env:
-          ports:
+            - name: REDIS_PASSWORD
-            - containerPort: 6379
+              valueFrom:
-              name: redis
+                secretKeyRef:
-          readinessProbe:
+                  name: authentik-credentials
-            tcpSocket: { port: 6379 }
+                  key: REDIS_PASSWORD
-            initialDelaySeconds: 5
+          ports:
-            periodSeconds: 5
+            - containerPort: 6379
-          livenessProbe:
+              name: redis
-            tcpSocket: { port: 6379 }
+          readinessProbe:
-            initialDelaySeconds: 30
+            tcpSocket: { port: 6379 }
-            periodSeconds: 30
+            initialDelaySeconds: 5
-          resources:
+            periodSeconds: 5
-            requests: { cpu: 50m, memory: 64Mi }
+          livenessProbe:
-            limits: { cpu: 500m, memory: 256Mi }
+            tcpSocket: { port: 6379 }
-
+            initialDelaySeconds: 30
----
+            periodSeconds: 30
-apiVersion: v1
+          resources:
-kind: Service
+            requests: { cpu: 50m, memory: 64Mi }
-metadata:
+            limits: { cpu: 500m, memory: 256Mi }
-  name: authentik-redis
+
-  namespace: authentik
+---
-spec:
+apiVersion: v1
-  selector:
+kind: Service
-    app: authentik-redis
+metadata:
-  ports:
+  name: authentik-redis
-    - name: redis
+  namespace: authentik
-      port: 6379
+spec:
-      targetPort: 6379
+  selector:
-
+    app: authentik-redis
----
+  ports:
-# Authentik server Deployment — HTTP frontend on :9000.
+    - name: redis
-apiVersion: apps/v1
+      port: 6379
-kind: Deployment
+      targetPort: 6379
-metadata:
+
-  name: authentik-server
+---
-  namespace: authentik
+# Authentik server Deployment — HTTP frontend on :9000.
-  labels:
+apiVersion: apps/v1
-    app: authentik-server
+kind: Deployment
-    argocd.argoproj.io/instance: infra-authentik
+metadata:
-spec:
+  name: authentik-server
-  replicas: 1
+  namespace: authentik
-  strategy:
+  labels:
-    type: Recreate  # shares /media RWO PVC with worker
+    app: authentik-server
-  selector:
+    argocd.argoproj.io/instance: infra-authentik
-    matchLabels:
+spec:
-      app: authentik-server
+  replicas: 1
-  template:
+  strategy:
-    metadata:
+    type: Recreate  # shares /media RWO PVC with worker
-      labels:
+  selector:
-        app: authentik-server
+    matchLabels:
-    spec:
+      app: authentik-server
-      securityContext:
+  template:
-        # Authentik image runs as uid 1000 "authentik" but the Longhorn PVC mounts
+    metadata:
-        # root:root by default. fsGroup recursively chgrp + chmod g+rwx so the
+      labels:
-        # non-root container can mkdir /media/public during the tenant_files migration.
+        app: authentik-server
-        fsGroup: 1000
+    spec:
-      containers:
+      securityContext:
-        - name: server
+        # Authentik image runs as uid 1000 "authentik" but the Longhorn PVC mounts
-          image: ghcr.io/goauthentik/server:2024.12.3
+        # root:root by default. fsGroup recursively chgrp + chmod g+rwx so the
-          args: ["server"]
+        # non-root container can mkdir /media/public during the tenant_files migration.
-          ports:
+        fsGroup: 1000
-            - containerPort: 9000
+      containers:
-              name: http
+        - name: server
-            - containerPort: 9443
+          image: ghcr.io/goauthentik/server:2024.12.3
-              name: https
+          args: ["server"]
-          env:
+          ports:
-            - name: AUTHENTIK_SECRET_KEY
+            - containerPort: 9000
-              valueFrom:
+              name: http
-                secretKeyRef:
+            - containerPort: 9443
-                  name: authentik-credentials
+              name: https
-                  key: AUTHENTIK_SECRET_KEY
+          env:
-            - name: AUTHENTIK_REDIS__HOST
+            - name: AUTHENTIK_SECRET_KEY
-              value: authentik-redis
+              valueFrom:
-            - name: AUTHENTIK_REDIS__PASSWORD
+                secretKeyRef:
-              valueFrom:
+                  name: authentik-credentials
-                secretKeyRef:
+                  key: AUTHENTIK_SECRET_KEY
-                  name: authentik-credentials
+            - name: AUTHENTIK_REDIS__HOST
-                  key: REDIS_PASSWORD
+              value: authentik-redis
-            - name: AUTHENTIK_POSTGRESQL__HOST
+            - name: AUTHENTIK_REDIS__PASSWORD
-              value: authentik-postgres
+              valueFrom:
-            - name: AUTHENTIK_POSTGRESQL__NAME
+                secretKeyRef:
-              value: authentik
+                  name: authentik-credentials
-            - name: AUTHENTIK_POSTGRESQL__USER
+                  key: REDIS_PASSWORD
-              value: authentik
+            - name: AUTHENTIK_POSTGRESQL__HOST
-            - name: AUTHENTIK_POSTGRESQL__PASSWORD
+              value: authentik-postgres
-              valueFrom:
+            - name: AUTHENTIK_POSTGRESQL__NAME
-                secretKeyRef:
+              value: authentik
-                  name: authentik-credentials
+            - name: AUTHENTIK_POSTGRESQL__USER
-                  key: POSTGRES_PASSWORD
+              value: authentik
-            - name: AUTHENTIK_BOOTSTRAP_PASSWORD
+            - name: AUTHENTIK_POSTGRESQL__PASSWORD
-              valueFrom:
+              valueFrom:
-                secretKeyRef:
+                secretKeyRef:
-                  name: authentik-credentials
+                  name: authentik-credentials
-                  key: BOOTSTRAP_ADMIN_PASSWORD
+                  key: POSTGRES_PASSWORD
-            - name: AUTHENTIK_BOOTSTRAP_TOKEN
+            - name: AUTHENTIK_BOOTSTRAP_PASSWORD
-              valueFrom:
+              valueFrom:
-                secretKeyRef:
+                secretKeyRef:
-                  name: authentik-credentials
+                  name: authentik-credentials
-                  key: BOOTSTRAP_ADMIN_TOKEN
+                  key: BOOTSTRAP_ADMIN_PASSWORD
-            - name: AUTHENTIK_BOOTSTRAP_EMAIL
+            - name: AUTHENTIK_BOOTSTRAP_TOKEN
-              valueFrom:
+              valueFrom:
-                secretKeyRef:
+                secretKeyRef:
-                  name: authentik-credentials
+                  name: authentik-credentials
-                  key: BOOTSTRAP_ADMIN_EMAIL
+                  key: BOOTSTRAP_ADMIN_TOKEN
-            - name: AUTHENTIK_DISABLE_UPDATE_CHECK
+            - name: AUTHENTIK_BOOTSTRAP_EMAIL
-              value: "true"
+              valueFrom:
-            - name: AUTHENTIK_ERROR_REPORTING__ENABLED
+                secretKeyRef:
-              value: "false"
+                  name: authentik-credentials
-            - name: AUTHENTIK_LOG_LEVEL
+                  key: BOOTSTRAP_ADMIN_EMAIL
-              value: info
+            - name: AUTHENTIK_DISABLE_UPDATE_CHECK
-          # First-boot Authentik can take 3+ min on the migration phase
+              value: "true"
-          # (waiting on DB lock while worker also runs migrations). Initial
+            - name: AUTHENTIK_ERROR_REPORTING__ENABLED
-          # delays are generous so kubelet doesn't kill the pod mid-migration;
+              value: "false"
-          # periodSeconds keeps post-startup probing responsive.
+            - name: AUTHENTIK_LOG_LEVEL
-          readinessProbe:
+              value: info
-            httpGet:
+          # First-boot Authentik can take 3+ min on the migration phase
-              path: /-/health/ready/
+          # (waiting on DB lock while worker also runs migrations). Initial
-              port: 9000
+          # delays are generous so kubelet doesn't kill the pod mid-migration;
-            initialDelaySeconds: 60
+          # periodSeconds keeps post-startup probing responsive.
-            periodSeconds: 10
+          readinessProbe:
-            timeoutSeconds: 5
+            httpGet:
-            failureThreshold: 12
+              path: /-/health/ready/
-          livenessProbe:
+              port: 9000
-            httpGet:
+            initialDelaySeconds: 60
-              path: /-/health/live/
+            periodSeconds: 10
-              port: 9000
+            timeoutSeconds: 5
-            initialDelaySeconds: 300
+            failureThreshold: 12
-            periodSeconds: 30
+          livenessProbe:
-            timeoutSeconds: 10
+            httpGet:
-            failureThreshold: 3
+              path: /-/health/live/
-          startupProbe:
+              port: 9000
-            httpGet:
+            initialDelaySeconds: 300
-              path: /-/health/live/
+            periodSeconds: 30
-              port: 9000
+            timeoutSeconds: 10
-            initialDelaySeconds: 30
+            failureThreshold: 3
-            periodSeconds: 15
+          startupProbe:
-            timeoutSeconds: 10
+            httpGet:
-            failureThreshold: 40  # 30s + 40*15s = 10.5 min budget
+              path: /-/health/live/
-          resources:
+              port: 9000
-            requests: { cpu: 150m, memory: 512Mi }
+            initialDelaySeconds: 30
-            limits: { cpu: 1500m, memory: 1Gi }
+            periodSeconds: 15
-          volumeMounts:
+            timeoutSeconds: 10
-            - name: media
+            failureThreshold: 40  # 30s + 40*15s = 10.5 min budget
-              mountPath: /media
+          resources:
-      volumes:
+            requests: { cpu: 150m, memory: 512Mi }
-        - name: media
+            limits: { cpu: 1500m, memory: 1Gi }
-          persistentVolumeClaim:
+          volumeMounts:
-            claimName: authentik-media
+            - name: media
-
+              mountPath: /media
----
+      volumes:
-# Authentik worker Deployment — runs Celery background tasks.
+        - name: media
-apiVersion: apps/v1
+          persistentVolumeClaim:
-kind: Deployment
+            claimName: authentik-media
-metadata:
+
-  name: authentik-worker
+---
-  namespace: authentik
+# Authentik worker Deployment — runs Celery background tasks.
-  labels:
+apiVersion: apps/v1
-    app: authentik-worker
+kind: Deployment
-    argocd.argoproj.io/instance: infra-authentik
+metadata:
-spec:
+  name: authentik-worker
-  replicas: 1
+  namespace: authentik
-  strategy:
+  labels:
-    type: Recreate  # shares /media RWO PVC with server
+    app: authentik-worker
-  selector:
+    argocd.argoproj.io/instance: infra-authentik
-    matchLabels:
+spec:
-      app: authentik-worker
+  replicas: 1
-  template:
+  strategy:
-    metadata:
+    type: Recreate  # shares /media RWO PVC with server
-      labels:
+  selector:
-        app: authentik-worker
+    matchLabels:
-    spec:
+      app: authentik-worker
-      securityContext:
+  template:
-        # Same as server pod — non-root uid 1000 needs PVC group write.
+    metadata:
-        fsGroup: 1000
+      labels:
-      containers:
+        app: authentik-worker
-        - name: worker
+    spec:
-          image: ghcr.io/goauthentik/server:2024.12.3
+      securityContext:
-          args: ["worker"]
+        # Same as server pod — non-root uid 1000 needs PVC group write.
-          env:
+        fsGroup: 1000
-            - name: AUTHENTIK_SECRET_KEY
+      containers:
-              valueFrom:
+        - name: worker
-                secretKeyRef:
+          image: ghcr.io/goauthentik/server:2024.12.3
-                  name: authentik-credentials
+          args: ["worker"]
-                  key: AUTHENTIK_SECRET_KEY
+          env:
-            - name: AUTHENTIK_REDIS__HOST
+            - name: AUTHENTIK_SECRET_KEY
-              value: authentik-redis
+              valueFrom:
-            - name: AUTHENTIK_REDIS__PASSWORD
+                secretKeyRef:
-              valueFrom:
+                  name: authentik-credentials
-                secretKeyRef:
+                  key: AUTHENTIK_SECRET_KEY
-                  name: authentik-credentials
+            - name: AUTHENTIK_REDIS__HOST
-                  key: REDIS_PASSWORD
+              value: authentik-redis
-            - name: AUTHENTIK_POSTGRESQL__HOST
+            - name: AUTHENTIK_REDIS__PASSWORD
-              value: authentik-postgres
+              valueFrom:
-            - name: AUTHENTIK_POSTGRESQL__NAME
+                secretKeyRef:
-              value: authentik
+                  name: authentik-credentials
-            - name: AUTHENTIK_POSTGRESQL__USER
+                  key: REDIS_PASSWORD
-              value: authentik
+            - name: AUTHENTIK_POSTGRESQL__HOST
-            - name: AUTHENTIK_POSTGRESQL__PASSWORD
+              value: authentik-postgres
-              valueFrom:
+            - name: AUTHENTIK_POSTGRESQL__NAME
-                secretKeyRef:
+              value: authentik
-                  name: authentik-credentials
+            - name: AUTHENTIK_POSTGRESQL__USER
-                  key: POSTGRES_PASSWORD
+              value: authentik
-            - name: AUTHENTIK_DISABLE_UPDATE_CHECK
+            - name: AUTHENTIK_POSTGRESQL__PASSWORD
-              value: "true"
+              valueFrom:
-            - name: AUTHENTIK_ERROR_REPORTING__ENABLED
+                secretKeyRef:
-              value: "false"
+                  name: authentik-credentials
-            - name: AUTHENTIK_LOG_LEVEL
+                  key: POSTGRES_PASSWORD
-              value: info
+            - name: AUTHENTIK_DISABLE_UPDATE_CHECK
-          resources:
+              value: "true"
-            requests: { cpu: 100m, memory: 256Mi }
+            - name: AUTHENTIK_ERROR_REPORTING__ENABLED
-            limits: { cpu: 1000m, memory: 768Mi }
+              value: "false"
-          volumeMounts:
+            - name: AUTHENTIK_LOG_LEVEL
-            - name: media
+              value: info
-              mountPath: /media
+          resources:
-      volumes:
+            requests: { cpu: 100m, memory: 256Mi }
-        - name: media
+            limits: { cpu: 1000m, memory: 768Mi }
-          persistentVolumeClaim:
+          volumeMounts:
-            claimName: authentik-media
+            - name: media
-
+              mountPath: /media
----
+      volumes:
-apiVersion: v1
+        - name: media
-kind: Service
+          persistentVolumeClaim:
-metadata:
+            claimName: authentik-media
-  name: authentik-server
+
-  namespace: authentik
+---
-spec:
+apiVersion: v1
-  selector:
+kind: Service
-    app: authentik-server
+metadata:
-  ports:
+  name: authentik-server
-    - name: http
+  namespace: authentik
-      port: 9000
+spec:
-      targetPort: 9000
+  selector:
-    - name: https
+    app: authentik-server
-      port: 9443
+  ports:
-      targetPort: 9443
+    - name: http
-
+      port: 9000
----
+      targetPort: 9000
-# step-ca leaf certificate for id.iamworkin.lan.
+    - name: https
-# step-ca container resolver uses pfSense Unbound, so the public A record for id.iamworkin.lan
+      port: 9443
-# MUST exist before this Certificate is applied (cert-manager HTTP-01 will silently 2h-backoff
+      targetPort: 9443
-# otherwise). Added 2026-05-25 via scripts/pfsense-add-id-host.py.
+
-apiVersion: cert-manager.io/v1
+---
-kind: Certificate
+# step-ca leaf certificate for id.iamworkin.lan.
-metadata:
+# step-ca container resolver uses pfSense Unbound, so the public A record for id.iamworkin.lan
-  name: authentik-tls
+# MUST exist before this Certificate is applied (cert-manager HTTP-01 will silently 2h-backoff
-  namespace: authentik
+# otherwise). Added 2026-05-25 via scripts/pfsense-add-id-host.py.
-spec:
+apiVersion: cert-manager.io/v1
-  secretName: authentik-tls
+kind: Certificate
-  dnsNames:
+metadata:
-    - id.iamworkin.lan
+  name: authentik-tls
-  issuerRef:
+  namespace: authentik
-    name: step-ca-acme
+spec:
-    kind: ClusterIssuer
+  secretName: authentik-tls
-
+  dnsNames:
----
+    - id.iamworkin.lan
-apiVersion: traefik.io/v1alpha1
+  issuerRef:
-kind: IngressRoute
+    name: step-ca-acme
-metadata:
+    kind: ClusterIssuer
-  name: authentik
+
-  namespace: authentik
+---
-spec:
+apiVersion: traefik.io/v1alpha1
-  entryPoints: [websecure]
+kind: IngressRoute
-  routes:
+metadata:
-    - match: Host(`id.iamworkin.lan`)
+  name: authentik
-      kind: Rule
+  namespace: authentik
-      services:
+spec:
-        - name: authentik-server
+  entryPoints: [websecure]
-          port: 9000
+  routes:
-  tls:
+    - match: Host(`id.iamworkin.lan`)
-    secretName: authentik-tls
+      kind: Rule
+      services:
+        - name: authentik-server
+          port: 9000
+  tls:
+    secretName: authentik-tls

apps/fc-messageboard/fc-messageboard.yaml

@@ -42,7 +42,7 @@ spec:
         app: messageboard-web
       annotations:
         fc.flowercore.io/healthz-anon: "true"
-        fc.flowercore.io/probe-path: "/healthz"
+        fc.flowercore.io/probe-path: "/health"
         prometheus.io/scrape: "true"
         prometheus.io/port: "8080"
         prometheus.io/path: "/metrics/prometheus"

apps/fc-ttsreader/fc-ttsreader.yaml

@@ -525,7 +525,7 @@ spec:
         app.kubernetes.io/part-of: flowercore
       annotations:
         fc.flowercore.io/healthz-anon: "true"
-        fc.flowercore.io/probe-path: "/healthz"
+        fc.flowercore.io/probe-path: "/health"
         prometheus.io/scrape: "true"
         prometheus.io/port: "5217"
         prometheus.io/path: "/metrics"

apps/fc-updater/fc-updater.yaml

@@ -54,7 +54,7 @@ spec:
     metadata:
       annotations:
         fc.flowercore.io/healthz-anon: "true"
-        fc.flowercore.io/probe-path: "/healthz"
+        fc.flowercore.io/probe-path: "/"
       labels:
         app: updatecenter-web
     spec:

apps/github-runner/README.md

@@ -24,6 +24,12 @@ original Longhorn ReadWriteOnce NuGet PVC. Every other repo-scoped runner uses
 two replicas with per-pod `emptyDir` caches. That is the safe backlog-drain
 strategy: no two pods share one RWO PVC.
 
+Ephemeral runner pods are expected to register, run one job, deregister, and
+exit so the Deployment starts a fresh pod for the next registration token. A
+small amount of exit-1/restart churn from token-expiry or no-work windows is
+accepted operational noise as long as jobs are not stuck queued and the
+repo-scoped runner-offline alerts stay quiet.
+
 Sprint 32 final long-tail wave adds 16 two-replica Deployments:
 `FlowerCore.Knowledge`, `FlowerCore.LlmBridge`, `FlowerCore.Media`,
 `FlowerCore.Presentations`, `FlowerCore.RemoteDesktop`, `FlowerCore.DNS`,

apps/monitoring/noc-monitoring.yaml

@@ -843,7 +843,9 @@ data:
         rules:
           - alert: PiManagerDown
             expr: up{job="pimanager-app"} == 0
-            for: 3m
+            # Sprint 67: delayed behind NodeDown's critical page so a powered-off
+            # Pi does not create the first duplicate page for the same host.
+            for: 8m
             labels:
               severity: warning
             annotations:
@@ -1242,6 +1244,58 @@ data:
               summary: "Marquee animation duration drifting > 10% on {{ $labels.renderer }} ({{ $labels.phase }})"
               description: "Median observed cycle duration deviates from target DurationMs by >10%. Could indicate browser tab throttling, GPU pressure, or phase-advancement bug."
 
+      # ============================================================
+      # Update Center public-edge probes
+      # Live-mirrored from FlowerCore.Notes/scripts/monitoring/alerts.yml.
+      # This K8s ConfigMap is the future migration target; live Prometheus
+      # still reads the canonical Notes file from noc1 Podman.
+      # ============================================================
+      - name: update_center
+        rules:
+          # Critical only when the edge is genuinely unreachable. A Cloudflare
+          # HTTP 429 means the prober hit a rate-limit, not that real clients
+          # are down, so the warning rule below owns that signal.
+          - alert: UpdateCenterPublicEdgeDown
+            expr: |
+              (probe_success{job="probe-update-center-public-edge"} == 0)
+              unless on(instance)
+              (probe_http_status_code{job="probe-update-center-public-edge"} == 429)
+            for: 10m
+            labels:
+              severity: critical
+              service: update-center
+              alert_channel: irc
+            annotations:
+              summary: "Update Center public edge probe failed for {{ $labels.instance }}"
+              description: >-
+                The external probe for {{ $labels.instance }} failed for 10 minutes with a
+                non-2xx status that is not a rate-limit. Public Update Center clients may be
+                unable to fetch manifest schema metadata through Cloudflare.
+              runbook: >-
+                1. curl -sk https://{{ $labels.instance }}/api/v1/manifests/_schema
+                2. Verify Cloudflare DNS record is proxied and targets the current public edge IP
+                3. kubectl -n fc-updater get ingressroute updatecenter-web-public secret cf-origin-flowercore-io
+                4. Check Traefik logs for Method() or TLS secret errors
+
+          - alert: UpdateCenterPublicEdgeRateLimited
+            expr: probe_http_status_code{job="probe-update-center-public-edge"} == 429
+            for: 15m
+            labels:
+              severity: warning
+              service: update-center
+              alert_channel: irc
+            annotations:
+              summary: "Cloudflare is rate-limiting (HTTP 429) the public-edge probe for {{ $labels.instance }}"
+              description: >-
+                The blackbox prober receives HTTP 429 from Cloudflare for {{ $labels.instance }}
+                while the origin is healthy. This is a Cloudflare rate-limit / WAF condition on
+                the public hostname, not an outage.
+              runbook: >-
+                1. curl -sk https://{{ $labels.instance }}/api/v1/manifests/_schema (expect 200 from a normal client)
+                2. Review Cloudflare rate-limit / WAF rules for the hostname; the 5m-cadence prober is tripping a 429
+                3. Add a Cloudflare rate-limit exception for the prober source IP or the /api/v1/manifests/_schema path
+                4. Confirm whether the singular host update.flowercore.io is still required, or only updates.flowercore.io
+
 # =============================================================================
 # ConfigMap: Blackbox Exporter Configuration
 # =============================================================================

argocd/applicationset-bluejay-infra.yaml

@@ -0,0 +1,74 @@
+apiVersion: argoproj.io/v1alpha1
+kind: ApplicationSet
+metadata:
+  annotations:
+    argocd.argoproj.io/refresh: "true"
+  name: bluejay-infra
+  namespace: argocd
+spec:
+  generators:
+  - git:
+      directories:
+      - path: apps/*
+      repoURL: http://gitea-clusterip.gitea.svc:3000/bluejay/bluejay-infra.git
+      revision: main
+      template:
+        metadata: {}
+        spec:
+          destination: {}
+          project: ""
+  goTemplate: true
+  goTemplateOptions:
+  - missingkey=error
+  template:
+    metadata:
+      name: infra-{{.path.basename}}
+    spec:
+      destination:
+        server: https://kubernetes.default.svc
+      ignoreDifferences:
+      - group: apps
+        jqPathExpressions:
+        - .spec.volumeClaimTemplates[]?.status
+        jsonPointers:
+        - /spec/volumeClaimTemplates
+        kind: StatefulSet
+        name: zabbix-postgres
+        namespace: zabbix
+      - group: apps
+        jqPathExpressions:
+        - .spec.volumeClaimTemplates[]?.status
+        jsonPointers:
+        - /spec/volumeClaimTemplates
+        kind: StatefulSet
+        name: guac-mysql
+        namespace: guacamole
+      - group: apps
+        jqPathExpressions:
+        - .spec.volumeClaimTemplates[]?.status
+        jsonPointers:
+        - /spec/volumeClaimTemplates
+        kind: StatefulSet
+        name: matrix-postgres
+        namespace: matrix
+      - group: apps
+        jqPathExpressions:
+        - .spec.volumeClaimTemplates[]?.status
+        jsonPointers:
+        - /spec/volumeClaimTemplates
+        kind: StatefulSet
+        name: authentik-postgres
+        namespace: authentik
+      project: default
+      source:
+        path: '{{.path.path}}'
+        repoURL: http://gitea-clusterip.gitea.svc:3000/bluejay/bluejay-infra.git
+        targetRevision: main
+      syncPolicy:
+        automated:
+          prune: true
+          selfHeal: true
+        syncOptions:
+        - CreateNamespace=true
+        - ServerSideApply=true
+        - RespectIgnoreDifferences=true

tests/bluejay-infra-lint/FleetManifestLintTests.cs

@@ -87,10 +87,10 @@ public sealed class FleetManifestLintTests
             ["fc-devicemgmt"] = ("fc-devicemgmt-web", "/healthz"),
             ["fc-library"] = ("library-web", "/health"),
             ["fc-llm-bridge"] = ("fc-llm-bridge", "/healthz"),
-            ["fc-messageboard"] = ("messageboard-web", "/healthz"),
+            ["fc-messageboard"] = ("messageboard-web", "/health"),
             ["fc-retail"] = ("retail-web", "/healthz"),
-            ["fc-ttsreader"] = ("ttsreader-web", "/healthz"),
+            ["fc-ttsreader"] = ("ttsreader-web", "/health"),
-            ["fc-updater"] = ("updatecenter-web", "/healthz"),
+            ["fc-updater"] = ("updatecenter-web", "/"),
             ["knowledge"] = ("knowledge-web", "/healthz"),
             ["telephony"] = ("telephony-web", "/health"),
             ["worldbuilder"] = ("worldbuilder-web", "/healthz"),
@@ -468,6 +468,99 @@ public sealed class FleetManifestLintTests
         monitoring.Should().Contain("dedicated LinuxRunnerOffline/MacMiniRunnerOffline alerts");
     }
 
+    [Fact]
+    public void GithubRunnerReadme_DocumentsAcceptedEphemeralExitChurn()
+    {
+        var readme = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "github-runner", "README.md"));
+
+        readme.Should().Contain("Ephemeral runner pods");
+        readme.Should().Contain("exit-1/restart churn");
+        readme.Should().Contain("accepted operational noise");
+        readme.Should().Contain("repo-scoped runner-offline alerts stay quiet");
+    }
+
+    [Fact]
+    public void Monitoring_PiManagerDownDelayAndUpdateCenterRateLimit_MatchCanonicalAlerts()
+    {
+        var notesAlerts = File.ReadAllText(Path.Combine(
+            Inventory.WorkspaceRoot,
+            "FlowerCore.Notes",
+            "scripts",
+            "monitoring",
+            "alerts.yml"));
+        var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
+
+        notesAlerts.Should().Contain("# Sprint 67: keep this warning behind NodeDown's 5m critical page");
+        notesAlerts.Should().Contain("- alert: PiManagerDown");
+        notesAlerts.Should().Contain("for: 8m");
+        monitoring.Should().Contain("# Sprint 67: delayed behind NodeDown's critical page");
+        monitoring.Should().Contain("- alert: PiManagerDown");
+        monitoring.Should().Contain("for: 8m");
+
+        notesAlerts.Should().Contain("- alert: UpdateCenterPublicEdgeRateLimited");
+        notesAlerts.Should().Contain("expr: probe_http_status_code{job=\"probe-update-center-public-edge\"} == 429");
+        notesAlerts.Should().Contain("for: 15m");
+        monitoring.Should().Contain("- alert: UpdateCenterPublicEdgeRateLimited");
+        monitoring.Should().Contain("expr: probe_http_status_code{job=\"probe-update-center-public-edge\"} == 429");
+        monitoring.Should().Contain("for: 15m");
+        monitoring.Should().Contain("severity: warning");
+    }
+
+    [Fact]
+    public void ApplicationSetExport_MustRemainManualRootOfGitOpsTree()
+    {
+        var readme = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "README.md"));
+        var appsetPath = Path.Combine(Inventory.BluejayRoot, "argocd", "applicationset-bluejay-infra.yaml");
+
+        File.Exists(appsetPath).Should().BeTrue();
+        var appset = File.ReadAllText(appsetPath);
+
+        appset.Should().Contain("kind: ApplicationSet");
+        appset.Should().Contain("name: bluejay-infra");
+        appset.Should().NotContain("\nstatus:");
+        appset.Should().NotContain("managedFields:");
+        readme.Should().Contain("root of this GitOps tree");
+        readme.Should().Contain("NOT self-managed");
+        readme.Should().Contain("kubectl -n argocd apply -f argocd/applicationset-bluejay-infra.yaml");
+    }
+
+    [Fact]
+    public void ApplicationSetExport_MustDiscoverAppsDirectoryOnMain()
+    {
+        var appset = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "argocd", "applicationset-bluejay-infra.yaml"));
+
+        appset.Should().Contain("path: apps/*");
+        appset.Should().Contain("revision: main");
+        appset.Should().Contain("repoURL: http://gitea-clusterip.gitea.svc:3000/bluejay/bluejay-infra.git");
+        appset.Should().Contain("path: '{{.path.path}}'");
+        appset.Should().Contain("targetRevision: main");
+        appset.Should().Contain("ServerSideApply=true");
+        appset.Should().Contain("RespectIgnoreDifferences=true");
+    }
+
+    [Fact]
+    public void ApplicationSetExport_MustPreserveStatefulSetIgnoreDifferences()
+    {
+        var appset = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "argocd", "applicationset-bluejay-infra.yaml"));
+
+        appset.Should().Contain("jsonPointers:");
+        appset.Should().Contain("- /spec/volumeClaimTemplates");
+        appset.Should().Contain(".spec.volumeClaimTemplates[]?.status");
+        Regex.Matches(appset, "kind: StatefulSet").Should().HaveCount(4);
+
+        foreach (var (name, ns) in new[]
+        {
+            ("zabbix-postgres", "zabbix"),
+            ("guac-mysql", "guacamole"),
+            ("matrix-postgres", "matrix"),
+            ("authentik-postgres", "authentik"),
+        })
+        {
+            appset.Should().Contain($"name: {name}");
+            appset.Should().Contain($"namespace: {ns}");
+        }
+    }
+
     [Fact]
     public void Monitoring_BlackboxTargetsForOidcSensitiveServices_MustUseAnonymousHealthRoutesWhenAvailable()
     {