runners: right-size replica counts per 14d CI activity (#24)

Drop 2 → 1 for 10 deploys based on trailing-14d run counts:
  - LlmBridge, Media, Knowledge, Intranet.Web, DNS  (0 runs each)
  - Presentations (6), Redis (3), Provisioning (3),
    MessageBoard (3), MenuBoard (3)

Bump 2 → 3 for Print.Web: 12 runs in trailing 5d, and the
help-screenshots AAT job holds a runner 30+ min, creating
head-of-line blocking for parallel PRs.

Net change: -9 replicas (≈ -9 GiB committed memory).
Aligns with Sprint 33 morning-routine capacity audit.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

README.md

@@ -118,6 +118,7 @@ That test project sweeps `bluejay-infra/apps/**` plus the canonical sibling `Flo
 
 ## References
 
+- OpenVox noc1 durability runbook: `docs/runbooks/openvoxserver-quadlet-durability.md`
 - Cert-manager recovery playbook: `FlowerCore.Notes/memory/project_cert_manager_recovery_2026_04_22.md`
 - Why pfSense DNS is required: `FlowerCore.Notes/memory/feedback_pfsense_dns_required_for_acme.md`
 - Public DNS operator host: `https://dns.iamworkin.lan`

apps/authentik/authentik.yaml

@@ -0,0 +1,448 @@
+# Authentik OIDC backend
+# ArgoCD-managed. BlueJay Lab.
+#
+# Stack:
+#   - PostgreSQL 16 StatefulSet (single replica, Longhorn RWO 5Gi)
+#   - Redis 7 Deployment (no persistence — session/cache only)
+#   - Authentik server + worker Deployments (image ghcr.io/goauthentik/server:2024.12.3)
+#   - Media PVC shared between server + worker (Longhorn RWO 2Gi)
+#   - Certificate via step-ca-acme ClusterIssuer
+#   - Traefik IngressRoute at id.iamworkin.lan
+#
+# Secrets come from 1Password item "authentik-credentials" (IAmWorkin vault, id y6i74ch22q5wvm7znquq4nhhcu)
+# 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.
+# 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).
+
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: authentik
+  labels:
+    app.kubernetes.io/part-of: bluejay-infra
+
+---
+# 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,
+# BOOTSTRAP_ADMIN_PASSWORD, BOOTSTRAP_ADMIN_TOKEN, BOOTSTRAP_ADMIN_EMAIL.
+apiVersion: onepassword.com/v1
+kind: OnePasswordItem
+metadata:
+  name: authentik-credentials
+  namespace: authentik
+spec:
+  itemPath: "vaults/IAmWorkin/items/authentik-credentials"
+
+---
+# Shared media volume for server + worker pods.
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: authentik-media
+  namespace: authentik
+spec:
+  storageClassName: longhorn
+  accessModes: [ReadWriteOnce]
+  resources:
+    requests:
+      storage: 2Gi
+
+---
+# PostgreSQL 16 StatefulSet — Authentik's primary store.
+apiVersion: apps/v1
+kind: StatefulSet
+metadata:
+  name: authentik-postgres
+  namespace: authentik
+  labels:
+    app: authentik-postgres
+    argocd.argoproj.io/instance: infra-authentik
+spec:
+  persistentVolumeClaimRetentionPolicy:
+    whenDeleted: Retain
+    whenScaled: Retain
+  podManagementPolicy: OrderedReady
+  serviceName: authentik-postgres
+  replicas: 1
+  revisionHistoryLimit: 10
+  selector:
+    matchLabels:
+      app: authentik-postgres
+  template:
+    metadata:
+      labels:
+        app: authentik-postgres
+    spec:
+      containers:
+        - name: postgres
+          image: postgres:16-alpine
+          ports:
+            - containerPort: 5432
+              name: postgres
+          env:
+            - name: POSTGRES_USER
+              value: authentik
+            - name: POSTGRES_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: POSTGRES_PASSWORD
+            - name: POSTGRES_DB
+              value: authentik
+            - name: POSTGRES_INITDB_ARGS
+              value: "--encoding=UTF-8 --lc-collate=C --lc-ctype=C"
+            - name: PGDATA
+              value: /var/lib/postgresql/data/pgdata
+          readinessProbe:
+            exec:
+              command: ["pg_isready", "-U", "authentik"]
+            initialDelaySeconds: 5
+            periodSeconds: 5
+          livenessProbe:
+            exec:
+              command: ["pg_isready", "-U", "authentik"]
+            initialDelaySeconds: 30
+            periodSeconds: 30
+          resources:
+            requests: { cpu: 100m, memory: 256Mi }
+            limits: { cpu: 1000m, memory: 1Gi }
+          volumeMounts:
+            - name: pgdata
+              mountPath: /var/lib/postgresql/data
+  volumeClaimTemplates:
+    - metadata:
+        name: pgdata
+      spec:
+        storageClassName: longhorn
+        accessModes: [ReadWriteOnce]
+        volumeMode: Filesystem
+        resources:
+          requests:
+            storage: 5Gi
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: authentik-postgres
+  namespace: authentik
+spec:
+  clusterIP: None
+  selector:
+    app: authentik-postgres
+  ports:
+    - name: postgres
+      port: 5432
+      targetPort: 5432
+
+---
+# Redis 7 — session storage + Celery broker. No persistence needed (cache).
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: authentik-redis
+  namespace: authentik
+  labels:
+    app: authentik-redis
+    argocd.argoproj.io/instance: infra-authentik
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: authentik-redis
+  template:
+    metadata:
+      labels:
+        app: authentik-redis
+    spec:
+      containers:
+        - name: redis
+          image: redis:7-alpine
+          args:
+            - "--save"
+            - ""
+            - "--appendonly"
+            - "no"
+            - "--requirepass"
+            - "$(REDIS_PASSWORD)"
+          env:
+            - name: REDIS_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: REDIS_PASSWORD
+          ports:
+            - containerPort: 6379
+              name: redis
+          readinessProbe:
+            tcpSocket: { port: 6379 }
+            initialDelaySeconds: 5
+            periodSeconds: 5
+          livenessProbe:
+            tcpSocket: { port: 6379 }
+            initialDelaySeconds: 30
+            periodSeconds: 30
+          resources:
+            requests: { cpu: 50m, memory: 64Mi }
+            limits: { cpu: 500m, memory: 256Mi }
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: authentik-redis
+  namespace: authentik
+spec:
+  selector:
+    app: authentik-redis
+  ports:
+    - name: redis
+      port: 6379
+      targetPort: 6379
+
+---
+# Authentik server Deployment — HTTP frontend on :9000.
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: authentik-server
+  namespace: authentik
+  labels:
+    app: authentik-server
+    argocd.argoproj.io/instance: infra-authentik
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate  # shares /media RWO PVC with worker
+  selector:
+    matchLabels:
+      app: authentik-server
+  template:
+    metadata:
+      labels:
+        app: authentik-server
+    spec:
+      securityContext:
+        # Authentik image runs as uid 1000 "authentik" but the Longhorn PVC mounts
+        # root:root by default. fsGroup recursively chgrp + chmod g+rwx so the
+        # non-root container can mkdir /media/public during the tenant_files migration.
+        fsGroup: 1000
+      containers:
+        - name: server
+          image: ghcr.io/goauthentik/server:2024.12.3
+          args: ["server"]
+          ports:
+            - containerPort: 9000
+              name: http
+            - containerPort: 9443
+              name: https
+          env:
+            - name: AUTHENTIK_SECRET_KEY
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: AUTHENTIK_SECRET_KEY
+            - name: AUTHENTIK_REDIS__HOST
+              value: authentik-redis
+            - name: AUTHENTIK_REDIS__PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: REDIS_PASSWORD
+            - name: AUTHENTIK_POSTGRESQL__HOST
+              value: authentik-postgres
+            - name: AUTHENTIK_POSTGRESQL__NAME
+              value: authentik
+            - name: AUTHENTIK_POSTGRESQL__USER
+              value: authentik
+            - name: AUTHENTIK_POSTGRESQL__PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: POSTGRES_PASSWORD
+            - name: AUTHENTIK_BOOTSTRAP_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: BOOTSTRAP_ADMIN_PASSWORD
+            - name: AUTHENTIK_BOOTSTRAP_TOKEN
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: BOOTSTRAP_ADMIN_TOKEN
+            - name: AUTHENTIK_BOOTSTRAP_EMAIL
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: BOOTSTRAP_ADMIN_EMAIL
+            - name: AUTHENTIK_DISABLE_UPDATE_CHECK
+              value: "true"
+            - name: AUTHENTIK_ERROR_REPORTING__ENABLED
+              value: "false"
+            - name: AUTHENTIK_LOG_LEVEL
+              value: info
+          # First-boot Authentik can take 3+ min on the migration phase
+          # (waiting on DB lock while worker also runs migrations). Initial
+          # delays are generous so kubelet doesn't kill the pod mid-migration;
+          # periodSeconds keeps post-startup probing responsive.
+          readinessProbe:
+            httpGet:
+              path: /-/health/ready/
+              port: 9000
+            initialDelaySeconds: 60
+            periodSeconds: 10
+            timeoutSeconds: 5
+            failureThreshold: 12
+          livenessProbe:
+            httpGet:
+              path: /-/health/live/
+              port: 9000
+            initialDelaySeconds: 300
+            periodSeconds: 30
+            timeoutSeconds: 10
+            failureThreshold: 3
+          startupProbe:
+            httpGet:
+              path: /-/health/live/
+              port: 9000
+            initialDelaySeconds: 30
+            periodSeconds: 15
+            timeoutSeconds: 10
+            failureThreshold: 40  # 30s + 40*15s = 10.5 min budget
+          resources:
+            requests: { cpu: 150m, memory: 512Mi }
+            limits: { cpu: 1500m, memory: 1Gi }
+          volumeMounts:
+            - name: media
+              mountPath: /media
+      volumes:
+        - name: media
+          persistentVolumeClaim:
+            claimName: authentik-media
+
+---
+# Authentik worker Deployment — runs Celery background tasks.
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: authentik-worker
+  namespace: authentik
+  labels:
+    app: authentik-worker
+    argocd.argoproj.io/instance: infra-authentik
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate  # shares /media RWO PVC with server
+  selector:
+    matchLabels:
+      app: authentik-worker
+  template:
+    metadata:
+      labels:
+        app: authentik-worker
+    spec:
+      securityContext:
+        # Same as server pod — non-root uid 1000 needs PVC group write.
+        fsGroup: 1000
+      containers:
+        - name: worker
+          image: ghcr.io/goauthentik/server:2024.12.3
+          args: ["worker"]
+          env:
+            - name: AUTHENTIK_SECRET_KEY
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: AUTHENTIK_SECRET_KEY
+            - name: AUTHENTIK_REDIS__HOST
+              value: authentik-redis
+            - name: AUTHENTIK_REDIS__PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: REDIS_PASSWORD
+            - name: AUTHENTIK_POSTGRESQL__HOST
+              value: authentik-postgres
+            - name: AUTHENTIK_POSTGRESQL__NAME
+              value: authentik
+            - name: AUTHENTIK_POSTGRESQL__USER
+              value: authentik
+            - name: AUTHENTIK_POSTGRESQL__PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: POSTGRES_PASSWORD
+            - name: AUTHENTIK_DISABLE_UPDATE_CHECK
+              value: "true"
+            - name: AUTHENTIK_ERROR_REPORTING__ENABLED
+              value: "false"
+            - name: AUTHENTIK_LOG_LEVEL
+              value: info
+          resources:
+            requests: { cpu: 100m, memory: 256Mi }
+            limits: { cpu: 1000m, memory: 768Mi }
+          volumeMounts:
+            - name: media
+              mountPath: /media
+      volumes:
+        - name: media
+          persistentVolumeClaim:
+            claimName: authentik-media
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: authentik-server
+  namespace: authentik
+spec:
+  selector:
+    app: authentik-server
+  ports:
+    - name: http
+      port: 9000
+      targetPort: 9000
+    - name: https
+      port: 9443
+      targetPort: 9443
+
+---
+# step-ca leaf certificate for id.iamworkin.lan.
+# step-ca container resolver uses pfSense Unbound, so the public A record for id.iamworkin.lan
+# MUST exist before this Certificate is applied (cert-manager HTTP-01 will silently 2h-backoff
+# otherwise). Added 2026-05-25 via scripts/pfsense-add-id-host.py.
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: authentik-tls
+  namespace: authentik
+spec:
+  secretName: authentik-tls
+  dnsNames:
+    - id.iamworkin.lan
+  issuerRef:
+    name: step-ca-acme
+    kind: ClusterIssuer
+
+---
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: authentik
+  namespace: authentik
+spec:
+  entryPoints: [websecure]
+  routes:
+    - match: Host(`id.iamworkin.lan`)
+      kind: Rule
+      services:
+        - name: authentik-server
+          port: 9000
+  tls:
+    secretName: authentik-tls

apps/fc-chat/fc-chat.yaml

@@ -30,3 +30,41 @@ spec:
           port: 80
   tls:
     secretName: chat-web-tls
+---
+# Public host profile marker. The app treats this header as authoritative for
+# the public twin, while the internal chat.iamworkin.lan route does not attach
+# it and keeps the operator-oriented UI.
+apiVersion: traefik.io/v1alpha1
+kind: Middleware
+metadata:
+  name: chat-public-profile-header
+  namespace: fc-chat
+spec:
+  headers:
+    customRequestHeaders:
+      X-FC-Chat-Host-Profile: "public"
+---
+# Public Cloudflare-fronted twin for the anonymous chat surface. Operator
+# paths are intentionally absent from the allowlist below, so /admin,
+# /operator, /console, /ops, /api/operator, and /operatorhub miss this route
+# and return Traefik 404 before reaching the pod. Operator action still needed:
+# create/verify Cloudflare DNS chat.flowercore.io -> public Traefik endpoint
+# and mirror the cf-origin-flowercore-io TLS secret into namespace fc-chat.
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: chat-web-public
+  namespace: fc-chat
+spec:
+  entryPoints:
+    - websecure
+  routes:
+    - match: Host(`chat.flowercore.io`) && (Path(`/`) || Path(`/chat`) || PathPrefix(`/_blazor`) || PathPrefix(`/_framework`) || PathPrefix(`/_content`) || PathPrefix(`/avatars`) || PathPrefix(`/css`) || PathPrefix(`/js`) || PathPrefix(`/favicon`) || PathPrefix(`/chathub`)) && (Method(`GET`) || Method(`HEAD`) || Method(`POST`) || Method(`OPTIONS`))
+      kind: Rule
+      middlewares:
+        - name: chat-public-profile-header
+      services:
+        - name: chat-web
+          port: 80
+  tls:
+    secretName: cf-origin-flowercore-io

apps/fc-devicemgmt/1password-item.yaml

@@ -0,0 +1,26 @@
+# Runtime secrets for FlowerCore.DeviceManagement.
+#
+# OnePasswordItem operator syncs this item into a Kubernetes Secret with the
+# same name. Expected fields:
+#   DB-Password
+#   mtls-ca.pem
+#   mtls-client.crt
+#   mtls-client.key
+#   mtls-chain.pem
+#
+# Do not add literal secret values to this repo. Runtime pods consume the
+# synced Secret through env vars and read-only mounts.
+apiVersion: onepassword.com/v1
+kind: OnePasswordItem
+metadata:
+  name: fc-devicemgmt-runtime
+  namespace: fc-devicemgmt
+  labels:
+    app.kubernetes.io/name: fc-devicemgmt
+    app.kubernetes.io/component: secrets
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
+spec:
+  itemPath: "vaults/IAmWorkin/items/FlowerCore DeviceManagement Runtime"

apps/fc-devicemgmt/certificate-web.yaml

@@ -0,0 +1,30 @@
+# Certificate for devices.iamworkin.lan.
+#
+# Preflight gate: FlowerCore.DNS / pfSense must contain an explicit A record:
+#   devices.iamworkin.lan -> 10.0.56.200
+# before this Certificate is synced. step-ca ACME cannot see the CoreDNS
+# wildcard, so missing pfSense DNS produces cert-manager HTTP-01 backoff
+# (feedback_pfsense_dns_required_for_acme).
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: fc-devicemgmt-web-tls
+  namespace: fc-devicemgmt
+  labels:
+    app.kubernetes.io/name: fc-devicemgmt-web
+    app.kubernetes.io/component: web
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
+  annotations:
+    flowercore.io/dns-preflight: "devices.iamworkin.lan must resolve to 10.0.56.200 before ACME sync"
+spec:
+  secretName: fc-devicemgmt-web-tls
+  issuerRef:
+    name: step-ca-acme
+    kind: ClusterIssuer
+  dnsNames:
+    - devices.iamworkin.lan
+  duration: 720h
+  renewBefore: 240h

apps/fc-devicemgmt/clusterrole-operator.yaml

@@ -0,0 +1,81 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: fc-devicemgmt-operator
+  labels:
+    app.kubernetes.io/name: fc-devicemgmt-operator
+    app.kubernetes.io/component: operator
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
+rules:
+  - apiGroups:
+      - devices.flowercore.io
+    resources:
+      - '*'
+    verbs:
+      - get
+      - list
+      - watch
+      - create
+      - update
+      - patch
+      - delete
+  - apiGroups:
+      - devices.flowercore.io
+    resources:
+      - devices/status
+      - devices/finalizers
+      - devicegroups/status
+      - devicegroups/finalizers
+      - devicepolicies/status
+      - devicepolicies/finalizers
+      - remotecommands/status
+      - remotecommands/finalizers
+    verbs:
+      - get
+      - update
+      - patch
+  - apiGroups:
+      - apps
+    resources:
+      - deployments
+    verbs:
+      - get
+  - apiGroups:
+      - ""
+    resources:
+      - pods
+      - services
+      - configmaps
+      - secrets
+      - events
+    verbs:
+      - get
+      - list
+      - watch
+      - create
+      - update
+      - patch
+      - delete
+  - apiGroups:
+      - batch
+    resources:
+      - jobs
+    verbs:
+      - get
+      - list
+      - watch
+      - create
+      - update
+      - patch
+      - delete
+  - apiGroups:
+      - networking.k8s.io
+    resources:
+      - networkpolicies
+    verbs:
+      - get
+      - list
+      - watch

apps/fc-devicemgmt/clusterrolebinding-operator.yaml

@@ -0,0 +1,19 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: fc-devicemgmt-operator
+  labels:
+    app.kubernetes.io/name: fc-devicemgmt-operator
+    app.kubernetes.io/component: operator
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: fc-devicemgmt-operator
+subjects:
+  - kind: ServiceAccount
+    name: fc-devicemgmt-operator
+    namespace: fc-devicemgmt

apps/fc-devicemgmt/deployment-operator.yaml

@@ -0,0 +1,109 @@
+# FlowerCore.DeviceManagement Operator.
+#
+# KubeOps controller for devices.flowercore.io resources. Operator-created
+# children must set OwnerReferences + traceability labels/annotations per
+# k8s-pod-ownership-and-traceability-standard.md. RBAC below grants
+# apps/deployments/get so the process can resolve its own Deployment UID.
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: fc-devicemgmt-operator
+  namespace: fc-devicemgmt
+  labels:
+    app: fc-devicemgmt-operator
+    app.kubernetes.io/name: fc-devicemgmt-operator
+    app.kubernetes.io/component: operator
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
+  annotations:
+    flowercore.io/traceability-standard: k8s-pod-ownership-and-traceability-standard
+spec:
+  replicas: 1
+  revisionHistoryLimit: 3
+  selector:
+    matchLabels:
+      app: fc-devicemgmt-operator
+  template:
+    metadata:
+      labels:
+        app: fc-devicemgmt-operator
+        app.kubernetes.io/name: fc-devicemgmt-operator
+        app.kubernetes.io/component: operator
+        app.kubernetes.io/part-of: flowercore
+        app.kubernetes.io/managed-by: argocd
+        flowercore.io/tenant-id: system
+        flowercore.io/created-by: bluejay-infra
+      annotations:
+        prometheus.io/scrape: "true"
+        prometheus.io/port: "8080"
+        prometheus.io/path: "/metrics"
+        flowercore.io/audit-trace-id: "runtime-activity-trace"
+    spec:
+      serviceAccountName: fc-devicemgmt-operator
+      securityContext:
+        fsGroup: 1654
+        fsGroupChangePolicy: OnRootMismatch
+      containers:
+        - name: operator
+          image: localhost/fc-devicemgmt-operator:v20260519-sp34cl3-fix
+          imagePullPolicy: Never
+          ports:
+            - name: metrics
+              containerPort: 8080
+          env:
+            - name: ASPNETCORE_ENVIRONMENT
+              value: "Production"
+            - name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
+              value: "false"
+            - name: POD_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.name
+            - name: POD_NAMESPACE
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.namespace
+            - name: FLOWERCORE_KUBERNETES_OWNER_DEPLOYMENT
+              value: "fc-devicemgmt-operator"
+            - name: FlowerCore__Service__Name
+              value: "FlowerCore.DeviceManagement.Operator"
+            - name: FlowerCore__DeviceManagement__DefaultTenantId
+              value: "system"
+          resources:
+            requests:
+              cpu: 50m
+              memory: 128Mi
+            limits:
+              cpu: 500m
+              memory: 512Mi
+          readinessProbe:
+            tcpSocket:
+              port: 8080
+            initialDelaySeconds: 5
+            periodSeconds: 10
+          livenessProbe:
+            tcpSocket:
+              port: 8080
+            initialDelaySeconds: 20
+            periodSeconds: 30
+          securityContext:
+            runAsNonRoot: true
+            runAsUser: 1654
+            runAsGroup: 1654
+            allowPrivilegeEscalation: false
+            readOnlyRootFilesystem: true
+            capabilities:
+              drop:
+                - ALL
+          volumeMounts:
+            - name: tmp
+              mountPath: /tmp
+            - name: logs
+              mountPath: /app/logs
+      volumes:
+        - name: tmp
+          emptyDir: {}
+        - name: logs
+          emptyDir: {}

apps/fc-devicemgmt/deployment-web.yaml

@@ -0,0 +1,151 @@
+# FlowerCore.DeviceManagement Web.
+#
+# Source repo is expected to ship FlowerCore.DeviceManagement.Web in a later
+# Sprint 9+ lane. This manifest is static-valid without requiring the image to
+# exist yet; import localhost/fc-devicemgmt-web:<tag> to all schedulable RKE2
+# nodes before letting ArgoCD sync a live rollout.
+#
+# SCALED TO 0 — 2026-05-19 morning-routine cleanup.
+# The Web pod cannot start until TWO upstream gaps close:
+#   1. MySQL DB instance `flowercore_devicemgmt` (user `fc_devicemgmt`) is
+#      provisioned via fc-mysql Manager. The cluster currently has ZERO
+#      MySqlInstanceCrds and no `mysql.fc-mysql.svc:3306` Service, so the
+#      deployment-web container env `FlowerCore__Database__Host=mysql.fc-mysql.svc`
+#      points at nothing. Provision via the fc-mysql Manager UI/REST/MCP.
+#   2. 1Password vault item `IAmWorkin/FlowerCore DeviceManagement Runtime`
+#      with 5 fields (DB-Password, mtls-ca.pem, mtls-client.crt, mtls-client.key,
+#      mtls-chain.pem) — see apps/fc-devicemgmt/1password-item.yaml. Mint mTLS
+#      from step-ca-agent ClusterIssuer per ADR-126; DB-Password must match the
+#      password configured for the MySQL user.
+# Re-enable: change replicas back to 2 after both gaps close. The image tag
+# in this file (v20260512-cx5) MAY also need a refresh — it predates the
+# Sprint 34 Cl-3 operator fix; Web may have an analogous bug.
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: fc-devicemgmt-web
+  namespace: fc-devicemgmt
+  labels:
+    app: fc-devicemgmt-web
+    app.kubernetes.io/name: fc-devicemgmt-web
+    app.kubernetes.io/component: web
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
+  annotations:
+    flowercore.io/traceability-standard: k8s-pod-ownership-and-traceability-standard
+spec:
+  replicas: 0
+  revisionHistoryLimit: 3
+  selector:
+    matchLabels:
+      app: fc-devicemgmt-web
+  template:
+    metadata:
+      labels:
+        app: fc-devicemgmt-web
+        app.kubernetes.io/name: fc-devicemgmt-web
+        app.kubernetes.io/component: web
+        app.kubernetes.io/part-of: flowercore
+        app.kubernetes.io/managed-by: argocd
+        flowercore.io/tenant-id: system
+        flowercore.io/created-by: bluejay-infra
+      annotations:
+        prometheus.io/scrape: "true"
+        prometheus.io/port: "8080"
+        prometheus.io/path: "/metrics"
+        flowercore.io/audit-trace-id: "runtime-activity-trace"
+    spec:
+      securityContext:
+        fsGroup: 1654
+        fsGroupChangePolicy: OnRootMismatch
+      containers:
+        - name: web
+          image: localhost/fc-devicemgmt-web:v20260512-cx5
+          imagePullPolicy: Never
+          ports:
+            - name: http
+              containerPort: 8080
+          env:
+            - name: ASPNETCORE_URLS
+              value: "http://+:8080"
+            - name: ASPNETCORE_ENVIRONMENT
+              value: "Production"
+            - name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
+              value: "false"
+            - name: FlowerCore__Service__Name
+              value: "FlowerCore.DeviceManagement.Web"
+            - name: FlowerCore__DeviceManagement__DefaultTenantId
+              value: "system"
+            - name: FlowerCore__Database__Provider
+              value: "MySql"
+            - name: FlowerCore__Database__Host
+              value: "mysql.fc-mysql.svc"
+            - name: FlowerCore__Database__Database
+              value: "flowercore_devicemgmt"
+            - name: FlowerCore__Database__User
+              value: "fc_devicemgmt"
+            - name: FlowerCore__Database__Password
+              valueFrom:
+                secretKeyRef:
+                  name: fc-devicemgmt-runtime
+                  key: DB-Password
+            - name: FlowerCore__DeviceManagement__AgentMtls__CaPath
+              value: "/secrets/devicemgmt-mtls/mtls-ca.pem"
+            - name: FlowerCore__DeviceManagement__AgentMtls__ClientCertificatePath
+              value: "/secrets/devicemgmt-mtls/mtls-client.crt"
+            - name: FlowerCore__DeviceManagement__AgentMtls__ClientKeyPath
+              value: "/secrets/devicemgmt-mtls/mtls-client.key"
+            - name: FlowerCore__EventBus__Redis__Configuration
+              value: "redis.fc-redis.svc:6379"
+          resources:
+            requests:
+              cpu: 100m
+              memory: 256Mi
+            limits:
+              cpu: 1000m
+              memory: 768Mi
+          startupProbe:
+            tcpSocket:
+              port: 8080
+            initialDelaySeconds: 5
+            periodSeconds: 5
+            failureThreshold: 30
+          readinessProbe:
+            tcpSocket:
+              port: 8080
+            periodSeconds: 10
+            failureThreshold: 3
+          livenessProbe:
+            tcpSocket:
+              port: 8080
+            initialDelaySeconds: 30
+            periodSeconds: 30
+            failureThreshold: 3
+          securityContext:
+            runAsNonRoot: true
+            runAsUser: 1654
+            runAsGroup: 1654
+            allowPrivilegeEscalation: false
+            readOnlyRootFilesystem: true
+            capabilities:
+              drop:
+                - ALL
+          volumeMounts:
+            - name: tmp
+              mountPath: /tmp
+            - name: logs
+              mountPath: /app/logs
+            - name: devicemgmt-mtls
+              mountPath: /secrets/devicemgmt-mtls
+              readOnly: true
+      volumes:
+        - name: tmp
+          emptyDir: {}
+        - name: logs
+          emptyDir: {}
+        - name: devicemgmt-mtls
+          secret:
+            secretName: fc-devicemgmt-runtime
+            defaultMode: 0400

apps/fc-devicemgmt/ingressroute-web.yaml

@@ -0,0 +1,55 @@
+# LAN ingress for FlowerCore.DeviceManagement Web.
+#
+# RKE2 Traefik has no built-in ACME resolver configured. Keep TLS certificate
+# ownership in cert-manager Certificate/fc-devicemgmt-web-tls.
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: fc-devicemgmt-web
+  namespace: fc-devicemgmt
+  labels:
+    app.kubernetes.io/name: fc-devicemgmt-web
+    app.kubernetes.io/component: web
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
+spec:
+  entryPoints:
+    - websecure
+  routes:
+    - match: Host(`devices.iamworkin.lan`)
+      kind: Rule
+      services:
+        - name: fc-devicemgmt-web
+          port: 80
+  tls:
+    secretName: fc-devicemgmt-web-tls
+
+# Future public agent/update host gate (OFF by default):
+#
+# Do not enable `update.flowercore.io` here until Authentik OIDC Q-OIDC-1
+# resolves the public-device-management auth model and route ownership with
+# UpdateCenter. When enabled, use a separate public IngressRoute with an
+# explicit Method allowlist, public-host auth middleware, and public TLS
+# certificate strategy. Leaving this as comments keeps ArgoCD from stealing
+# live UpdateCenter traffic.
+#
+# apiVersion: traefik.io/v1alpha1
+# kind: IngressRoute
+# metadata:
+#   name: fc-devicemgmt-web-public
+#   namespace: fc-devicemgmt
+#   annotations:
+#     flowercore.io/public-host-gate: "disabled-until-Q-OIDC-1"
+# spec:
+#   entryPoints:
+#     - websecure
+#   routes:
+#     - match: Host(`update.flowercore.io`) && (Method(`GET`) || Method(`HEAD`) || Method(`POST`) || Method(`OPTIONS`))
+#       kind: Rule
+#       services:
+#         - name: fc-devicemgmt-web
+#           port: 80
+#   tls:
+#     secretName: fc-devicemgmt-public-tls

apps/fc-devicemgmt/namespace.yaml

@@ -0,0 +1,13 @@
+# FlowerCore.DeviceManagement namespace.
+#
+# ArgoCD discovers this directory as Application `infra-fc-devicemgmt`.
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: fc-devicemgmt
+  labels:
+    app.kubernetes.io/name: fc-devicemgmt
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra

apps/fc-devicemgmt/network-policy.yaml

@@ -0,0 +1,224 @@
+# FlowerCore.DeviceManagement NetworkPolicies.
+#
+# NetworkPolicies belong in bluejay-infra so ArgoCD owns rebuild state.
+# Rules include Traefik post-DNAT backend ports per
+# feedback_netpol_dnat_backend_port and Synology NFS egress for the requested
+# cold-tier / future artifact path.
+---
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: fc-devicemgmt-web-isolation
+  namespace: fc-devicemgmt
+  labels:
+    app.kubernetes.io/name: fc-devicemgmt-web
+    app.kubernetes.io/component: web
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
+spec:
+  podSelector:
+    matchLabels:
+      app: fc-devicemgmt-web
+  policyTypes:
+    - Ingress
+    - Egress
+  ingress:
+    # LAN edge: only cluster Traefik should reach the Web pod for
+    # devices.iamworkin.lan.
+    - from:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: traefik-system
+          podSelector:
+            matchLabels:
+              app.kubernetes.io/name: traefik
+      ports:
+        - port: 8080
+          protocol: TCP
+    # Direct LAN diagnostics are allowed only from FlowerCore LAN/VPN ranges.
+    - from:
+        - ipBlock:
+            cidr: 10.0.56.0/24
+        - ipBlock:
+            cidr: 10.0.57.0/24
+        - ipBlock:
+            cidr: 10.0.58.0/24
+        - ipBlock:
+            cidr: 10.0.68.0/27
+      ports:
+        - port: 8080
+          protocol: TCP
+  egress:
+    # CoreDNS.
+    - to:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: kube-system
+          podSelector:
+            matchLabels:
+              k8s-app: kube-dns
+      ports:
+        - port: 53
+          protocol: UDP
+        - port: 53
+          protocol: TCP
+    # Database namespace.
+    - to:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: fc-mysql
+      ports:
+        - port: 3306
+          protocol: TCP
+    # Redis backplane for multi-replica SignalR / live-status fan-out.
+    - to:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: fc-redis
+      ports:
+        - port: 6379
+          protocol: TCP
+    # Traefik VIP / in-cluster Traefik for self-callbacks and public URL
+    # generation tests. Include post-DNAT backend ports 8443 + 8080.
+    - to:
+        - ipBlock:
+            cidr: 10.0.56.200/32
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: traefik-system
+          podSelector:
+            matchLabels:
+              app.kubernetes.io/name: traefik
+      ports:
+        - port: 80
+          protocol: TCP
+        - port: 443
+          protocol: TCP
+        - port: 8080
+          protocol: TCP
+        - port: 8443
+          protocol: TCP
+    # Agent egress: LAN/VPN devices may run DM Agent in Generic, Kiosk, Pi,
+    # ThinClient, or Server mode. Keep this private-range only.
+    - to:
+        - ipBlock:
+            cidr: 10.0.56.0/24
+        - ipBlock:
+            cidr: 10.0.57.0/24
+        - ipBlock:
+            cidr: 10.0.58.0/24
+        - ipBlock:
+            cidr: 10.0.68.0/27
+      ports:
+        - port: 80
+          protocol: TCP
+        - port: 443
+          protocol: TCP
+        - port: 8080
+          protocol: TCP
+        - port: 8443
+          protocol: TCP
+        - port: 5000
+          protocol: TCP
+        - port: 5001
+          protocol: TCP
+    # Synology NFS cold-tier / artifact mount allowance.
+    - to:
+        - ipBlock:
+            cidr: 10.0.58.3/32
+      ports:
+        - port: 2049
+          protocol: TCP
+        - port: 2049
+          protocol: UDP
+        - port: 111
+          protocol: TCP
+        - port: 111
+          protocol: UDP
+---
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: fc-devicemgmt-operator-isolation
+  namespace: fc-devicemgmt
+  labels:
+    app.kubernetes.io/name: fc-devicemgmt-operator
+    app.kubernetes.io/component: operator
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
+spec:
+  podSelector:
+    matchLabels:
+      app: fc-devicemgmt-operator
+  policyTypes:
+    - Ingress
+    - Egress
+  ingress:
+    - from:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: monitoring
+      ports:
+        - port: 8080
+          protocol: TCP
+  egress:
+    # CoreDNS.
+    - to:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: kube-system
+          podSelector:
+            matchLabels:
+              k8s-app: kube-dns
+      ports:
+        - port: 53
+          protocol: UDP
+        - port: 53
+          protocol: TCP
+    # Kubernetes API for KubeOps reconciliation and Deployment UID lookup.
+    - to: []
+      ports:
+        - port: 443
+          protocol: TCP
+        - port: 6443
+          protocol: TCP
+    # Agent egress for operator-initiated probes / fallback command dispatch.
+    - to:
+        - ipBlock:
+            cidr: 10.0.56.0/24
+        - ipBlock:
+            cidr: 10.0.57.0/24
+        - ipBlock:
+            cidr: 10.0.58.0/24
+        - ipBlock:
+            cidr: 10.0.68.0/27
+      ports:
+        - port: 80
+          protocol: TCP
+        - port: 443
+          protocol: TCP
+        - port: 8080
+          protocol: TCP
+        - port: 8443
+          protocol: TCP
+        - port: 5000
+          protocol: TCP
+        - port: 5001
+          protocol: TCP
+    # Synology NFS allowance for future cold-tier/audit archival jobs.
+    - to:
+        - ipBlock:
+            cidr: 10.0.58.3/32
+      ports:
+        - port: 2049
+          protocol: TCP
+        - port: 2049
+          protocol: UDP
+        - port: 111
+          protocol: TCP
+        - port: 111
+          protocol: UDP

apps/fc-devicemgmt/service-web.yaml

@@ -0,0 +1,22 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: fc-devicemgmt-web
+  namespace: fc-devicemgmt
+  labels:
+    app: fc-devicemgmt-web
+    app.kubernetes.io/name: fc-devicemgmt-web
+    app.kubernetes.io/component: web
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
+spec:
+  type: ClusterIP
+  selector:
+    app: fc-devicemgmt-web
+  ports:
+    - name: http
+      port: 80
+      targetPort: 8080
+      protocol: TCP

apps/fc-devicemgmt/serviceaccount-operator.yaml

@@ -0,0 +1,12 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: fc-devicemgmt-operator
+  namespace: fc-devicemgmt
+  labels:
+    app.kubernetes.io/name: fc-devicemgmt-operator
+    app.kubernetes.io/component: operator
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra

apps/fc-redis/fc-redis.yaml

@@ -0,0 +1,171 @@
+# fc-redis — SignalR backplane for cross-product event bus
+#
+# Lands per Q-SO-1 resolution (2026-05-11 PM): SignalR backplane in Phase A,
+# not Phase C as originally drafted. Operator directive: "Redis can be
+# deployed just fine as it's another FlowerCore technology we'll want to
+# manage."
+#
+# Phase A scope (this file):
+#   - Single Redis 7.x Alpine pod
+#   - 1Gi Longhorn RWO PVC for AOF persistence
+#   - ClusterIP Service at `redis.fc-redis.svc.cluster.local:6379`
+#   - No AUTH (in-cluster only; not exposed externally)
+#   - No IngressRoute (backplane is server-to-server only)
+#
+# Consumers (Phase A IMPL across FC services):
+#   - FlowerCore.Signage.Web (OpsConsoleHub)
+#   - FlowerCore.Scoreboard.Web (ScoreboardHub)
+#   - FlowerCore.SignalControl.Web
+#   - FlowerCore.DMS.Web
+#   - Any other product joining the cross-product event bus
+#
+# Each consumer adds:
+#   services.AddSignalR()
+#           .AddStackExchangeRedis(
+#               "redis.fc-redis.svc.cluster.local:6379",
+#               opts => opts.Configuration.ChannelPrefix =
+#                   StackExchange.Redis.RedisChannel.Literal("fc-opsconsole"));
+#
+# Phase B / C follow-ons (out of scope here):
+#   - Redis Sentinel for HA (3-node)
+#   - AUTH password from 1Password Connect (rotate via /rotate-password)
+#   - redis_exporter sidecar for Prometheus scrape
+#   - Network policies restricting which namespaces can dial 6379
+#
+# Design: docs/signage/operations-console-phase-2-design.md §3.5
+# Decision: Q-SO-1 (RESOLVED 2026-05-11 PM)
+# Memory: feedback_blooming_ui_pattern_no_iframes
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: fc-redis
+  labels:
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: fc-redis-data
+  namespace: fc-redis
+spec:
+  accessModes:
+    - ReadWriteOnce
+  storageClassName: longhorn
+  resources:
+    requests:
+      storage: 1Gi
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: fc-redis-config
+  namespace: fc-redis
+data:
+  redis.conf: |
+    # Phase A — minimal config; no AUTH, no replication.
+    bind 0.0.0.0
+    protected-mode no
+    port 6379
+    tcp-backlog 511
+    timeout 0
+    tcp-keepalive 300
+
+    # Persistence: AOF (fsync every second is the standard SignalR-backplane
+    # durability sweet spot — the backplane only needs to survive Redis
+    # restarts, not absolute zero loss).
+    appendonly yes
+    appendfsync everysec
+    auto-aof-rewrite-percentage 100
+    auto-aof-rewrite-min-size 64mb
+
+    # Reasonable defaults — let Redis pick most things.
+    maxmemory-policy allkeys-lru
+    maxmemory 256mb
+
+    # Logging
+    loglevel notice
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: fc-redis
+  namespace: fc-redis
+  labels:
+    app: fc-redis
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate           # RWO PVC; do not do rolling update
+  selector:
+    matchLabels:
+      app: fc-redis
+  template:
+    metadata:
+      labels:
+        app: fc-redis
+    spec:
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 999       # redis:7-alpine default uid
+        runAsGroup: 999
+        fsGroup: 999
+      containers:
+        - name: redis
+          image: redis:7-alpine
+          imagePullPolicy: IfNotPresent
+          command: ["redis-server", "/etc/redis/redis.conf"]
+          ports:
+            - name: redis
+              containerPort: 6379
+          resources:
+            requests:
+              cpu: "50m"
+              memory: "128Mi"
+            limits:
+              cpu: "500m"
+              memory: "384Mi"
+          volumeMounts:
+            - name: data
+              mountPath: /data
+            - name: config
+              mountPath: /etc/redis
+              readOnly: true
+          livenessProbe:
+            tcpSocket:
+              port: 6379
+            initialDelaySeconds: 5
+            periodSeconds: 10
+          readinessProbe:
+            exec:
+              command: ["redis-cli", "ping"]
+            initialDelaySeconds: 2
+            periodSeconds: 5
+          securityContext:
+            allowPrivilegeEscalation: false
+            readOnlyRootFilesystem: true
+            capabilities:
+              drop: [ALL]
+      volumes:
+        - name: data
+          persistentVolumeClaim:
+            claimName: fc-redis-data
+        - name: config
+          configMap:
+            name: fc-redis-config
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: redis
+  namespace: fc-redis
+spec:
+  type: ClusterIP
+  selector:
+    app: fc-redis
+  ports:
+    - name: redis
+      port: 6379
+      targetPort: 6379
+      protocol: TCP

apps/fc-signage-appletv/README.md

@@ -0,0 +1,14 @@
+# fc-signage-appletv
+
+Apple TV signage is a sealed appliance running the `FlowerCore.Signage.Agent.AppleTv` tvOS app per ADR-134.
+
+This ApplicationSet entry is documentation and inventory metadata only. It intentionally creates no `Deployment`, `Service`, or `Pod`.
+
+The Apple TV app connects outbound to existing FC.Signage.Web surfaces:
+
+- `https://signage.iamworkin.lan/hub/signage` for SignalR live status.
+- `GET /api/v1/nodes/{nodeId}/state` for the 30 second polling fallback.
+- `POST /api/v1/nodes/register` and `POST /api/v1/nodes/{nodeId}/enroll` for pairing and mTLS enrollment.
+- `POST /api/v1/nodes/{nodeId}/heartbeat` for metrics, current content identity, and local audit excerpts.
+
+Distribution is via Apple Developer Enterprise Program or TestFlight plus FC.Distribution / UpdateCenter publishing once Apple credentials are available.

apps/fc-signage-appletv/kustomization.yaml

@@ -0,0 +1,5 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - manifest.yaml

apps/fc-signage-appletv/manifest.yaml

@@ -0,0 +1,26 @@
+# Apple TV signage is a sealed tvOS appliance. This ArgoCD app intentionally
+# carries documentation metadata only; no Deployment, Service, or Pod resources
+# are created for the player.
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: fc-signage-appletv-docs
+  namespace: fc-signage
+  labels:
+    app.kubernetes.io/name: fc-signage-appletv
+    app.kubernetes.io/part-of: flowercore-signage
+    flowercore.io/manifest-kind: docs-only
+data:
+  README: |
+    FlowerCore.Signage.Agent.AppleTv is distributed through Apple Developer
+    Enterprise Program or TestFlight, not Kubernetes.
+
+    The app connects outbound to FC.Signage.Web:
+    - SignalR: https://signage.iamworkin.lan/hub/signage
+    - Polling fallback: GET /api/v1/nodes/{nodeId}/state
+    - Enrollment: POST /api/v1/nodes/{nodeId}/enroll
+    - Heartbeat: POST /api/v1/nodes/{nodeId}/heartbeat
+
+    This placeholder gives ArgoCD and inventory dashboards a first-class
+    Apple TV signage app entry without creating runtime pods.

apps/fc-signage-pi-player/README.md

@@ -0,0 +1,17 @@
+# FlowerCore Signage Pi Player
+
+Phase 1 Raspberry Pi signage player packaging for Chromium kiosk deployments.
+This bundle is intentionally air-gap friendly: systemd units, shell scripts,
+udev rules, and Chromium managed policy are all checked into the repo and are
+installed by `FlowerCore.Puppet`.
+
+## Scope
+
+- Bootstrap a stable node identity and mTLS client certificate.
+- Launch Chromium in kiosk mode against `FC.Signage.Web` player routes.
+- Restart the kiosk on HDMI hotplug.
+- Renew mTLS certificates daily when fewer than 30 days remain.
+- Detect display capabilities at boot, daily, and on HDMI hotplug.
+
+Phase 2 native Avalonia rendering is documented separately in Notes and remains
+deferred.

apps/fc-signage-pi-player/chromium-policies/flowercore-signage.json

@@ -0,0 +1,15 @@
+{
+  "AutofillAddressEnabled": false,
+  "AutofillCreditCardEnabled": false,
+  "PasswordManagerEnabled": false,
+  "BrowserSignin": 0,
+  "MetricsReportingEnabled": false,
+  "SafeBrowsingProtectionLevel": 0,
+  "DefaultNotificationsSetting": 2,
+  "DefaultPopupsSetting": 2,
+  "BackgroundModeEnabled": false,
+  "DefaultBrowserSettingEnabled": false,
+  "PromotionalTabsEnabled": false,
+  "CommandLineFlagSecurityWarningsEnabled": false,
+  "ExtensionInstallBlocklist": ["*"]
+}

apps/fc-signage-pi-player/scripts/fc-signage-detect-display

@@ -0,0 +1,132 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+NODE_JSON="/etc/flowercore/signage-node.json"
+CERT_DIR="/etc/fc-signage-player"
+SIGNAGE_URL="${FC_SIGNAGE_URL:-https://signage.iamworkin.lan}"
+NODE_ID=$(jq -r '.nodeId' "$NODE_JSON")
+
+CONNECTORS=()
+for dir in /sys/class/drm/card*-HDMI-A-*; do
+  [[ -e "$dir/status" ]] || continue
+  if [[ "$(cat "$dir/status")" == "connected" ]]; then
+    CONNECTORS+=("$(basename "$dir")")
+  fi
+done
+
+if [[ ${#CONNECTORS[@]} -eq 0 ]]; then
+  CAPABILITIES_JSON=$(jq -n --arg id "$NODE_ID" '{
+    nodeId: $id,
+    platform: "linux-arm64-pi",
+    displayConnected: false,
+    detectedAt: (now | todate),
+    note: "No HDMI display detected"
+  }')
+else
+  PRIMARY="${CONNECTORS[0]}"
+  EDID_PATH="/sys/class/drm/${PRIMARY}/edid"
+  WIDTH=0
+  HEIGHT=0
+  REFRESH=60
+  HDR=false
+  AUDIO_HDMI=false
+  MFG=""
+  MODEL=""
+  PHYSICAL_SIZE=null
+
+  if [[ -s "$EDID_PATH" ]] && command -v edid-decode >/dev/null 2>&1; then
+    EDID_INFO=$(edid-decode < "$EDID_PATH" 2>/dev/null || true)
+    MFG=$(echo "$EDID_INFO" | grep -m1 -oP 'Manufacturer:\s*\K\S+' || true)
+    MODEL=$(echo "$EDID_INFO" | grep -m1 -oP 'Model:\s*\K\S+' || true)
+    PREF=$(echo "$EDID_INFO" | grep -m1 -oP '\d+x\d+\s*@\s*\d+(?:\.\d+)?\s*Hz' || true)
+    if [[ -n "$PREF" ]]; then
+      WIDTH=$(echo "$PREF" | grep -oP '^\d+')
+      HEIGHT=$(echo "$PREF" | grep -oP 'x\K\d+')
+      REFRESH=$(echo "$PREF" | grep -oP '@\s*\K[\d.]+' | cut -d. -f1)
+    fi
+    if echo "$EDID_INFO" | grep -qiE 'HDR (Static|Dynamic) Metadata Block'; then HDR=true; fi
+    if echo "$EDID_INFO" | grep -qiE 'CEA Audio Block|Audio Format Descriptor'; then AUDIO_HDMI=true; fi
+    PH_W=$(echo "$EDID_INFO" | grep -m1 -oP 'Maximum image size:\s*\K\d+\s*cm\s*x\s*\d+' || true)
+    if [[ -n "$PH_W" ]]; then
+      PH_CM_W=$(echo "$PH_W" | grep -oP '^\d+')
+      PH_CM_H=$(echo "$PH_W" | grep -oP 'x\s*\K\d+')
+      if (( PH_CM_W > 0 && PH_CM_H > 0 )); then
+        PHYSICAL_SIZE=$(awk -v w="$PH_CM_W" -v h="$PH_CM_H" 'BEGIN { printf "%.1f", sqrt(w*w + h*h)/2.54 }')
+      fi
+    fi
+  fi
+
+  if [[ "$WIDTH" == "0" ]] && command -v kmsprint >/dev/null 2>&1; then
+    KMS=$(kmsprint 2>/dev/null | grep -A2 "$PRIMARY" | grep -oP '\d+x\d+' | head -1 || true)
+    if [[ -n "$KMS" ]]; then
+      WIDTH=$(echo "$KMS" | grep -oP '^\d+')
+      HEIGHT=$(echo "$KMS" | grep -oP 'x\K\d+')
+    fi
+  fi
+
+  AUDIO_ALSA=false
+  if aplay -l 2>/dev/null | grep -qi 'card.*HDMI'; then AUDIO_ALSA=true; fi
+  HAS_AUDIO=false
+  if [[ "$AUDIO_HDMI" == "true" && "$AUDIO_ALSA" == "true" ]]; then HAS_AUDIO=true; fi
+
+  CAPABILITIES_JSON=$(jq -n \
+    --arg id "$NODE_ID" \
+    --argjson w "$WIDTH" \
+    --argjson h "$HEIGHT" \
+    --argjson r "$REFRESH" \
+    --argjson hdr "$HDR" \
+    --argjson audio "$HAS_AUDIO" \
+    --arg connector "$PRIMARY" \
+    --arg mfg "$MFG" \
+    --arg model "$MODEL" \
+    --argjson size "$PHYSICAL_SIZE" \
+    '{
+      nodeId: $id,
+      platform: "linux-arm64-pi",
+      displayConnected: true,
+      detectedAt: (now | todate),
+      hardware: {
+        maxResolution: { width: $w, height: $h },
+        nativeResolution: { width: $w, height: $h },
+        refreshRateHz: $r,
+        colorDepth: ($hdr | if . then "Color30Hdr" else "Color24" end),
+        hasAudioOutput: $audio,
+        audioChannelCount: ($audio | if . then 2 else 0 end),
+        physicalSizeInches: $size,
+        connector: $connector,
+        manufacturer: $mfg,
+        modelName: $model
+      },
+      render: { codecs: ["h264", "vp9", "mp4"] }
+    }')
+fi
+
+ENDPOINT_CANDIDATES=(
+  "${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/capabilities"
+  "${SIGNAGE_URL}/api/v1/displays/${NODE_ID}/capability-profile"
+)
+
+SUCCESS=false
+for url in "${ENDPOINT_CANDIDATES[@]}"; do
+  HTTP_STATUS=$(curl -sk -o /tmp/cap-response.json -w "%{http_code}" \
+    --max-time 10 \
+    --cert "$CERT_DIR/client.crt" --key "$CERT_DIR/client.key" \
+    -X POST "$url" \
+    -H "Content-Type: application/json" \
+    -d "$CAPABILITIES_JSON" || echo "000")
+  if [[ "$HTTP_STATUS" == "200" || "$HTTP_STATUS" == "201" || "$HTTP_STATUS" == "204" ]]; then
+    SUCCESS=true
+    break
+  fi
+done
+
+mkdir -p /var/log/fc-signage-player
+if [[ "$SUCCESS" != "true" ]]; then
+  echo "[$(date -Is)] capability declare: no endpoint accepted the profile; logging locally" \
+    | tee -a /var/log/fc-signage-player/capabilities.log
+  echo "$CAPABILITIES_JSON" | tee -a /var/log/fc-signage-player/capabilities.log
+else
+  echo "[$(date -Is)] capability declare: ok ($url)" | tee -a /var/log/fc-signage-player/capabilities.log
+fi
+
+echo "$CAPABILITIES_JSON"

apps/fc-signage-pi-player/scripts/flowercore-signage-bootstrap.sh

@@ -0,0 +1,144 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+NODE_JSON="/etc/flowercore/signage-node.json"
+CERT_DIR="/etc/fc-signage-player"
+SIGNAGE_URL="${FC_SIGNAGE_URL:-https://signage.iamworkin.lan}"
+SETUP_CODE_FILE="/etc/flowercore/signage-setup-code"
+
+mkdir -p /etc/flowercore "$CERT_DIR" /var/log/fc-signage-player
+chown fc-signage:fc-signage /etc/flowercore "$CERT_DIR" /var/log/fc-signage-player
+chmod 0750 "$CERT_DIR"
+
+if [[ -s "$NODE_JSON" && -s "$CERT_DIR/client.p12" ]]; then
+  ENROLLED=$(jq -r '.enrolledAt // empty' "$NODE_JSON")
+  if [[ -n "$ENROLLED" ]]; then
+    echo "[$(date -Is)] bootstrap: already enrolled at $ENROLLED; skipping"
+    exit 0
+  fi
+fi
+
+if [[ -s "$NODE_JSON" ]]; then
+  NODE_UUID=$(jq -r '.nodeUuid // empty' "$NODE_JSON")
+  MACHINE_ID=$(jq -r '.machineId // empty' "$NODE_JSON")
+else
+  NODE_UUID=$(uuidgen)
+  MACHINE_ID=$(echo "$NODE_UUID" | tr -d '-' | cut -c1-16)
+  jq -n --arg uuid "$NODE_UUID" --arg machine "$MACHINE_ID" --arg host "$(hostname -f)" --arg ts "$(date -Is)" \
+    '{nodeUuid: $uuid, machineId: $machine, hostname: $host, platform: "linux-arm64-pi", createdAt: $ts}' \
+    > "$NODE_JSON"
+  chmod 0640 "$NODE_JSON"
+  chown fc-signage:fc-signage "$NODE_JSON"
+fi
+
+SETUP_CODE=""
+if [[ -s "$SETUP_CODE_FILE" ]]; then
+  SETUP_CODE=$(tr -d '\r\n\t ' < "$SETUP_CODE_FILE")
+fi
+
+MODEL=$(tr -d '\0' < /sys/firmware/devicetree/base/model 2>/dev/null || echo Unknown)
+REG_PAYLOAD=$(jq -n \
+  --arg machine "$MACHINE_ID" \
+  --arg name "$(hostname -f)" \
+  --arg setup "$SETUP_CODE" \
+  --arg resolution "1920x1080" \
+  --arg model "$MODEL" \
+  '{
+    machineId: $machine,
+    name: $name,
+    setupCode: ($setup | if . == "" then null else . end),
+    resolution: $resolution,
+    hardwareModel: $model,
+    platform: "linux-arm64-pi"
+  }')
+
+for attempt in 1 2; do
+  HTTP_STATUS=$(curl -sk -o /tmp/register-response.json -w "%{http_code}" \
+    --max-time 15 \
+    -X POST "${SIGNAGE_URL}/api/v1/nodes/register" \
+    -H "Content-Type: application/json" \
+    -d "$REG_PAYLOAD" || echo "000")
+  if [[ "$HTTP_STATUS" == "200" || "$HTTP_STATUS" == "201" ]]; then
+    break
+  fi
+  echo "[$(date -Is)] bootstrap: register attempt $attempt returned $HTTP_STATUS" >&2
+  sleep 5
+done
+
+if [[ "$HTTP_STATUS" != "200" && "$HTTP_STATUS" != "201" ]]; then
+  echo "[$(date -Is)] bootstrap: register failed after 2 attempts" >&2
+  exit 2
+fi
+
+NODE_ID=$(jq -r '.nodeId // empty' /tmp/register-response.json)
+if [[ -z "$NODE_ID" ]]; then
+  echo "[$(date -Is)] bootstrap: register response did not include nodeId" >&2
+  exit 2
+fi
+jq --arg id "$NODE_ID" '.nodeId = $id' "$NODE_JSON" > "${NODE_JSON}.tmp" && mv "${NODE_JSON}.tmp" "$NODE_JSON"
+
+if [[ -s "$SETUP_CODE_FILE" ]]; then
+  curl -sk -X POST "${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/approve-via-setup-code" \
+    -H "Content-Type: application/json" \
+    -d "{\"setupCode\":\"${SETUP_CODE}\"}" \
+    -o /dev/null || true
+fi
+
+STATUS=""
+DEADLINE=$(( $(date +%s) + 1800 ))
+while (( $(date +%s) < DEADLINE )); do
+  STATUS=$(curl -sk --max-time 5 "${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/status" | jq -r '.status // empty')
+  if [[ "$STATUS" == "Approved" || "$STATUS" == "Enrolled" || "$STATUS" == "Online" ]]; then
+    break
+  fi
+  sleep 15
+done
+
+if [[ "$STATUS" != "Approved" && "$STATUS" != "Enrolled" && "$STATUS" != "Online" ]]; then
+  echo "[$(date -Is)] bootstrap: approval not granted within 30min budget" >&2
+  exit 3
+fi
+
+KEY_PATH="${CERT_DIR}/client.key"
+CSR_PATH="${CERT_DIR}/client.csr"
+openssl ecparam -genkey -name prime256v1 -out "$KEY_PATH"
+openssl req -new -key "$KEY_PATH" -out "$CSR_PATH" \
+  -subj "/CN=${NODE_ID}/O=FlowerCore/OU=SignagePlayer-Pi"
+
+ENROLL_PAYLOAD=$(jq -n --arg csr "$(cat "$CSR_PATH")" '{certificateSigningRequest: $csr}')
+HTTP_STATUS=$(curl -sk -o /tmp/enroll-response.json -w "%{http_code}" \
+  --max-time 15 \
+  -X POST "${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/enroll" \
+  -H "Content-Type: application/json" \
+  -d "$ENROLL_PAYLOAD")
+
+if [[ "$HTTP_STATUS" != "200" && "$HTTP_STATUS" != "201" ]]; then
+  echo "[$(date -Is)] bootstrap: enroll failed with HTTP $HTTP_STATUS" >&2
+  exit 4
+fi
+
+jq -r '.clientCertificatePem // .signedCertificatePem' /tmp/enroll-response.json > "${CERT_DIR}/client.crt"
+jq -r '.caCertificatePem' /tmp/enroll-response.json > "${CERT_DIR}/ca-chain.pem"
+P12_PASS=$(openssl rand -hex 24)
+echo -n "$P12_PASS" > "${CERT_DIR}/client.p12.pass"
+chmod 0600 "${CERT_DIR}/client.p12.pass"
+
+openssl pkcs12 -export \
+  -inkey "$KEY_PATH" \
+  -in "${CERT_DIR}/client.crt" \
+  -certfile "${CERT_DIR}/ca-chain.pem" \
+  -out "${CERT_DIR}/client.p12" \
+  -password "pass:${P12_PASS}"
+
+chown fc-signage:fc-signage "${CERT_DIR}"/* "$NODE_JSON"
+chmod 0640 "${CERT_DIR}/client.p12" "${CERT_DIR}/client.crt" "${CERT_DIR}/ca-chain.pem" "$KEY_PATH"
+chmod 0600 "${CERT_DIR}/client.p12.pass"
+
+EXPIRY=$(openssl x509 -in "${CERT_DIR}/client.crt" -enddate -noout | sed 's/notAfter=//')
+jq --arg ts "$(date -Is)" --arg exp "$EXPIRY" \
+  '.enrolledAt = $ts | .certExpiry = $exp' "$NODE_JSON" > "${NODE_JSON}.tmp" \
+  && mv "${NODE_JSON}.tmp" "$NODE_JSON"
+
+systemctl start flowercore-signage-detect-display.service || true
+systemctl start flowercore-signage-player-pi.service || true
+echo "[$(date -Is)] bootstrap: enrolled and kiosk started (NodeId=${NODE_ID})"

apps/fc-signage-pi-player/scripts/flowercore-signage-hdmi-respond.sh

@@ -0,0 +1,6 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+sleep 2
+systemctl start flowercore-signage-detect-display.service || true
+systemctl restart flowercore-signage-player-pi.service

apps/fc-signage-pi-player/scripts/flowercore-signage-launch.sh

@@ -0,0 +1,44 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+NODE_JSON="/etc/flowercore/signage-node.json"
+NODE_ID=$(jq -r '.nodeId' "$NODE_JSON")
+SIGNAGE_URL="${FC_SIGNAGE_URL:-https://signage.iamworkin.lan}"
+CERT_DIR="/etc/fc-signage-player"
+
+CERT_THUMB=$(openssl pkcs12 -in "$CERT_DIR/client.p12" -passin file:"$CERT_DIR/client.p12.pass" -nodes -nokeys 2>/dev/null \
+  | openssl x509 -fingerprint -sha256 -noout \
+  | sed 's/.*=//' \
+  | tr -d ':')
+
+PLAYER_URL="${SIGNAGE_URL}/player/${NODE_ID}/embed?token=${CERT_THUMB}"
+HTTP_STATUS=$(curl -sk -o /dev/null -w "%{http_code}" --max-time 5 \
+  --cert-type P12 --cert "$CERT_DIR/client.p12:$(cat "$CERT_DIR/client.p12.pass")" \
+  "$PLAYER_URL" || echo "000")
+
+mkdir -p /var/log/fc-signage-player
+if [[ "$HTTP_STATUS" != "200" && "$HTTP_STATUS" != "301" && "$HTTP_STATUS" != "302" ]]; then
+  echo "[$(date -Is)] /embed returned $HTTP_STATUS; falling back to /player/${NODE_ID}" \
+    >> /var/log/fc-signage-player/url-divergence.log
+  PLAYER_URL="${SIGNAGE_URL}/player/${NODE_ID}?token=${CERT_THUMB}"
+fi
+
+exec chromium-browser \
+  --kiosk \
+  --noerrdialogs \
+  --disable-infobars \
+  --disable-translate \
+  --disable-features=TranslateUI,InfiniteSessionRestore \
+  --autoplay-policy=no-user-gesture-required \
+  --password-store=basic \
+  --user-data-dir=/var/lib/fc-signage-player/profile \
+  --disk-cache-dir=/var/lib/fc-signage-player/cache \
+  --disk-cache-size=104857600 \
+  --no-first-run \
+  --no-default-browser-check \
+  --check-for-update-interval=2592000 \
+  --enable-features=OverlayScrollbar \
+  --start-fullscreen \
+  --window-position=0,0 \
+  --window-size=1920,1080 \
+  "$PLAYER_URL"

apps/fc-signage-pi-player/scripts/flowercore-signage-prelaunch.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+mkdir -p /var/log/fc-signage-player
+
+for f in /etc/flowercore/signage-node.json /etc/fc-signage-player/client.p12 /etc/fc-signage-player/client.p12.pass; do
+  if [[ ! -r "$f" ]]; then
+    echo "[$(date -Is)] prelaunch: missing or unreadable $f" >&2
+    exit 1
+  fi
+done
+
+if openssl pkcs12 -in /etc/fc-signage-player/client.p12 -passin file:/etc/fc-signage-player/client.p12.pass -nokeys -clcerts 2>/dev/null \
+   | openssl x509 -checkend $((7*24*3600)) -noout; then
+  :
+else
+  echo "[$(date -Is)] prelaunch: client cert expires within 7 days" >&2
+fi
+
+echo "[$(date -Is)] prelaunch: ok" | tee -a /var/log/fc-signage-player/prelaunch.log

apps/fc-signage-pi-player/scripts/flowercore-signage-renew-cert.sh

@@ -0,0 +1,46 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+CERT_DIR="/etc/fc-signage-player"
+NODE_JSON="/etc/flowercore/signage-node.json"
+SIGNAGE_URL="${FC_SIGNAGE_URL:-https://signage.iamworkin.lan}"
+
+[[ -s "$CERT_DIR/client.crt" ]] || { echo "no cert to renew"; exit 0; }
+
+if openssl x509 -in "$CERT_DIR/client.crt" -checkend $((30*24*3600)) -noout; then
+  exit 0
+fi
+
+NODE_ID=$(jq -r '.nodeId' "$NODE_JSON")
+NEW_KEY="$CERT_DIR/client.key.new"
+NEW_CSR="$CERT_DIR/client.csr.new"
+
+openssl ecparam -genkey -name prime256v1 -out "$NEW_KEY"
+openssl req -new -key "$NEW_KEY" -out "$NEW_CSR" \
+  -subj "/CN=${NODE_ID}/O=FlowerCore/OU=SignagePlayer-Pi"
+
+HTTP_STATUS=$(curl -sk -o /tmp/renew-response.json -w "%{http_code}" \
+  --cert "$CERT_DIR/client.crt" --key "$CERT_DIR/client.key" \
+  -X POST "${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/renew" \
+  -H "Content-Type: application/json" \
+  -d "$(jq -n --arg csr "$(cat "$NEW_CSR")" '{certificateSigningRequest: $csr}')")
+
+if [[ "$HTTP_STATUS" != "200" && "$HTTP_STATUS" != "201" ]]; then
+  echo "[$(date -Is)] renew: failed HTTP $HTTP_STATUS; leaving old cert in place" >&2
+  exit 5
+fi
+
+jq -r '.clientCertificatePem // .signedCertificatePem' /tmp/renew-response.json > "$CERT_DIR/client.crt.new"
+jq -r '.caCertificatePem' /tmp/renew-response.json > "$CERT_DIR/ca-chain.pem.new"
+P12_PASS=$(cat "$CERT_DIR/client.p12.pass")
+openssl pkcs12 -export -inkey "$NEW_KEY" -in "$CERT_DIR/client.crt.new" \
+  -certfile "$CERT_DIR/ca-chain.pem.new" \
+  -out "$CERT_DIR/client.p12.new" -password "pass:${P12_PASS}"
+
+mv "$CERT_DIR/client.key.new" "$CERT_DIR/client.key"
+mv "$CERT_DIR/client.crt.new" "$CERT_DIR/client.crt"
+mv "$CERT_DIR/ca-chain.pem.new" "$CERT_DIR/ca-chain.pem"
+mv "$CERT_DIR/client.p12.new" "$CERT_DIR/client.p12"
+
+chown fc-signage:fc-signage "$CERT_DIR"/client.*
+systemctl restart flowercore-signage-player-pi.service

apps/fc-signage-pi-player/systemd/99-flowercore-signage-hdmi.rules

@@ -0,0 +1,2 @@
+# Settle DRM for 2s before restarting Chromium, then redeclare capabilities.
+SUBSYSTEM=="drm", KERNEL=="card?-HDMI-A-?", ACTION=="change", RUN+="/usr/bin/systemctl start flowercore-signage-player-pi-hdmi.service"

apps/fc-signage-pi-player/systemd/flowercore-signage-bootstrap.service

@@ -0,0 +1,16 @@
+[Unit]
+Description=FlowerCore Signage Pi: first-boot identity + mTLS enrollment
+Wants=network-online.target
+After=network-online.target
+Before=flowercore-signage-player-pi.service
+
+[Service]
+Type=oneshot
+ExecStart=/usr/local/bin/flowercore-signage-bootstrap.sh
+RemainAfterExit=yes
+StandardOutput=journal
+StandardError=journal
+TimeoutStartSec=2100
+
+[Install]
+WantedBy=multi-user.target

apps/fc-signage-pi-player/systemd/flowercore-signage-detect-display.service

@@ -0,0 +1,8 @@
+[Unit]
+Description=FlowerCore Signage Pi: detect connected display + declare capabilities
+After=flowercore-signage-bootstrap.service
+
+[Service]
+Type=oneshot
+User=fc-signage
+ExecStart=/usr/local/bin/fc-signage-detect-display

apps/fc-signage-pi-player/systemd/flowercore-signage-detect-display.timer

@@ -0,0 +1,11 @@
+[Unit]
+Description=Daily FlowerCore Signage Pi display capability redeclaration
+
+[Timer]
+OnCalendar=daily
+RandomizedDelaySec=1h
+Persistent=true
+OnBootSec=30s
+
+[Install]
+WantedBy=timers.target

apps/fc-signage-pi-player/systemd/flowercore-signage-player-pi-hdmi.service

@@ -0,0 +1,7 @@
+[Unit]
+Description=FlowerCore Signage Pi Player HDMI hotplug responder
+DefaultDependencies=no
+
+[Service]
+Type=oneshot
+ExecStart=/usr/local/bin/flowercore-signage-hdmi-respond.sh

apps/fc-signage-pi-player/systemd/flowercore-signage-player-pi.service

@@ -0,0 +1,30 @@
+[Unit]
+Description=FlowerCore Digital Signage Pi Player (Chromium kiosk)
+Documentation=https://github.com/astoltz/FlowerCore.Notes/blob/master/docs/standards/appletv-pi-signage-agents-design.md
+Wants=network-online.target
+After=network-online.target graphical.target
+ConditionPathExists=/etc/flowercore/signage-node.json
+ConditionPathExists=/etc/fc-signage-player/client.p12
+
+[Service]
+Type=simple
+User=fc-signage
+Group=fc-signage
+WorkingDirectory=/var/lib/fc-signage-player
+EnvironmentFile=-/etc/flowercore/signage-player.env
+ExecStartPre=/usr/local/bin/flowercore-signage-prelaunch.sh
+ExecStart=/usr/local/bin/flowercore-signage-launch.sh
+Restart=always
+RestartSec=10s
+StartLimitBurst=5
+StartLimitIntervalSec=300s
+MemoryMax=2G
+MemoryHigh=1500M
+ProtectSystem=strict
+ProtectHome=true
+ReadWritePaths=/var/lib/fc-signage-player /var/log/fc-signage-player
+PrivateTmp=true
+NoNewPrivileges=true
+
+[Install]
+WantedBy=graphical.target

apps/fc-signage-pi-player/systemd/flowercore-signage-renew.service

@@ -0,0 +1,6 @@
+[Unit]
+Description=FlowerCore Signage Pi: cert renewal worker
+
+[Service]
+Type=oneshot
+ExecStart=/usr/local/bin/flowercore-signage-renew-cert.sh

apps/fc-signage-pi-player/systemd/flowercore-signage-renew.timer

@@ -0,0 +1,10 @@
+[Unit]
+Description=Daily check for FlowerCore Signage Pi cert renewal
+
+[Timer]
+OnCalendar=daily
+RandomizedDelaySec=2h
+Persistent=true
+
+[Install]
+WantedBy=timers.target

apps/fc-signage-pi-player/tests/display_capability.bats

@@ -0,0 +1,22 @@
+#!/usr/bin/env bats
+
+setup() {
+  APP_ROOT="$(cd "$BATS_TEST_DIRNAME/.." && pwd)"
+  DETECT="$APP_ROOT/scripts/fc-signage-detect-display"
+}
+
+@test "display detection emits graceful disconnected profile when no hdmi connector is present" {
+  script="$(cat "$DETECT")"
+  [[ "$script" == *"displayConnected: false"* ]]
+  [[ "$script" == *"No HDMI display detected"* ]]
+}
+
+@test "display detection parses edid, falls back to kmsprint, and logs endpoint failures locally" {
+  script="$(cat "$DETECT")"
+  [[ "$script" == *"edid-decode"* ]]
+  [[ "$script" == *"HDR (Static|Dynamic) Metadata Block"* ]]
+  [[ "$script" == *"kmsprint"* ]]
+  [[ "$script" == *"/api/v1/nodes/\${NODE_ID}/capabilities"* ]]
+  [[ "$script" == *"/api/v1/displays/\${NODE_ID}/capability-profile"* ]]
+  [[ "$script" == *"capabilities.log"* ]]
+}

apps/fc-signage-pi-player/tests/identity_bootstrap.bats

@@ -0,0 +1,64 @@
+#!/usr/bin/env bats
+
+setup() {
+  APP_ROOT="$(cd "$BATS_TEST_DIRNAME/.." && pwd)"
+  BOOTSTRAP="$APP_ROOT/scripts/flowercore-signage-bootstrap.sh"
+  RENEW="$APP_ROOT/scripts/flowercore-signage-renew-cert.sh"
+}
+
+@test "bootstrap is idempotent when node is already enrolled" {
+  script="$(cat "$BOOTSTRAP")"
+  [[ "$script" == *'[[ -s "$NODE_JSON" && -s "$CERT_DIR/client.p12" ]]'* ]]
+  [[ "$script" == *"already enrolled"* ]]
+  [[ "$script" == *"exit 0"* ]]
+}
+
+@test "bootstrap generates a stable node uuid and machine id" {
+  script="$(cat "$BOOTSTRAP")"
+  [[ "$script" == *"uuidgen"* ]]
+  [[ "$script" == *"nodeUuid"* ]]
+  [[ "$script" == *"machineId"* ]]
+  [[ "$script" == *"cut -c1-16"* ]]
+}
+
+@test "bootstrap posts to the canonical register endpoint" {
+  grep -q '/api/v1/nodes/register' "$BOOTSTRAP"
+  grep -q '"linux-arm64-pi"' "$BOOTSTRAP"
+}
+
+@test "bootstrap retries registration once for first-call races" {
+  script="$(cat "$BOOTSTRAP")"
+  [[ "$script" == *"for attempt in 1 2"* ]]
+  [[ "$script" == *"register attempt \$attempt returned"* ]]
+  [[ "$script" == *"sleep 5"* ]]
+}
+
+@test "bootstrap supports setup-code approval with manual polling fallback" {
+  script="$(cat "$BOOTSTRAP")"
+  [[ "$script" == *"signage-setup-code"* ]]
+  [[ "$script" == *"approve-via-setup-code"* ]]
+  [[ "$script" == *"+ 1800"* ]]
+  [[ "$script" == *"sleep 15"* ]]
+}
+
+@test "bootstrap generates an ecdsa p256 csr for the signage pi subject" {
+  script="$(cat "$BOOTSTRAP")"
+  [[ "$script" == *"ecparam -genkey -name prime256v1"* ]]
+  [[ "$script" == *'/CN=${NODE_ID}/O=FlowerCore/OU=SignagePlayer-Pi'* ]]
+}
+
+@test "bootstrap writes pkcs12 bundle with restrictive permissions" {
+  script="$(cat "$BOOTSTRAP")"
+  [[ "$script" == *"openssl pkcs12 -export"* ]]
+  [[ "$script" == *"client.p12.pass"* ]]
+  [[ "$script" == *"chmod 0640"* ]]
+  [[ "$script" == *"chmod 0600"* ]]
+}
+
+@test "renewal only calls renew endpoint inside the thirty-day window and swaps atomically" {
+  script="$(cat "$RENEW")"
+  [[ "$script" == *'-checkend $((30*24*3600))'* ]]
+  [[ "$script" == *"/api/v1/nodes/\${NODE_ID}/renew"* ]]
+  [[ "$script" == *"client.key.new"* ]]
+  [[ "$script" == *'mv "$CERT_DIR/client.p12.new"   "$CERT_DIR/client.p12"'* ]]
+}

apps/fc-signage-pi-player/tests/systemd_kiosk_wrapper.bats

@@ -0,0 +1,68 @@
+#!/usr/bin/env bats
+
+setup() {
+  APP_ROOT="$(cd "$BATS_TEST_DIRNAME/.." && pwd)"
+}
+
+@test "player unit exists" {
+  [ -f "$APP_ROOT/systemd/flowercore-signage-player-pi.service" ]
+}
+
+@test "player unit uses simple chromium service with restart backoff" {
+  unit="$(cat "$APP_ROOT/systemd/flowercore-signage-player-pi.service")"
+  [[ "$unit" == *"Type=simple"* ]]
+  [[ "$unit" == *"Restart=always"* ]]
+  [[ "$unit" == *"RestartSec=10s"* ]]
+  [[ "$unit" == *"StartLimitBurst=5"* ]]
+  [[ "$unit" == *"StartLimitIntervalSec=300s"* ]]
+}
+
+@test "player unit caps chromium memory at two gigabytes" {
+  grep -q '^MemoryMax=2G$' "$APP_ROOT/systemd/flowercore-signage-player-pi.service"
+  grep -q '^MemoryHigh=1500M$' "$APP_ROOT/systemd/flowercore-signage-player-pi.service"
+}
+
+@test "player unit condition-gates startup on identity and p12 certificate" {
+  grep -q '^ConditionPathExists=/etc/flowercore/signage-node.json$' "$APP_ROOT/systemd/flowercore-signage-player-pi.service"
+  grep -q '^ConditionPathExists=/etc/fc-signage-player/client.p12$' "$APP_ROOT/systemd/flowercore-signage-player-pi.service"
+}
+
+@test "player unit runs prelaunch checks before chromium" {
+  grep -q '^ExecStartPre=/usr/local/bin/flowercore-signage-prelaunch.sh$' "$APP_ROOT/systemd/flowercore-signage-player-pi.service"
+  grep -q '^ExecStart=/usr/local/bin/flowercore-signage-launch.sh$' "$APP_ROOT/systemd/flowercore-signage-player-pi.service"
+}
+
+@test "hdmi udev rule routes through the two-second settle service" {
+  rule="$(cat "$APP_ROOT/systemd/99-flowercore-signage-hdmi.rules")"
+  [[ "$rule" == *'KERNEL=="card?-HDMI-A-?"'* ]]
+  [[ "$rule" == *"systemctl start flowercore-signage-player-pi-hdmi.service"* ]]
+  [[ "$rule" != *"systemctl restart flowercore-signage-player-pi.service"* ]]
+}
+
+@test "hdmi responder settles, declares display, then restarts chromium" {
+  responder="$(cat "$APP_ROOT/scripts/flowercore-signage-hdmi-respond.sh")"
+  [[ "$responder" == *"sleep 2"* ]]
+  [[ "$responder" == *"systemctl start flowercore-signage-detect-display.service"* ]]
+  [[ "$responder" == *"systemctl restart flowercore-signage-player-pi.service"* ]]
+}
+
+@test "chromium policy json is valid and disables credential prompts" {
+  command -v jq >/dev/null || skip "jq not installed"
+  jq -e '.AutofillAddressEnabled == false and .AutofillCreditCardEnabled == false and .PasswordManagerEnabled == false' \
+    "$APP_ROOT/chromium-policies/flowercore-signage.json" >/dev/null
+}
+
+@test "launch script tries embed URL and logs bare-player fallback" {
+  launch="$(cat "$APP_ROOT/scripts/flowercore-signage-launch.sh")"
+  [[ "$launch" == *'/player/${NODE_ID}/embed?token=${CERT_THUMB}'* ]]
+  [[ "$launch" == *"url-divergence.log"* ]]
+  [[ "$launch" == *'/player/${NODE_ID}?token=${CERT_THUMB}'* ]]
+}
+
+@test "prelaunch script validates required node and cert files" {
+  prelaunch="$(cat "$APP_ROOT/scripts/flowercore-signage-prelaunch.sh")"
+  [[ "$prelaunch" == *"/etc/flowercore/signage-node.json"* ]]
+  [[ "$prelaunch" == *"/etc/fc-signage-player/client.p12"* ]]
+  [[ "$prelaunch" == *"/etc/fc-signage-player/client.p12.pass"* ]]
+  [[ "$prelaunch" == *"exit 1"* ]]
+}

apps/fc-ttsreader/fc-ttsreader.yaml

@@ -532,7 +532,7 @@ spec:
         fsGroupChangePolicy: OnRootMismatch
       containers:
         - name: web
-          image: localhost/fc-ttsreader-web:v20260506-phase6
+          image: localhost/fc-ttsreader-web:v20260518-sprint36-demo-finish-b132cbf
           imagePullPolicy: Never
           ports:
             - containerPort: 5217
@@ -555,9 +555,13 @@ spec:
             - name: TtsReader__Jobs__Root
               value: "/data/jobs"
             - name: TtsReader__Piper__Host
-              value: "ttsreader-piper.fc-ttsreader.svc.cluster.local."
+              value: "10.0.57.17"
             - name: TtsReader__Piper__Port
-              value: "10200"
+              value: "8500"
+            - name: TtsReader__Piper__Transport
+              value: "http"
+            - name: TtsReader__Piper__HttpPath
+              value: "/tts"
             - name: TtsReader__Kokoro__Enabled
               value: "true"
             - name: TtsReader__Kokoro__BaseUrl

apps/github-runner/.gitattributes

@@ -0,0 +1,2 @@
+*.sh text eol=lf
+Dockerfile text eol=lf

apps/github-runner/Dockerfile

@@ -0,0 +1,44 @@
+FROM myoung34/github-runner:latest
+
+ARG RUBY_VERSION=3.3.11
+ARG RUBY_MINOR=3.3
+ARG RUBY_BUILD_VERSION=v20260326
+ARG RUNNER_UID=1001
+ARG RUNNER_GID=1001
+
+ENV RUNNER_TOOL_CACHE=/home/runner/_tool
+ENV RUNNER_RUBY_TOOLCACHE=/opt/runner-toolcache
+ENV PATH="/home/runner/_tool/Ruby/${RUBY_MINOR}/x64/bin:/opt/runner-toolcache/Ruby/${RUBY_MINOR}/x64/bin:${PATH}"
+
+USER root
+
+RUN apt-get update \
+    && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
+        autoconf \
+        bison \
+        build-essential \
+        ca-certificates \
+        curl \
+        libdb-dev \
+        libffi-dev \
+        libgdbm-dev \
+        libgmp-dev \
+        libncurses-dev \
+        libreadline-dev \
+        libssl-dev \
+        libyaml-dev \
+        patch \
+        pkg-config \
+        uuid-dev \
+        zlib1g-dev \
+    && curl -fsSL "https://github.com/rbenv/ruby-build/archive/refs/tags/${RUBY_BUILD_VERSION}.tar.gz" -o /tmp/ruby-build.tar.gz \
+    && mkdir -p /tmp/ruby-build \
+    && tar -xzf /tmp/ruby-build.tar.gz --strip-components=1 -C /tmp/ruby-build \
+    && /tmp/ruby-build/install.sh \
+    && rm -rf /tmp/ruby-build /tmp/ruby-build.tar.gz /var/lib/apt/lists/*
+
+COPY install-ruby-toolcache.sh /usr/local/bin/install-ruby-toolcache.sh
+
+RUN chmod +x /usr/local/bin/install-ruby-toolcache.sh \
+    && RUBY_VERSION="${RUBY_VERSION}" RUBY_MINOR="${RUBY_MINOR}" TOOLCACHE_ROOT="${RUNNER_RUBY_TOOLCACHE}" RUNNER_UID="${RUNNER_UID}" RUNNER_GID="${RUNNER_GID}" /usr/local/bin/install-ruby-toolcache.sh \
+    && ruby -v

apps/github-runner/README.md

@@ -0,0 +1,121 @@
+# GitHub Runner Fleet
+
+ArgoCD owns `apps/github-runner/github-runner.yaml`. Do not patch live runner
+Deployments with `kubectl`; update this manifest and let ArgoCD reconcile.
+
+## Runner Shape
+
+All repo-scoped Linux runners use:
+
+- `localhost/fc-github-runner:v20260520-ruby3.3.11`, derived from
+  `myoung34/github-runner:latest`
+- `ACCESS_TOKEN` from the `github-runner-token` Secret
+- `RUN_AS_ROOT=false`
+- `EPHEMERAL=true`
+- `LABELS=self-hosted,linux,fc-build-linux`
+- writable non-root paths under `/home/runner` for .NET, NuGet, XDG cache, and
+  Actions tool cache
+- Ruby 3.3.11 seeded into `/home/runner/_tool/Ruby/3.3/x64` from the baked
+  `/opt/runner-toolcache` copy so `ruby/setup-ruby@v1` can discover it on
+  self-hosted `ubuntu-20.04-x64` runners
+
+`github-runner` for `FlowerCore.Common` is single-replica because it retains the
+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.
+
+Sprint 32 final long-tail wave adds 16 two-replica Deployments:
+`FlowerCore.Knowledge`, `FlowerCore.LlmBridge`, `FlowerCore.Media`,
+`FlowerCore.Presentations`, `FlowerCore.RemoteDesktop`, `FlowerCore.DNS`,
+`FlowerCore.Distribution`, `FlowerCore.Scoreboard`,
+`FlowerCore.SegmentDisplay`, `FlowerCore.Signage.Contracts`,
+`FlowerCore.SignalControl`, `FlowerCore.Intranet.Web`,
+`FlowerCore.Provisioning`, `FlowerCore.Redis`, `FlowerCore.MessageBoard`, and
+`FlowerCore.MenuBoard`.
+
+## Image Build
+
+Ruby is baked with a pinned `ruby-build` release and Ruby patch version. The pod
+still mounts an `emptyDir` over `/home/runner`, so the `setup-runner-home` init
+container copies the baked toolcache from `/opt/runner-toolcache/Ruby` into
+`/home/runner/_tool/Ruby` before the runner container starts.
+
+```bash
+cd apps/github-runner
+podman build -t localhost/fc-github-runner:v20260520-ruby3.3.11 .
+podman run --rm localhost/fc-github-runner:v20260520-ruby3.3.11 ruby -v
+podman run --rm localhost/fc-github-runner:v20260520-ruby3.3.11 \
+  test -f /opt/runner-toolcache/Ruby/3.3/x64.complete
+podman save localhost/fc-github-runner:v20260520-ruby3.3.11 \
+  -o fc-github-runner-v20260520-ruby3.3.11.tar
+```
+
+Import the saved image on every schedulable RKE2 node before ArgoCD rolls the
+Deployments:
+
+```bash
+for node in rke2-server rke2-agent1 rke2-agent2; do
+  scp fc-github-runner-v20260520-ruby3.3.11.tar "$node:/tmp/"
+  ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images rm localhost/fc-github-runner:v20260520-ruby3.3.11 || true'
+  ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images import /tmp/fc-github-runner-v20260520-ruby3.3.11.tar'
+done
+```
+
+## Post-Merge Proof
+
+After the PR is merged and ArgoCD syncs, verify the runner fleet:
+
+```bash
+kubectl -n github-runner get deploy,pods,pvc
+```
+
+Verify the Ruby toolcache in a fresh pod:
+
+```bash
+kubectl -n github-runner exec deploy/github-runner-puppet -c runner -- ruby -v
+kubectl -n github-runner exec deploy/github-runner-puppet -c runner -- sh -c \
+  'echo "$RUNNER_TOOL_CACHE" && test -f "$RUNNER_TOOL_CACHE/Ruby/3.3/x64.complete"'
+```
+
+Verify GitHub registration for the repo-scoped runners:
+
+```bash
+for repo in FlowerCore.Common FlowerCore.Shared.Pos FlowerCore.Puppet FlowerCore.Signage \
+            FlowerCore.DMS FlowerCore.Telephony FlowerCore.Print.Web FlowerCore.Chat \
+            FlowerCore.MySQL FlowerCore.Kiosk.Linux FlowerCore.Marquee FlowerCore.TtsReader \
+            FlowerCore.Knowledge FlowerCore.LlmBridge FlowerCore.Media \
+            FlowerCore.Presentations FlowerCore.RemoteDesktop FlowerCore.DNS \
+            FlowerCore.Distribution FlowerCore.Scoreboard FlowerCore.SegmentDisplay \
+            FlowerCore.Signage.Contracts FlowerCore.SignalControl FlowerCore.Intranet.Web \
+            FlowerCore.Provisioning FlowerCore.Redis FlowerCore.MessageBoard \
+            FlowerCore.MenuBoard; do
+  echo "=== $repo ==="
+  gh api "/repos/astoltz/$repo/actions/runners" \
+    --jq '.runners[] | select(.labels[].name == "fc-build-linux") | {name,status,busy,labels:[.labels[].name]}'
+done
+```
+
+Shared.Pos publish proof after the runner pod is online:
+
+```bash
+gh run list --repo astoltz/FlowerCore.Shared.Pos \
+  --workflow "Build, Test & Publish" --branch main --limit 5
+```
+
+If the latest run is still queued after runner registration, rerun the workflow
+from GitHub Actions and verify it lands on an `rke2-linux-*` runner.
+
+## Failure Notes
+
+- `actions/setup-dotnet` permission error at `/usr/share/dotnet`: check that
+  `DOTNET_INSTALL_DIR=/home/runner/.dotnet` and related cache env vars are
+  present on the runner pod.
+- `ruby/setup-ruby@v1` says self-hosted runners must install Ruby in
+  `$RUNNER_TOOL_CACHE`: check that the init container copied
+  `/opt/runner-toolcache/Ruby` into `/home/runner/_tool/Ruby` and that
+  `/home/runner/_tool/Ruby/3.3/x64.complete` exists.
+- `404` during runner registration: the fine-grained PAT is valid but missing
+  repository access for that repo. Add the repo to the PAT access list; the PAT
+  value does not change.
+- `Multi-Attach` volume error: only the Common runner uses a RWO PVC and it must
+  stay single-replica. New multi-replica runners use `emptyDir`.

apps/github-runner/install-ruby-toolcache.sh

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+RUBY_VERSION="${RUBY_VERSION:-3.3.11}"
+RUBY_MINOR="${RUBY_MINOR:-3.3}"
+TOOLCACHE_ROOT="${TOOLCACHE_ROOT:-/opt/runner-toolcache}"
+RUNNER_UID="${RUNNER_UID:-1001}"
+RUNNER_GID="${RUNNER_GID:-1001}"
+RUBY_PREFIX="${TOOLCACHE_ROOT}/Ruby/${RUBY_VERSION}/x64"
+
+mkdir -p "${TOOLCACHE_ROOT}/Ruby"
+RUBY_CONFIGURE_OPTS="${RUBY_CONFIGURE_OPTS:---disable-install-doc --disable-yjit}" ruby-build "${RUBY_VERSION}" "${RUBY_PREFIX}"
+
+touch "${TOOLCACHE_ROOT}/Ruby/${RUBY_VERSION}/x64.complete"
+ln -sfn "${RUBY_VERSION}" "${TOOLCACHE_ROOT}/Ruby/${RUBY_MINOR}"
+
+"${RUBY_PREFIX}/bin/ruby" -v
+chown -R "${RUNNER_UID}:${RUNNER_GID}" "${TOOLCACHE_ROOT}"
+chmod -R a+rX "${TOOLCACHE_ROOT}"

apps/guacamole/guacamole.yaml

@@ -466,11 +466,11 @@ spec:
   itemPath: vaults/IAmWorkin/items/Guacamole JSON Auth
 ---
 ---
-# 1Password-backed credentials for Mac mini VNC access (Phase 1 — 2026-04-28)
+# 1Password-backed credentials for Mac mini VNC access (Phase 1 <EFBFBD> 2026-04-28)
 # The operator mints Secret 'macmini-vnc-creds' with keys: username, password, VNC Password
 # Note: '1Password' field label 'VNC Password' -> K8s Secret key 'VNC Password' (space retained)
 # Guacamole VNC connection password is sourced from the 'VNC Password' field.
-# Actual IP is 10.0.56.115 (INFRA VLAN) — the 1P item 'IP' field is kept as backup reference.
+# Actual IP is 10.0.56.115 (INFRA VLAN) <EFBFBD> the 1P item 'IP' field is kept as backup reference.
 apiVersion: onepassword.com/v1
 kind: OnePasswordItem
 metadata:
@@ -481,6 +481,7 @@ metadata:
     app.kubernetes.io/part-of: flowercore
 spec:
   itemPath: vaults/IAmWorkin/items/Mac Mini
+---
 # Blue Jay Branding Extension (CSS + translations)
 apiVersion: v1
 kind: ConfigMap

apps/kubevirt-vms/ci1.yaml

@@ -1,51 +1,9 @@
 # =============================================================================
-# ci1 — Windows Server 2025 KubeVirt VM (GitHub Actions Self-Hosted Runner)
+# ci1 - Windows Server 2025 KubeVirt VM (GitHub Actions Self-Hosted Runner)
 # =============================================================================
-# Purpose: dedicated CI runner for FlowerCore.Updater Sandbox E2E nightly +
+# Boots from the sysprepped containerDisk template built by the Windows VM
-# future fleet WPF AAT lanes. Replaces the never-registered
+# sysprep pipeline. See docs/infrastructure/windows-vm-sysprep-pipeline.md.
-# `bluejay-ws-sandbox-1` runner placeholder. Andrew explicitly does NOT want
+# Path A/B/C install history is preserved in git log only.
-# BLUEJAY-WS registered as a runner (workstation has personal/operator state).
-#
-# Storage layout (2026-05-08):
-#   * ISO is now sourced from Synology NFS (Path B) — see
-#     win2025-iso-nfs-pv.yaml. The Longhorn Filesystem PVC
-#     `windows-server-2025-iso` below is RETAINED but UNUSED so the prior
-#     CDI upload state is preserved as a fallback (and so ArgoCD doesn't
-#     prune it on this commit). It can be deleted in a follow-up commit
-#     after the NFS path is proven on a successful Windows install.
-#
-# Status (2026-05-08): LIVE — Phase 1 prereqs satisfied:
-#   * Multus CNI v4.2.2 thick-plugin DaemonSet running on all 3 RKE2 nodes
-#     (apps/multus/multus.yaml; ApplicationSet `infra-multus` Synced/Healthy)
-#   * CDI v1.65.0 operator + CR Deployed (apps/cdi/; ApplicationSet
-#     `infra-cdi` Synced/Healthy; uploadproxy reachable via kubectl port-forward)
-#   * Windows Server 2025 ISO uploaded via CDI virtctl image-upload to
-#     PVC windows-server-2025-iso (7.7 GiB → 10Gi PVC, Bound, Upload Complete)
-#   * Local Administrator password generated, stored in 1Password vault
-#     IAmWorkin (qaphopopkryhbg353ukzhhuqoq) item id h3ix4mgfk65gmkcmvh6ly3d3hu
-#   * NetworkAttachmentDefinition prod-vlan57 registered (apps/kubevirt-vms/
-#     prod-vlan57-nad.yaml). VM still uses pod-network masquerade until Phase 1.5
-#     host bridge work lands (Puppet br-prod + enp86s0.57); switching is a
-#     one-line YAML edit + git push.
-#
-# See docs/infrastructure/windows-server-build-runner-plan.md "Phase 1 readiness gate".
-#
-# Network choice in this draft: **pod-network fallback** (Calico default).
-# Outbound-only is fine for the Updater Sandbox E2E runner workload (the runner
-# polls GitHub Actions over HTTPS; no inbound listener needed). Switch to a
-# Multus PROD VLAN NetworkAttachmentDefinition once Multus is installed and the
-# operator wants L2 access from `ci1` to other PROD VLAN services.
-#
-# Sizing: 8 vCPU / 16 GB RAM / 200 GB disk on Longhorn (default storageClass).
-# Capacity check 2026-05-08: each RKE2 node has 16 vCPU / ~64Gi allocatable;
-# 8 vCPU is ~17% of one node's allocatable, fits comfortably.
-#
-# Apply (after operator approval + ISO loaded):
-#   kubectl --kubeconfig $env:USERPROFILE\.kube\rke2.yaml apply -f apps/kubevirt-vms/ci1.yaml
-#
-# Connect to console for Windows install:
-#   virtctl --kubeconfig $env:USERPROFILE\.kube\rke2.yaml vnc ci1 -n kubevirt-vms
-#   (Or via Guacamole once a connection profile is added.)
 # =============================================================================
 
 apiVersion: v1
@@ -57,248 +15,6 @@ metadata:
     pod-security.kubernetes.io/enforce: privileged
 
 ---
-# ISO PVC — populated via CDI virtctl image-upload (CDI is now installed).
-#
-# **Volume mode (2026-05-08 status):** Filesystem-mode PVC. A migration to
-# `volumeMode: Block` via DataVolume was attempted to address an OVMF SATA
-# CDROM read timeout, but CDI v1.65.0's upload-target pod runs as uid 107
-# with `capabilities.drop: [ALL]` and cannot open the underlying block
-# device (`blockdev: cannot open /dev/cdi-block-volume: Permission denied`).
-# Reverted to Filesystem PVC pending one of:
-#   - CDI deployment override granting CAP_SYS_RAWIO to upload pod
-#   - Pre-populated PVC via privileged init pod that dd's the ISO directly
-#   - Migration to a different storage class that exposes block devices
-#     differently (e.g. iSCSI, where Longhorn's CSI mount path may behave
-#     differently)
-#
-# Population workflow (this PVC, Filesystem mode):
-#   1. virtctl --kubeconfig $env:USERPROFILE\.kube\rke2.yaml image-upload pvc \
-#        windows-server-2025-iso -n kubevirt-vms \
-#        --image-path "$env:USERPROFILE\Downloads\en-us_windows_server_2025_updated_march_2026_x64_dvd_8e06425a.iso" \
-#        --size 10Gi --storage-class longhorn --access-mode ReadWriteOnce \
-#        --uploadproxy-url https://localhost:8443 --insecure
-#   (--uploadproxy-url uses port-forward in practice: `kubectl port-forward
-#   -n cdi service/cdi-uploadproxy 8443:443 &` first.)
-#
-# **Open boot issue:** even with the ISO at bootOrder:1, OVMF console showed:
-#   BdsDxe: starting Boot0001 "UEFI QEMU DVD-ROM QM00001 " from ... Sata(...)
-#   BdsDxe: failed to start Boot0001 ... Time out
-# Diagnosis confirmed PVC content IS a valid bootable ISO9660 image — the
-# timeout is in OVMF reading from the SATA-CDROM-backed-by-filesystem-PVC.
-# Block mode would likely fix it; see CDI permission issue above.
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: windows-server-2025-iso
-  namespace: kubevirt-vms
-  labels:
-    app: ci-runner
-    flowercore.io/managed-by: bluejay-infra
-spec:
-  accessModes:
-    - ReadWriteOnce          # Bump to ReadOnlyMany after population for multi-VM use
-  resources:
-    requests:
-      storage: 10Gi          # Server 2025 ISO is 7.7GB; 10Gi for headroom
-  storageClassName: longhorn
-
----
-# Root disk PVC — empty 200Gi volume that Windows installs into.
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: ci1-rootdisk
-  namespace: kubevirt-vms
-spec:
-  accessModes:
-    - ReadWriteOnce
-  resources:
-    requests:
-      storage: 200Gi
-  storageClassName: longhorn
-
----
-# Sysprep ConfigMap — autounattend.xml for hands-off Windows install.
-# Sets local Administrator password (REPLACE the placeholder), enables RDP,
-# enables WinRM, sets hostname, and configures static-ish networking via DHCP.
-# The ISO + VirtIO drivers handle the rest.
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: ci1-autounattend
-  namespace: kubevirt-vms
-data:
-  autounattend.xml: |
-    <?xml version="1.0" encoding="utf-8"?>
-    <unattend xmlns="urn:schemas-microsoft-com:unattend">
-
-      <!-- Pass 1: WindowsPE — Disk setup and VirtIO driver injection -->
-      <settings pass="windowsPE">
-        <component name="Microsoft-Windows-International-Core-WinPE"
-                   processorArchitecture="amd64"
-                   publicKeyToken="31bf3856ad364e35"
-                   language="neutral" versionScope="nonSxS">
-          <SetupUILanguage>
-            <UILanguage>en-US</UILanguage>
-          </SetupUILanguage>
-          <InputLocale>en-US</InputLocale>
-          <SystemLocale>en-US</SystemLocale>
-          <UILanguage>en-US</UILanguage>
-          <UserLocale>en-US</UserLocale>
-        </component>
-
-        <component name="Microsoft-Windows-PnpCustomizationsWinPE"
-                   processorArchitecture="amd64"
-                   publicKeyToken="31bf3856ad364e35"
-                   language="neutral" versionScope="nonSxS">
-          <DriverPaths>
-            <PathAndCredentials wcm:action="add" wcm:keyValue="1">
-              <Path>E:\amd64\2k25</Path>
-            </PathAndCredentials>
-          </DriverPaths>
-        </component>
-
-        <component name="Microsoft-Windows-Setup"
-                   processorArchitecture="amd64"
-                   publicKeyToken="31bf3856ad364e35"
-                   language="neutral" versionScope="nonSxS">
-          <DiskConfiguration>
-            <Disk wcm:action="add">
-              <DiskID>0</DiskID>
-              <WillWipeDisk>true</WillWipeDisk>
-              <CreatePartitions>
-                <CreatePartition wcm:action="add">
-                  <Order>1</Order>
-                  <Size>260</Size>
-                  <Type>EFI</Type>
-                </CreatePartition>
-                <CreatePartition wcm:action="add">
-                  <Order>2</Order>
-                  <Size>128</Size>
-                  <Type>MSR</Type>
-                </CreatePartition>
-                <CreatePartition wcm:action="add">
-                  <Order>3</Order>
-                  <Extend>true</Extend>
-                  <Type>Primary</Type>
-                </CreatePartition>
-              </CreatePartitions>
-              <ModifyPartitions>
-                <ModifyPartition wcm:action="add">
-                  <Order>1</Order>
-                  <PartitionID>1</PartitionID>
-                  <Format>FAT32</Format>
-                  <Label>EFI</Label>
-                </ModifyPartition>
-                <ModifyPartition wcm:action="add">
-                  <Order>2</Order>
-                  <PartitionID>2</PartitionID>
-                </ModifyPartition>
-                <ModifyPartition wcm:action="add">
-                  <Order>3</Order>
-                  <PartitionID>3</PartitionID>
-                  <Format>NTFS</Format>
-                  <Label>Windows</Label>
-                </ModifyPartition>
-              </ModifyPartitions>
-            </Disk>
-          </DiskConfiguration>
-
-          <ImageInstall>
-            <OSImage>
-              <InstallTo>
-                <DiskID>0</DiskID>
-                <PartitionID>3</PartitionID>
-              </InstallTo>
-              <!-- Index 2 = Standard Desktop Experience. Use 4 for Datacenter Desktop. -->
-              <InstallFrom>
-                <MetaData wcm:action="add">
-                  <Key>/IMAGE/INDEX</Key>
-                  <Value>2</Value>
-                </MetaData>
-              </InstallFrom>
-            </OSImage>
-          </ImageInstall>
-
-          <UserData>
-            <AcceptEula>true</AcceptEula>
-            <FullName>FlowerCore CI Runner</FullName>
-            <Organization>FlowerCore</Organization>
-            <!-- Eval install — no product key needed for 180-day evaluation -->
-          </UserData>
-        </component>
-      </settings>
-
-      <!-- Pass 4: Specialize — Hostname, RDP, WinRM -->
-      <settings pass="specialize">
-        <component name="Microsoft-Windows-Shell-Setup"
-                   processorArchitecture="amd64"
-                   publicKeyToken="31bf3856ad364e35"
-                   language="neutral" versionScope="nonSxS">
-          <ComputerName>CI1</ComputerName>
-          <TimeZone>Central Standard Time</TimeZone>
-        </component>
-
-        <component name="Microsoft-Windows-TerminalServices-LocalSessionManager"
-                   processorArchitecture="amd64"
-                   publicKeyToken="31bf3856ad364e35"
-                   language="neutral" versionScope="nonSxS">
-          <fDenyTSConnections>false</fDenyTSConnections>
-        </component>
-      </settings>
-
-      <!-- Pass 7: OOBE — Admin account, RDP firewall, WinRM -->
-      <settings pass="oobeSystem">
-        <component name="Microsoft-Windows-Shell-Setup"
-                   processorArchitecture="amd64"
-                   publicKeyToken="31bf3856ad364e35"
-                   language="neutral" versionScope="nonSxS">
-          <OOBE>
-            <HideEULAPage>true</HideEULAPage>
-            <HideLocalAccountScreen>true</HideLocalAccountScreen>
-            <HideOEMRegistrationScreen>true</HideOEMRegistrationScreen>
-            <HideOnlineAccountScreens>true</HideOnlineAccountScreens>
-            <HideWirelessSetupInOOBE>true</HideWirelessSetupInOOBE>
-            <ProtectYourPC>3</ProtectYourPC>
-          </OOBE>
-          <UserAccounts>
-            <AdministratorPassword>
-              <!-- Real password is in 1Password — vault qaphopopkryhbg353ukzhhuqoq,
-                   item id h3ix4mgfk65gmkcmvh6ly3d3hu, title:
-                   "ci1 Administrator (Windows Server 2025 KubeVirt VM)".
-                   Field "autounattend AdministratorPassword Value (UTF-16-LE base64)"
-                   matches the Value below.
-                   To rotate: regenerate, recompute base64
-                     $combined = $pw + "AdministratorPassword"
-                     [Convert]::ToBase64String([Text.Encoding]::Unicode.GetBytes($combined))
-                   then update both 1P item AND this Value field, recreate VM. -->
-              <Value>bAA3AGsANABOAHcAcgBMAG4AeQBTAHUAYgBBAHQAaQBzAFUAcAB6AEMAWQAhADkAYQBCAEEAZABtAGkAbgBpAHMAdAByAGEAdABvAHIAUABhAHMAcwB3AG8AcgBkAA==</Value>
-              <PlainText>false</PlainText>
-            </AdministratorPassword>
-          </UserAccounts>
-          <FirstLogonCommands>
-            <SynchronousCommand wcm:action="add">
-              <Order>1</Order>
-              <CommandLine>powershell.exe -ExecutionPolicy Bypass -Command "Set-NetFirewallRule -DisplayGroup 'Remote Desktop' -Enabled True"</CommandLine>
-              <Description>Enable RDP firewall rule</Description>
-            </SynchronousCommand>
-            <SynchronousCommand wcm:action="add">
-              <Order>2</Order>
-              <CommandLine>powershell.exe -ExecutionPolicy Bypass -Command "Enable-PSRemoting -Force; Set-Item WSMan:\localhost\Service\Auth\Basic $true; Set-Item WSMan:\localhost\Service\AllowUnencrypted $true"</CommandLine>
-              <Description>Enable WinRM (Phase 2 will pivot to HTTPS via step-ca cert)</Description>
-            </SynchronousCommand>
-            <SynchronousCommand wcm:action="add">
-              <Order>3</Order>
-              <CommandLine>cmd.exe /c reg add "HKLM\SOFTWARE\Microsoft\Windows\CurrentVersion\Policies\System" /v EnableLUA /t REG_DWORD /d 0 /f</CommandLine>
-              <Description>Disable UAC (Phase 2 Puppet will re-evaluate)</Description>
-            </SynchronousCommand>
-          </FirstLogonCommands>
-        </component>
-      </settings>
-    </unattend>
-
----
-# VirtualMachine — Windows Server 2025 CI runner.
 apiVersion: kubevirt.io/v1
 kind: VirtualMachine
 metadata:
@@ -309,33 +25,7 @@ metadata:
     role: github-actions-runner
     flowercore.io/managed-by: bluejay-infra
 spec:
-  # `running: true` is deprecated in favor of `runStrategy`. They are mutually
+  runStrategy: Always
-  # exclusive — KubeVirt's validating webhook rejects any VM that sets both:
-  #   admission webhook "virtualmachine-validator.kubevirt.io" denied the request:
-  #   Running and RunStrategy are mutually exclusive.
-  # `Always` keeps a VMI running and restarts it if it crashes/exits — same
-  # semantics as the old `running: true`.
-  #
-  # **2026-05-08 status: VM cannot start due to a stale QEMU flock on the
-  # rootdisk PVC** (qemu reports `Failed to get "write" lock` on
-  # `/var/run/kubevirt-private/vmi-disks/rootdisk/disk.img`). The flock was
-  # left by a previous QEMU process during a force-deleted launcher pod
-  # cycle. Recovery requires either (a) a Longhorn engine restart on
-  # rke2-agent2, (b) a Longhorn volume detach via the longhorn-manager API
-  # (kubectl patch on `volume.longhorn.io/<pvc-name>` does not work — the
-  # spec.nodeID is reconciled back), or (c) a node reboot of rke2-agent2.
-  #
-  # **Confirmed working:** the bootOrder swap (windows-iso=1, rootdisk=2)
-  # and the runStrategy migration (above). The ISO PVC was successfully
-  # repopulated via virtctl image-upload pvc on the Filesystem-mode PVC.
-  #
-  # **Open: SATA CDROM read timeout** — even with bootOrder=1, OVMF reported
-  # `BdsDxe: failed to start Boot0001 ... Time out` reading the SATA CDROM
-  # backed by the Filesystem-mode PVC. A switch to Block-mode DataVolume
-  # was attempted but blocked by a CDI v1.65.0 upload-pod permission issue
-  # (capability drop prevents writing to the underlying block device).
-  # See header docstring on the ISO PVC.
-  runStrategy: Always   # LIVE — ISO uploaded 2026-05-08, password in 1P
   template:
     metadata:
       labels:
@@ -377,73 +67,16 @@ spec:
         firmware:
           bootloader:
             efi:
-              # 2026-05-08: SecureBoot=false during initial install. With SecureBoot
-              # enabled, OVMF's BdsDxe times out reading Boot0001 from the SCSI
-              # CDROM ("BdsDxe: failed to start Boot0001 ... Time out") before the
-              # EFI bootloader signature can verify against the OVMF VARS trust DB.
-              # KubeVirt's `/usr/share/OVMF/OVMF_VARS.secboot.fd` template doesn't
-              # appear to include the Microsoft KEK/DB by default, so signed
-              # Windows EFI bootloaders fail validation. Disabling SecureBoot lets
-              # OVMF skip the chain check and boot directly. This is acceptable for
-              # a CI runner — TPM 2.0 is still emulated (`tpm: {}` below) so
-              # BitLocker / Hyper-V / WSL still work.
-              # When the operator wants SecureBoot back, the path is:
-              #   1. Custom-build OVMF_VARS.fd with Microsoft KEK/DB enrolled
-              #   2. Mount it into the VM via firmware.bootloader.efi.persistent
-              #   3. Set secureBoot: true again
-              # Tracked separately from the install unblock.
               secureBoot: false
         devices:
-          tpm: {}             # Non-persistent vTPM — sufficient for runner; no BitLocker
+          tpm: {}
           disks:
-            # bootOrder: ISO must be 1 for first-boot install (the rootdisk has no
-            # EFI bootloader yet). After Windows installs, it writes its own UEFI
-            # Boot#### entries pointing at the rootdisk's EFI partition; UEFI then
-            # boots from rootdisk going forward and the ISO at bootOrder:2 acts as
-            # a fallback for re-install scenarios.
-            #
-            # Original (broken) order had rootdisk=1, windows-iso=2 — UEFI tried
-            # the empty virtio disk first, got nothing, fell back to the SATA
-            # CDROM at Boot0001 with a short timeout, and timed out before the
-            # CDROM enumerated. Console showed:
-            #   BdsDxe: failed to start Boot0001 ... Time out
-            #   BdsDxe: No bootable option or device was found.
-            # Confirmed via debug pod: PVC content IS a real bootable ISO9660
-            # (file: "ISO 9660 CD-ROM filesystem data ... (bootable)"), so the
-            # only bug was boot priority.
-            # 2026-05-08 PM: cdrom bus SCSI + containerDisk delivery. This
-            # combination boots qemu cleanly and reaches OVMF, but OVMF
-            # BdsDxe still hits "starting Boot0001 ... Time out" on the
-            # cdrom — see HANDOFF.md / CODEX-STATUS.md "OPEN — ci1" for the
-            # full diagnostic chain. virtio-blk disk swap was attempted as a
-            # workaround but introduced a separate QEMU rootdisk flock issue
-            # without fixing the underlying OVMF cdrom problem; reverted.
-            # Operator decision needed for next architectural step (OVMF
-            # custom build with extended timeout, KubeVirt version bump,
-            # Hyper-V/VirtualBox-and-export, or BIOS legacy boot). The
-            # containerDisk distribution pipeline (build/save/scp/ctr import)
-            # is proven and ready to reuse for any of those.
-            - name: windows-iso
-              bootOrder: 1
-              cdrom:
-                bus: scsi
             - name: rootdisk
-              bootOrder: 2
               disk:
                 bus: virtio
-            - name: virtio-drivers
-              cdrom:
-                bus: sata
-            - name: sysprep
-              cdrom:
-                bus: sata
           interfaces:
-            # Pod-network fallback for Phase 1. To switch to PROD VLAN once Multus
+            # Pod-network fallback for CI runner outbound traffic. Switch to
-            # + the prod-vlan57 NAD exist, replace this block with:
+            # prod-vlan57 once the bridge/NAD lane is ready for L2 access.
-            #   - name: prod-net
-            #     bridge: {}
-            #     model: virtio
-            # and update the networks: stanza to use multus.networkName: kubevirt-vms/prod-vlan57
             - name: default
               masquerade: {}
               model: virtio
@@ -454,55 +87,7 @@ spec:
           pod: {}
       volumes:
         - name: rootdisk
-          persistentVolumeClaim:
-            claimName: ci1-rootdisk
-        - name: windows-iso
-          # 2026-05-08 PM (Path C, CONTAINERDISK): the ISO is now packaged as
-          # a KubeVirt containerDisk OCI image baked from
-          # `FROM scratch ; ADD --chown=107:107 disk.img /disk/disk.img`.
-          # The qemu user (uid 107) reads the ISO directly from a tmpfs view
-          # of the OCI layer, bypassing both:
-          #   - Synology NFS export ACL (Path B failed: uid 107 denied at
-          #     directory level even with mode 0777, see memory
-          #     feedback_synology_iso_export_root_only_uid_107_denied)
-          #   - OVMF cdrom read-window timeout (Path A and Path B's SCSI
-          #     retry both hit `BdsDxe: failed to start Boot0001 ... Time out`
-          #     when the cdrom was backed by a PVC the storage controller
-          #     couldn't satisfy reads from fast enough).
-          #
-          # Image build (one-time, per ISO version):
-          #   1. Copy ISO to disk.img, write Dockerfile
-          #   2. podman build --tag localhost/win-server-2025:1.0 .  (on noc1)
-          #   3. podman save -o win-server-2025-1.0.tar localhost/win-server-2025:1.0
-          #   4. SCP tar to all 3 RKE2 nodes (rke2-server, rke2-agent1, rke2-agent2)
-          #   5. sudo /var/lib/rancher/rke2/bin/ctr -a /run/k3s/containerd/containerd.sock \
-          #        -n k8s.io images import /tmp/win-server-2025-1.0.tar
-          # Standard FC pattern per `feedback_rke2_localhost_imagepullpolicy`.
-          #
-          # When a new Windows ISO version ships, bump the tag (1.1, 1.2, ...),
-          # rebuild + redistribute, and update the image: line below in a new
-          # commit. KubeVirt picks up the new image via a VM restart.
-          #
-          # The legacy NFS PVC + PV (apps/kubevirt-vms/win2025-iso-nfs-pv.yaml)
-          # and CDI Longhorn PVC (`windows-server-2025-iso`) are RETAINED for
-          # this commit so the prior states are recoverable. Once the
-          # containerDisk path proves on a successful Windows install, both
-          # legacy artifacts can be pruned in a follow-up commit.
           containerDisk:
-            image: localhost/win-server-2025:1.0
+            image: localhost/fc-win-server-2025:v1
             imagePullPolicy: Never
-        - name: virtio-drivers
-          containerDisk:
-            # Pinned to v1.8.2 (latest stable as of 2026-05-08).
-            # The :latest tag uses Docker manifest v1 schema which containerd
-            # 2.1 (RKE2 v1.34.5) refuses to pull with:
-            #   "media type application/vnd.docker.distribution.manifest.v1+prettyjws
-            #    is no longer supported since containerd v2.1"
-            # v1.8.2 is rebuilt with manifest v2/OCI and works on containerd 2.1.
-            # Bump available: https://quay.io/repository/kubevirt/virtio-container-disk?tab=tags
-            image: quay.io/kubevirt/virtio-container-disk:v1.8.2
-        - name: sysprep
-          sysprep:
-            configMap:
-              name: ci1-autounattend
       terminationGracePeriodSeconds: 3600

apps/kubevirt-vms/kustomization.yaml

@@ -0,0 +1,3 @@
+resources:
+  - ci1.yaml
+  - prod-vlan57-nad.yaml

apps/monitoring/noc-monitoring.yaml

@@ -75,6 +75,20 @@ data:
               cluster: "rke2"
               role: "agent"
 
+      # Mac mini macOS runner node (INFRA VLAN)
+      - job_name: "macmini-node"
+        scrape_timeout: 15s
+        static_configs:
+          - targets: ["10.0.56.115:9100"]
+            labels:
+              instance: "macmini"
+              host: "macmini.iamworkin.lan"
+              vlan: "infra"
+              arch: "arm64"
+              role: "macos-runner"
+              puppet_managed: "true"
+              puppet_server: "puppet.iamworkin.lan"
+
       # In-cluster node-exporter DaemonSet
       - job_name: "k8s-node-exporter"
         kubernetes_sd_configs:
@@ -266,13 +280,14 @@ data:
               printer_model: "NuPrint 210"
 
       # Print.Web health (Blazor app on edge2:5200)
+      # Target `/health` (anonymous) — root path requires API key auth and returns 401.
       - job_name: "probe-printweb"
         metrics_path: /probe
         params:
           module: [http_2xx]
         scrape_interval: 30s
         static_configs:
-          - targets: ["http://10.0.57.16:5200/"]
+          - targets: ["http://10.0.57.16:5200/health"]
             labels:
               instance: "print-web"
               service: "print-web"
@@ -697,6 +712,36 @@ data:
               summary: "Print.Web Ollama runner held for >10m ({{ $labels.model }})"
               description: "Print.Web reports model {{ $labels.model }} with {{ $value | printf \"%.0f\" }}s of keep-alive remaining. Check concurrent requests before the Pi 5 Ollama lane thrashes."
 
+      - name: macmini-runners
+        rules:
+          - alert: MacMiniRunnerOffline
+            expr: (flowercore_github_runner_online{runner=~"macmini-.*"} == 0) or absent(flowercore_github_runner_online{runner=~"macmini-.*"})
+            for: 10m
+            labels:
+              severity: warning
+              service: github-runner
+            annotations:
+              summary: "Mac mini GitHub runner offline ({{ $labels.runner }})"
+              description: "A macmini-* GitHub Actions runner has not reported online for more than 10 minutes. Puppet manages its LaunchDaemon under /Library/LaunchDaemons/io.flowercore.github-runner-<slug>.plist; runners survive reboot and do not require a GUI session."
+
+      - name: linux-runners
+        rules:
+          - alert: LinuxRunnerOffline
+            expr: |
+              kube_deployment_status_replicas_ready{
+                namespace="github-runner",
+                deployment=~"github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"
+              } == 0
+            for: 5m
+            labels:
+              severity: warning
+              alert_channel: irc
+              service: github-runner
+              team: ci
+            annotations:
+              summary: "Linux CI runner offline: {{ $labels.deployment }}"
+              description: "Deployment {{ $labels.deployment }} in namespace github-runner has 0 ready replicas for more than 5 minutes. CI jobs targeting this repo will queue until the runner pod restarts and re-registers with GitHub. Check pods with: kubectl -n github-runner get pods -l app.kubernetes.io/name={{ $labels.deployment }}. Check logs with: kubectl -n github-runner logs -l app.kubernetes.io/name={{ $labels.deployment }} --tail=50. Common causes: PAT missing repo access, runner CrashLoopBackOff, or node/resource pressure."
+
       - name: remote-desktop
         rules:
           - alert: RemoteDesktopWebDown
@@ -922,6 +967,52 @@ data:
             annotations:
               summary: "Disk usage high on {{ $labels.instance }} ({{ $value | printf \"%.1f\" }}%)"
 
+      # Puppet agent + service alerts.
+      # Mirror of FlowerCore.Notes/scripts/monitoring/alerts.yml `puppet` group
+      # so a future migration to in-cluster Prometheus inherits the ruleset.
+      # Source-of-truth for the live Podman Prometheus on noc1 is the Notes file.
+      # See feedback_monitoring_k8s_target_vs_live_podman.
+      - name: puppet
+        rules:
+          - alert: PuppetAgentReportStale
+            expr: puppet_last_run_age_seconds > 7200
+            for: 30m
+            labels:
+              severity: warning
+              alert_channel: irc
+            annotations:
+              summary: "Puppet agent {{ $labels.instance }} hasn't reported in over 2h"
+              description: "Last run age: {{ $value | humanizeDuration }}. The puppet agent on {{ $labels.instance }} may be stopped, the node may be powered off, or noc1 may be unreachable from this node."
+              runbook: "1. SSH to node (via noc1 jumpbox if needed) 2. sudo systemctl status puppet 3. sudo puppet agent -t --noop to force a run 4. Check r10k: ssh fcadmin@10.0.56.10 'sudo podman logs openvoxserver --tail 50' 5. Verify noc1 reachability: ping puppet.iamworkin.lan"
+
+          - alert: PuppetAgentReportCritical
+            expr: puppet_last_run_age_seconds > 86400
+            for: 1h
+            labels:
+              severity: critical
+              alert_channel: irc
+            annotations:
+              summary: "Puppet agent {{ $labels.instance }} silent for over 24h — node is unmanaged"
+              description: "Last run age: {{ $value | humanizeDuration }}. Node {{ $labels.instance }} has not submitted a Puppet report in over 24 hours. Config drift is accumulating — investigate immediately. If intentional (maintenance), add to the exclusion filter or silence in Grafana."
+              runbook: "URGENT: 1. Check node power state 2. SSH via noc1 jumpbox: ssh fcadmin@10.0.56.10 then ssh <node> 3. sudo systemctl status puppet 4. sudo systemctl start puppet + sudo puppet agent -t 5. Check for network partitions (VLAN connectivity to 10.0.56.10) 6. If node was recently reimaged: sudo puppet agent -t to re-register with new SSL cert"
+
+          # Sprint 33 Cx-7 Phase B (2026-05-25 postmortem follow-up):
+          # Detects puppet.service in failed state — distinct from PuppetAgentReportStale
+          # which catches "agent hasn't run." This catches "systemd gave up restarting it"
+          # (CA-verify loop or other fatal exit). Requires node-exporter systemd collector
+          # enabled with --collector.systemd. If `node_systemd_unit_state` has no series
+          # for a node, the collector is disabled there — flag in postmortem follow-up.
+          - alert: PuppetServiceFailed
+            expr: node_systemd_unit_state{name="puppet.service",state="failed"} == 1
+            for: 5m
+            labels:
+              severity: warning
+              alert_channel: irc
+            annotations:
+              summary: "Puppet service failed on {{ $labels.instance }}"
+              description: "puppet.service on {{ $labels.instance }} has been in failed state for 5+ minutes. systemd has stopped auto-restarting (CA-verify-loop or other exit). Manual `systemctl status puppet` confirms. Run `sudo systemctl start puppet` to recover; investigate journal for root cause."
+              runbook_url: "https://github.com/astoltz/FlowerCore.Notes/blob/master/memory/feedback_puppet_service_dead_after_ca_loop_alert_misreads.md"
+
       # K8s pod-state alerts. Require kube-state-metrics scrape (added
       # 2026-04-26 — see scrape_configs above). Would have surfaced the
       # agent-zero ollama-proxy 172x crash-loop instead of letting it
@@ -1183,24 +1274,55 @@ metadata:
 data:
   notify.py: |
     #!/usr/bin/env python3
-    """HTTP->IRC alert relay with thermal printer forwarding for Grafana webhooks.
+    """HTTP->IRC alert relay with thermal-printer DIGEST forwarding.
-    Listens on :9119, posts to #alerts on UnrealIRCd via raw IRC protocol.
+
-    Alerts tagged alert_channel=thermal_print also POST to Print.Web /api/print/alert.
+    Listens on :9119, posts to #alerts on UnrealIRCd, forwards to Print.Web
+    /api/print/alert. Thermal printing is BATCHED into hourly digests by
+    default so the printer no longer spam-fires per Grafana webhook.
+
+    Routing (per Grafana webhook alert):
+      - IRC: always per-event (operator likes the stream)
+      - Thermal printer:
+          * severity in {critical,disaster,page} OR
+            label alert_channel=thermal_print_immediate -> print NOW
+          * label alert_channel=thermal_print -> enqueue into hourly digest
+          * everything else -> IRC only
+      - RESOLVED webhooks remove the alert from the digest buffer
+
+    Env vars (defaults preserve old behavior on first deploy):
+      THERMAL_PRINT_ENABLED  default "true"   - master kill switch
+      BATCH_INTERVAL_MIN     default "60"     - minutes between digest prints
+      BATCH_MAX_PENDING      default "50"     - force-flush threshold
+
+    HTTP surface:
+      POST /         - Grafana webhook entry
+      POST /flush    - manual digest flush (idempotent)
+      GET  /         - status + config + buffer depth + stats
     """
-    import json, socket, sys, time
+    import json, os, socket, sys, threading, time
+    from collections import defaultdict
+    from datetime import datetime, timezone
     from http.server import HTTPServer, BaseHTTPRequestHandler
     from urllib.request import Request, urlopen
-    from urllib.error import URLError
 
-    IRC_HOST = "unrealircd.irc.svc"  # short name: CoreDNS ndots:5 + iamworkin.lan template hijacks full .cluster.local (see memory)
+    THERMAL_PRINT_ENABLED = os.environ.get("THERMAL_PRINT_ENABLED", "true").lower() == "true"
-    IRC_PORT = 6667
+    BATCH_INTERVAL_MIN    = int(os.environ.get("BATCH_INTERVAL_MIN", "60"))
-    IRC_NICK = "grafana-bot"
+    BATCH_MAX_PENDING     = int(os.environ.get("BATCH_MAX_PENDING", "50"))
-    IRC_CHANNEL = "#alerts"
+
-    PRINT_WEB_URL = "http://10.0.57.16:5200/api/print/alert"
+    IRC_HOST      = os.environ.get("IRC_HOST", "unrealircd.irc.svc")
-    PRINT_ENABLED = True
+    IRC_PORT      = int(os.environ.get("IRC_PORT", "6667"))
+    IRC_NICK      = os.environ.get("IRC_NICK", "grafana-bot")
+    IRC_CHANNEL   = os.environ.get("IRC_CHANNEL", "#alerts")
+    PRINT_WEB_URL = os.environ.get("PRINT_WEB_URL", "http://10.0.57.16:5200/api/print/alert")
+
+    _buffer_lock = threading.Lock()
+    _buffer = {}   # fingerprint -> {"alert": dict, "first_seen": float, "last_seen": float}
+    _last_flush_time = time.time()
+    _stats = {"webhooks_received": 0, "irc_sent": 0, "print_immediate": 0,
+              "digest_flushed": 0, "buffer_dedup": 0, "buffer_added": 0,
+              "buffer_resolved": 0, "started_at": time.time()}
 
     def send_irc(message):
-        """Connect, handle PING, join, send, quit."""
         try:
             sock = socket.create_connection((IRC_HOST, IRC_PORT), timeout=15)
             sock.sendall(f"NICK {IRC_NICK}\r\n".encode())
@@ -1233,52 +1355,137 @@ data:
             time.sleep(0.5)
             sock.sendall(b"QUIT :alert delivered\r\n")
             sock.close()
+            _stats["irc_sent"] += 1
             return True
         except Exception as e:
             print(f"[irc-notify] IRC send failed: {e}", file=sys.stderr)
             return False
 
-    def send_thermal_print(alert):
+    def post_thermal(payload, kind):
-        if not PRINT_ENABLED: return
+        if not THERMAL_PRINT_ENABLED:
-        labels = alert.get("labels", {})
+            print(f"[irc-notify] thermal disabled; skip {kind} ({payload.get('title','?')[:40]})", file=sys.stderr)
-        annotations = alert.get("annotations", {})
+            return False
-        status = alert.get("status", "firing").upper()
-        summary = annotations.get("summary", "")
-        description = annotations.get("description", "")
-        runbook = annotations.get("runbook", "")
-        # Build a useful message: summary + description + runbook steps
-        parts = []
-        if summary: parts.append(summary)
-        if description and description != summary: parts.append(description)
-        if runbook: parts.append("STEPS: " + runbook)
-        message = " | ".join(parts) if parts else labels.get("alertname", "Unknown alert")
-        payload = {
-            "title": labels.get("alertname", "Unknown"),
-            "severity": labels.get("severity", "warning").capitalize(),
-            "host": labels.get("instance", labels.get("host", "unknown")),
-            "message": message,
-            "eventId": alert.get("fingerprint", ""),
-            "source": "Grafana",
-            "status": "RESOLVED" if status == "RESOLVED" else "PROBLEM",
-            "acknowledged": False
-        }
         try:
             req = Request(PRINT_WEB_URL, data=json.dumps(payload).encode("utf-8"),
                           headers={"Content-Type": "application/json"}, method="POST")
             resp = urlopen(req, timeout=10)
-            print(f"[irc-notify] Thermal print sent: {resp.read().decode()}", file=sys.stderr)
+            if kind == "immediate": _stats["print_immediate"] += 1
+            print(f"[irc-notify] thermal {kind} sent: {payload.get('title','?')[:50]}", file=sys.stderr)
+            return True
         except Exception as e:
-            print(f"[irc-notify] Thermal print failed: {e}", file=sys.stderr)
+            print(f"[irc-notify] thermal {kind} failed: {e}", file=sys.stderr)
-
-    def should_print(alert):
-        labels = alert.get("labels", {})
-        if labels.get("alert_channel") == "thermal_print": return True
-        if labels.get("severity", "").lower() in ("critical", "disaster"): return True
-        if alert.get("status", "").upper() == "RESOLVED": return False
             return False
 
+    def fingerprint_of(alert):
+        fp = alert.get("fingerprint", "")
+        if fp: return fp
+        labels = alert.get("labels", {})
+        target = labels.get("pod") or labels.get("instance") or labels.get("deployment") or labels.get("statefulset") or labels.get("namespace") or ""
+        return f"{labels.get('alertname','?')}/{labels.get('namespace','')}/{target}"
+
+    def is_critical(alert):
+        return alert.get("labels", {}).get("severity", "").lower() in ("critical", "disaster", "page")
+
+    def is_immediate_label(alert):
+        return alert.get("labels", {}).get("alert_channel") == "thermal_print_immediate"
+
+    def is_batched_label(alert):
+        return alert.get("labels", {}).get("alert_channel") == "thermal_print"
+
+    def add_to_digest(alert):
+        """Add an alert to the digest buffer. Returns True if the buffer GREW
+        (new fingerprint), False if it was a dedup, resolution, or no-op.
+        """
+        if not THERMAL_PRINT_ENABLED: return False
+        fp = fingerprint_of(alert)
+        status = alert.get("status", "firing").lower()
+        with _buffer_lock:
+            if status == "resolved":
+                if fp in _buffer:
+                    del _buffer[fp]
+                    _stats["buffer_resolved"] += 1
+                return False
+            if fp in _buffer:
+                _buffer[fp]["last_seen"] = time.time()
+                _buffer[fp]["alert"] = alert
+                _stats["buffer_dedup"] += 1
+                return False
+            _buffer[fp] = {"alert": alert, "first_seen": time.time(), "last_seen": time.time()}
+            _stats["buffer_added"] += 1
+            return True
+
+    def build_digest_payload():
+        with _buffer_lock:
+            items = list(_buffer.values())
+        if not items: return None
+        by_name = defaultdict(list)
+        for item in items:
+            labels = item["alert"].get("labels", {})
+            by_name[labels.get("alertname", "Unknown")].append(item)
+        lines = []
+        for name, group in sorted(by_name.items()):
+            targets = []
+            for it in group[:5]:
+                labels = it["alert"].get("labels", {})
+                t = (labels.get("pod") or labels.get("instance") or labels.get("deployment")
+                     or labels.get("statefulset") or labels.get("namespace") or "?")
+                targets.append(t)
+            more = f" (+{len(group)-5})" if len(group) > 5 else ""
+            sevs = sorted({it["alert"].get("labels", {}).get("severity", "warning") for it in group})
+            lines.append(f"[{'/'.join(sevs)}] {name} x{len(group)}: {', '.join(targets)}{more}")
+        now = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M UTC")
+        title = f"Alert digest: {len(items)} firing"
+        body = "\n".join([
+            f"=== {title} ===",
+            f"as of {now}",
+            "",
+            *lines,
+            "",
+            "Stream: #alerts (IRC)  |  Triage: grafana-noc1.iamworkin.lan",
+            "Force-flush: POST irc-notify.monitoring.svc:9119/flush",
+        ])
+        return {"title": title, "severity": "Warning", "host": "monitoring",
+                "message": body, "eventId": f"digest-{int(time.time())}",
+                "source": "Grafana digest", "status": "PROBLEM", "acknowledged": False}
+
+    def flush_digest():
+        payload = build_digest_payload()
+        if payload is None:
+            print("[irc-notify] flush: buffer empty, no digest sent", file=sys.stderr)
+            return False
+        sent = post_thermal(payload, "digest")
+        with _buffer_lock:
+            _buffer.clear()
+        if sent: _stats["digest_flushed"] += 1
+        return sent
+
+    def digest_loop():
+        global _last_flush_time
+        while True:
+            try:
+                now = time.time()
+                elapsed = now - _last_flush_time
+                if elapsed >= BATCH_INTERVAL_MIN * 60:
+                    print(f"[irc-notify] digest tick: interval reached ({BATCH_INTERVAL_MIN}m); buffer={len(_buffer)}", file=sys.stderr)
+                    flush_digest()
+                    _last_flush_time = now
+                elif len(_buffer) >= BATCH_MAX_PENDING:
+                    print(f"[irc-notify] digest tick: buffer full ({len(_buffer)}); force flush", file=sys.stderr)
+                    flush_digest()
+                    _last_flush_time = now
+                time.sleep(15)
+            except Exception as e:
+                print(f"[irc-notify] digest loop error: {e}", file=sys.stderr)
+                time.sleep(60)
+
     class Handler(BaseHTTPRequestHandler):
         def do_POST(self):
+            if self.path == "/flush":
+                ok = flush_digest()
+                self.send_response(200); self.send_header("Content-Type", "application/json"); self.end_headers()
+                self.wfile.write(json.dumps({"flushed": ok, "buffer_after": len(_buffer)}).encode())
+                return
+            _stats["webhooks_received"] += 1
             length = int(self.headers.get("Content-Length", 0))
             body = json.loads(self.rfile.read(length)) if length else {}
             for alert in body.get("alerts", []):
@@ -1293,22 +1500,56 @@ data:
                 msg = f"{icon}{sev_tag} {name}: {summary}"
                 if desc: msg += f"\n  {desc}"
                 send_irc(msg)
-                if should_print(alert): send_thermal_print(alert)
+                # Thermal routing — EVERYTHING (including criticals) goes into
-            self.send_response(200)
+                # the hourly digest. Only the explicit `alert_channel=thermal_print_immediate`
-            self.send_header("Content-Type", "application/json")
+                # label bypasses, and even that flushes-the-current-digest rather
-            self.end_headers()
+                # than printing a standalone job, so the same fingerprint can't
+                # spam the printer per webhook cycle.
+                if status == "RESOLVED":
+                    add_to_digest(alert)  # removes from buffer
+                    continue
+                if is_immediate_label(alert):
+                    # Explicit opt-in for "paper this NOW" — first arrival of a
+                    # new fingerprint triggers an immediate digest flush; repeat
+                    # webhooks for the same fingerprint dedupe in the buffer
+                    # until the next interval or until the alert resolves.
+                    new_in_buffer = add_to_digest(alert)
+                    if new_in_buffer:
+                        global _last_flush_time
+                        flush_digest()
+                        _last_flush_time = time.time()
+                elif is_critical(alert) or is_batched_label(alert):
+                    add_to_digest(alert)
+                # else: IRC-only (warnings without thermal_print label)
+            self.send_response(200); self.send_header("Content-Type", "application/json"); self.end_headers()
             self.wfile.write(b'{"status":"ok"}')
+
         def do_GET(self):
-            self.send_response(200)
+            self.send_response(200); self.send_header("Content-Type", "application/json"); self.end_headers()
-            self.send_header("Content-Type", "application/json")
+            with _buffer_lock:
-            self.end_headers()
+                alertnames = sorted({it["alert"].get("labels", {}).get("alertname", "?") for it in _buffer.values()})
-            self.wfile.write(json.dumps({"service":"irc-notify","thermal_print":PRINT_ENABLED}).encode())
+                depth = len(_buffer)
+            info = {
+                "service": "irc-notify",
+                "config": {"thermal_print_enabled": THERMAL_PRINT_ENABLED,
+                           "batch_interval_min": BATCH_INTERVAL_MIN,
+                           "batch_max_pending": BATCH_MAX_PENDING,
+                           "irc_target": f"{IRC_HOST}:{IRC_PORT} {IRC_CHANNEL}",
+                           "print_web_url": PRINT_WEB_URL},
+                "buffer": {"depth": depth, "alertnames": alertnames,
+                           "seconds_since_last_flush": int(time.time() - _last_flush_time),
+                           "seconds_until_next_flush": max(0, int(BATCH_INTERVAL_MIN*60 - (time.time() - _last_flush_time)))},
+                "stats": _stats,
+            }
+            self.wfile.write(json.dumps(info, indent=2).encode())
+
         def log_message(self, format, *args):
             print(f"[irc-notify] {args[0]}", file=sys.stderr)
 
     if __name__ == "__main__":
+        threading.Thread(target=digest_loop, daemon=True).start()
         server = HTTPServer(("0.0.0.0", 9119), Handler)
-        print(f"IRC alert relay :9119 -> {IRC_HOST}:{IRC_PORT} {IRC_CHANNEL} (thermal: {PRINT_ENABLED})")
+        print(f"[irc-notify] :9119 -> IRC {IRC_HOST}:{IRC_PORT} {IRC_CHANNEL} | thermal={'ON' if THERMAL_PRINT_ENABLED else 'OFF'} | digest={BATCH_INTERVAL_MIN}m max={BATCH_MAX_PENDING}", file=sys.stderr)
         server.serve_forever()
 
 # =============================================================================
@@ -3395,6 +3636,39 @@ data:
                 relativeTimeRange: {from: 120, to: 0}
                 datasourceUid: __expr__
                 model: {type: threshold, expression: B, conditions: [{evaluator: {params: [600], type: gt}}], refId: C}
+      - orgId: 1
+        name: CI Runners
+        folder: CI Alerts
+        interval: 1m
+        rules:
+          - uid: linux-runner-offline
+            title: LinuxRunnerOffline
+            condition: C
+            for: 5m
+            noDataState: OK
+            execErrState: Error
+            annotations:
+              summary: "Linux CI runner offline: {{ $labels.deployment }}"
+              description: "A github-runner namespace Deployment has 0 ready replicas for more than 5 minutes. CI jobs targeting that repo will queue until the runner pod restarts and re-registers."
+              runbook: "1. kubectl -n github-runner get pods -l app.kubernetes.io/name={{ $labels.deployment }} 2. kubectl -n github-runner logs -l app.kubernetes.io/name={{ $labels.deployment }} --tail=50 3. Verify PAT repo access if registration returns 404 4. Verify no RWO PVC is shared by scaled runners"
+            labels:
+              severity: warning
+              service: github-runner
+              alert_channel: irc
+              team: ci
+            data:
+              - refId: A
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: prometheus
+                model: {expr: 'kube_deployment_status_replicas_ready{namespace="github-runner",deployment=~"github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"} == 0', instant: true, refId: A}
+              - refId: B
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: __expr__
+                model: {type: reduce, expression: A, reducer: last, refId: B}
+              - refId: C
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: __expr__
+                model: {type: threshold, expression: B, conditions: [{evaluator: {params: [0], type: gt}}], refId: C}
       - orgId: 1
         name: Infrastructure
         folder: AI Stack Alerts
@@ -3427,6 +3701,32 @@ data:
                 relativeTimeRange: {from: 120, to: 0}
                 datasourceUid: __expr__
                 model: {type: threshold, expression: B, conditions: [{evaluator: {params: [1], type: lt}}], refId: C}
+          - uid: macmini-runner-offline
+            title: MacMiniRunnerOffline
+            condition: C
+            for: 10m
+            noDataState: Alerting
+            execErrState: OK
+            annotations:
+              summary: Mac mini GitHub runner offline
+              description: "One or more macmini-* GitHub Actions runners have not reported online for more than 10 minutes. LaunchDaemons survive reboot and do not require the bluejay GUI session."
+              runbook: "1. ssh fcadmin@macmini.iamworkin.lan 2. launchctl print system/io.flowercore.github-runner-<slug> 3. Check /Users/fcadmin/Library/Logs/github-runners/<slug>/stderr.log 4. Re-register the repo runner if .runner is missing"
+            labels:
+              severity: warning
+              service: github-runner
+            data:
+              - refId: A
+                relativeTimeRange: {from: 600, to: 0}
+                datasourceUid: prometheus
+                model: {expr: 'min(flowercore_github_runner_online{runner=~"macmini-.*"} or vector(0))', instant: true, refId: A}
+              - refId: B
+                relativeTimeRange: {from: 600, to: 0}
+                datasourceUid: __expr__
+                model: {type: reduce, expression: A, reducer: last, refId: B}
+              - refId: C
+                relativeTimeRange: {from: 600, to: 0}
+                datasourceUid: __expr__
+                model: {type: threshold, expression: B, conditions: [{evaluator: {params: [1], type: lt}}], refId: C}
           - uid: high-cpu
             title: High CPU (>85%)
             condition: C

apps/worldbuilder/README.md

@@ -28,9 +28,12 @@ Source: `D:\git\FlowerCore\FlowerCore.WorldBuilder` (master)
    Memory: `feedback_rke2_image_import_per_node_scp`.
 3. **Bump image tag** in `worldbuilder.yaml` and git push.
    ArgoCD ApplicationSet picks up within ~3 minutes.
-4. **First production render** — open `https://worldbuilder.iamworkin.lan`,
+4. **First production render** — open
-   create World → Character → Storyboard → ExportJob, confirm artifact
+   `https://worldbuilder.iamworkin.lan/studio/c32e0000-0000-4000-8000-000000000004`
-   downloads. ComfyUI lives on BLUEJAY-WS at `http://10.0.56.20:8188`.
+   and confirm the Cyberpunk Blue Jay demo prompt loads with five seeded fake
+   generated images. This Sprint 32 visitor-safe profile uses
+   `ClientMode=fake`; switch the image-generation env vars back to ComfyUI only
+   for an operator-owned GPU render lane.
 
 ## Health probes
 
@@ -53,8 +56,13 @@ Source: `D:\git\FlowerCore\FlowerCore.WorldBuilder` (master)
 
 ## Image generation backend
 
-`FlowerCore:WorldBuilder:ImageGeneration:BaseUrl=http://10.0.56.20:8188` —
+Sprint 32 pins the Kubernetes profile to
-ComfyUI runs on BLUEJAY-WS Windows (R9700 / gfx1201 / ROCm 7.2.1). Pod reaches
+`FlowerCore:WorldBuilder:ImageGeneration:ClientMode=fake` with
-the workstation directly across the 10.0.56.0/24 VLAN (no Podman-style host-
+`BaseUrl=http://127.0.0.1:1`. That keeps the public/internal visitor demo
-filter issues — K8s pods route via Calico, which is L3-routed across the
+deterministic, avoids GPU exposure, and still exercises the studio/gallery
-VLAN).
+surface with persisted generated-image metadata.
+
+The previous ComfyUI backend target was `http://10.0.56.20:8188` on
+BLUEJAY-WS (R9700 / gfx1201 / ROCm 7.2.1). Re-enable it only in an
+operator-owned follow-up that also verifies workstation reachability and image
+import freshness.

apps/worldbuilder/worldbuilder.yaml

@@ -16,7 +16,11 @@ kind: Namespace
 metadata:
   name: fc-worldbuilder
   labels:
+    app.kubernetes.io/name: fc-worldbuilder
     app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
 ---
 # SQLite DB + generated image gallery + PDF/PNG exports.
 # Longhorn RWO — single replica with `Recreate` rollout strategy keeps it safe.
@@ -25,6 +29,13 @@ kind: PersistentVolumeClaim
 metadata:
   name: worldbuilder-data
   namespace: fc-worldbuilder
+  labels:
+    app.kubernetes.io/name: worldbuilder-data
+    app.kubernetes.io/component: storage
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
 spec:
   accessModes:
     - ReadWriteOnce
@@ -40,7 +51,13 @@ metadata:
   namespace: fc-worldbuilder
   labels:
     app.kubernetes.io/name: worldbuilder-web
+    app.kubernetes.io/component: web
     app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
+  annotations:
+    flowercore.io/traceability-standard: k8s-pod-ownership-and-traceability-standard
 spec:
   replicas: 1
   revisionHistoryLimit: 3
@@ -54,11 +71,16 @@ spec:
     metadata:
       labels:
         app.kubernetes.io/name: worldbuilder-web
+        app.kubernetes.io/component: web
         app.kubernetes.io/part-of: flowercore
+        app.kubernetes.io/managed-by: argocd
+        flowercore.io/tenant-id: system
+        flowercore.io/created-by: bluejay-infra
       annotations:
         prometheus.io/scrape: "true"
         prometheus.io/port: "8080"
         prometheus.io/path: "/metrics/prometheus"
+        flowercore.io/audit-trace-id: "worldbuilder-runtime-demo"
     spec:
       securityContext:
         fsGroup: 1654
@@ -92,11 +114,14 @@ spec:
               value: "/data/gallery"
             - name: FlowerCore__WorldBuilder__Export__RootPath
               value: "/data/exports"
-            # ComfyUI on BLUEJAY-WS (R9700 / gfx1201 / ROCm 7.2.1).
+            # Visitor-safe Sprint 32 profile: fake backend keeps public demo
+            # rendering deterministic and avoids exposing BLUEJAY-WS GPU.
             - name: FlowerCore__WorldBuilder__ImageGeneration__BaseUrl
-              value: "http://10.0.56.20:8188"
+              value: "http://127.0.0.1:1"
             - name: FlowerCore__WorldBuilder__ImageGeneration__ClientMode
-              value: "comfyui"
+              value: "fake"
+            - name: FlowerCore__WorldBuilder__ImageGeneration__BackendId
+              value: "fake"
           resources:
             # Cluster CPU-request budget runs hot (99% on all 3 nodes at deploy
             # time) while actual CPU usage is well below capacity. Idle Blazor
@@ -165,7 +190,11 @@ metadata:
   namespace: fc-worldbuilder
   labels:
     app.kubernetes.io/name: worldbuilder-web
+    app.kubernetes.io/component: web
     app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
 spec:
   type: ClusterIP
   selector:
@@ -180,6 +209,13 @@ kind: Certificate
 metadata:
   name: worldbuilder-web-tls
   namespace: fc-worldbuilder
+  labels:
+    app.kubernetes.io/name: worldbuilder-web-tls
+    app.kubernetes.io/component: ingress
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
 spec:
   secretName: worldbuilder-web-tls
   issuerRef:
@@ -200,6 +236,13 @@ kind: IngressRoute
 metadata:
   name: worldbuilder-web
   namespace: fc-worldbuilder
+  labels:
+    app.kubernetes.io/name: worldbuilder-web
+    app.kubernetes.io/component: ingress
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
 spec:
   entryPoints:
     - websecure

apps/zabbix/zabbix.yaml

@@ -305,15 +305,17 @@ spec:
               path: /
               port: 8080
             initialDelaySeconds: 60
-            timeoutSeconds: 5
+            timeoutSeconds: 15
             periodSeconds: 10
+            failureThreshold: 3
           readinessProbe:
             httpGet:
               path: /
               port: 8080
             initialDelaySeconds: 30
             periodSeconds: 5
-            timeoutSeconds: 5
+            timeoutSeconds: 15
+            failureThreshold: 3
 ---
 apiVersion: v1
 kind: Service

docs/runbooks/openvoxserver-quadlet-durability.md

@@ -0,0 +1,84 @@
+# openvoxserver Quadlet Durability
+
+This runbook documents the noc1 `openvoxserver` durability fix for the Puppet control-repo deploy path. The service is a noc1 host artifact, not an ArgoCD application, so discovery always starts on noc1 rather than in `apps/*`.
+
+## Current State
+
+As of the Sprint 32 Cx-12 apply on 2026-05-17:
+
+- `/etc/containers/systemd/openvoxserver.container` has a `GIT_SSH_COMMAND` environment entry that points at the persisted serverdata deploy key.
+- `/etc/systemd/system/openvoxserver-safeconfig.service` is enabled and active, and reapplies `git config --global --add safe.directory *` inside the running container.
+- `/opt/puppet/r10k-deploy.sh` self-heals before each fetch by setting `safe.directory`, the repo-local `core.sshCommand`, and the persisted `known_hosts` file when needed.
+- `puppet-deploy.service` exits `0/SUCCESS` after the apply and the control repo reports `HEAD == origin/master`.
+- `systemctl cat openvoxserver` does not currently resolve to a generated unit on noc1. The container is running through Podman with `restart=always`, so destructive recreate smoke must not run until the generated unit is present.
+
+## Discovery
+
+Run every command through noc1 as `fcadmin`; do not assume BLUEJAY-WS can reach container-local surfaces directly.
+
+```bash
+ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "hostname && sudo -n true"
+ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo find /etc/containers/systemd /usr/share/containers/systemd /etc/systemd/system -name 'openvoxserver*' 2>/dev/null"
+ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo sed -n '1,220p' /etc/containers/systemd/openvoxserver.container"
+ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo systemctl cat puppet-deploy.service"
+```
+
+If a future noc1 profile manages these files, update the Puppet control repo and let `puppet-deploy.service` apply the change. On 2026-05-17, host `puppet` was not installed, so Cx-12 used a direct noc1 host edit.
+
+## Durable Fix Shape
+
+The Quadlet keeps the deploy key as a path reference only:
+
+```ini
+Environment=GIT_SSH_COMMAND=ssh -i /opt/puppetlabs/server/data/puppetserver/.puppet-deploy-key -o StrictHostKeyChecking=yes -o IdentitiesOnly=yes -o UserKnownHostsFile=/opt/puppetlabs/server/data/puppetserver/.known_hosts
+```
+
+The safeconfig service is intentionally independent of `openvoxserver.service` until the generated unit exists. It waits for the `openvoxserver` container name and then runs:
+
+```bash
+/usr/bin/podman exec openvoxserver git config --global --add safe.directory *
+```
+
+The deploy script self-heals inside the container before it fetches the control repo:
+
+```bash
+git config --global --add safe.directory "*" 2>/dev/null || true
+DEPLOY_KEY="/opt/puppetlabs/server/data/puppetserver/.puppet-deploy-key"
+KNOWN_HOSTS="/opt/puppetlabs/server/data/puppetserver/.known_hosts"
+REPO="/etc/puppetlabs/code/environments/production"
+export GIT_SSH_COMMAND="ssh -i $DEPLOY_KEY -o StrictHostKeyChecking=yes -o IdentitiesOnly=yes -o UserKnownHostsFile=$KNOWN_HOSTS"
+git -C "$REPO" config core.sshCommand "$GIT_SSH_COMMAND" 2>/dev/null || true
+```
+
+## Validation
+
+Non-destructive validation:
+
+```bash
+ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo grep -n 'GIT_SSH_COMMAND' /etc/containers/systemd/openvoxserver.container"
+ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo systemctl status openvoxserver-safeconfig.service --no-pager -l"
+ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo systemctl start puppet-deploy.service && sudo systemctl status puppet-deploy.service --no-pager -l"
+ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo podman exec openvoxserver git -C /etc/puppetlabs/code/environments/production config --get core.sshCommand"
+```
+
+Destructive recreate smoke is opt-in only:
+
+```bash
+scp scripts/monitoring/openvox-recreate-smoke.sh fcadmin@10.0.56.10:/tmp/openvox-recreate-smoke.sh
+ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "chmod +x /tmp/openvox-recreate-smoke.sh && sudo OPENVOX_RECREATE_SMOKE=1 /tmp/openvox-recreate-smoke.sh"
+```
+
+Do not run the smoke during normal sprint work. It stops and removes the production container before starting it again through systemd, and it now refuses to continue unless `systemctl cat openvoxserver` succeeds.
+
+## Credential Rotation Note
+
+When rotating the Puppet deploy key, update the persisted serverdata copy on noc1:
+
+```bash
+sudo install -m 0600 -o root -g root <new-deploy-key> /opt/puppet/serverdata/.puppet-deploy-key
+sudo podman exec openvoxserver sh -c "ssh-keyscan github.com > /opt/puppetlabs/server/data/puppetserver/.known_hosts"
+sudo systemctl start openvoxserver-safeconfig.service
+sudo systemctl start puppet-deploy.service
+```
+
+Never commit the deploy key or print it in logs.

scripts/monitoring/openvox-recreate-smoke.sh

@@ -0,0 +1,48 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+if [ "${OPENVOX_RECREATE_SMOKE:-}" != "1" ]; then
+  echo "SKIP: set OPENVOX_RECREATE_SMOKE=1 to run the destructive openvoxserver recreate smoke." >&2
+  exit 64
+fi
+
+SUDO="${SUDO:-sudo}"
+REPO="/etc/puppetlabs/code/environments/production"
+CORE_SSH_COMMAND_FRAGMENT=".puppet-deploy-key"
+
+if ! $SUDO systemctl cat openvoxserver >/dev/null 2>&1; then
+  echo "SKIP: systemctl cat openvoxserver failed; refusing to remove a container without a verified systemd recreate path." >&2
+  exit 65
+fi
+
+before="$($SUDO podman exec openvoxserver git -C "$REPO" rev-parse --short HEAD)"
+echo "Before recreate: $before"
+
+$SUDO systemctl stop openvoxserver
+$SUDO podman rm openvoxserver 2>/dev/null || true
+$SUDO systemctl start openvoxserver
+
+sleep 50
+
+$SUDO systemctl start puppet-deploy.service
+sleep 5
+
+$SUDO systemctl status puppet-deploy.service --no-pager -l
+
+after="$($SUDO podman exec openvoxserver git -C "$REPO" rev-parse --short origin/master)"
+echo "After recreate origin/master: $after"
+
+$SUDO test -d /opt/puppet/code/environments/production/site-modules/profile/manifests
+
+core_ssh="$($SUDO podman exec openvoxserver git -C "$REPO" config --get core.sshCommand)"
+case "$core_ssh" in
+  *"$CORE_SSH_COMMAND_FRAGMENT"*) ;;
+  *)
+    echo "FAIL: core.sshCommand does not reference the persisted deploy key." >&2
+    exit 1
+    ;;
+esac
+
+$SUDO podman exec openvoxserver git -C "$REPO" status --short --branch
+
+echo "PASS: openvoxserver recreate smoke completed without git safety or deploy-key failure."

tests/bluejay-infra-lint/FleetManifestLintTests.cs

@@ -13,6 +13,7 @@ public sealed class FleetManifestLintTests
 
     private static readonly HashSet<string> PublicReadOnlyHosts = new(StringComparer.Ordinal)
     {
+        "brochure.flowercore.io",
         "dist.flowercore.io",
         "dns.iamworkin.lan",
     };
@@ -54,6 +55,43 @@ public sealed class FleetManifestLintTests
         "ttsreader-piper",
     };
 
+    private static readonly IReadOnlyDictionary<string, string> LinuxRunnerRepos = new Dictionary<string, string>(StringComparer.Ordinal)
+    {
+        ["github-runner"] = "https://github.com/astoltz/FlowerCore.Common",
+        ["github-runner-sharedpos"] = "https://github.com/astoltz/FlowerCore.Shared.Pos",
+        ["github-runner-puppet"] = "https://github.com/astoltz/FlowerCore.Puppet",
+        ["github-runner-signage"] = "https://github.com/astoltz/FlowerCore.Signage",
+        ["github-runner-dms"] = "https://github.com/astoltz/FlowerCore.DMS",
+        ["github-runner-telephony"] = "https://github.com/astoltz/FlowerCore.Telephony",
+        ["github-runner-print-web"] = "https://github.com/astoltz/FlowerCore.Print.Web",
+        ["github-runner-chat"] = "https://github.com/astoltz/FlowerCore.Chat",
+        ["github-runner-mysql"] = "https://github.com/astoltz/FlowerCore.MySQL",
+        ["github-runner-kiosk-linux"] = "https://github.com/astoltz/FlowerCore.Kiosk.Linux",
+    };
+
+    private static readonly HashSet<string> ScaledLinuxRunnerDeployments = new(StringComparer.Ordinal)
+    {
+        "github-runner-sharedpos",
+        "github-runner-puppet",
+        "github-runner-signage",
+        "github-runner-dms",
+        "github-runner-telephony",
+        "github-runner-print-web",
+        "github-runner-chat",
+        "github-runner-mysql",
+        "github-runner-kiosk-linux",
+    };
+
+    private static readonly IReadOnlyDictionary<string, string> WritableRunnerEnv = new Dictionary<string, string>(StringComparer.Ordinal)
+    {
+        ["HOME"] = "/home/runner",
+        ["DOTNET_INSTALL_DIR"] = "/home/runner/.dotnet",
+        ["DOTNET_CLI_HOME"] = "/home/runner",
+        ["NUGET_PACKAGES"] = "/home/runner/.nuget/packages",
+        ["XDG_CACHE_HOME"] = "/home/runner/.cache",
+        ["RUNNER_TOOL_CACHE"] = "/home/runner/_tool",
+    };
+
     [Fact]
     public void IngressRoutes_MustKeepServiceReferencesInTheSameNamespace()
     {
@@ -187,6 +225,98 @@ public sealed class FleetManifestLintTests
         violations.Should().BeEmpty();
     }
 
+    [Fact]
+    public void GitHubRunnerFleet_MustRegisterRequiredReposAsRepoScopedDeployments()
+    {
+        var deployments = GitHubRunnerDeployments();
+
+        foreach (var expectedRunner in LinuxRunnerRepos)
+        {
+            deployments.Should().ContainKey(expectedRunner.Key);
+
+            var container = deployments[expectedRunner.Key].ContainerMappings().Should().ContainSingle().Subject;
+            EnvValue(container, "REPO_URL").Should().Be(expectedRunner.Value);
+            EnvValue(container, "EPHEMERAL").Should().Be("true");
+            EnvValue(container, "LABELS").Should().Be("self-hosted,linux,fc-build-linux");
+            EnvValue(container, "RUN_AS_ROOT").Should().Be("false");
+            EnvValue(container, "ACCESS_TOKEN").Should().BeNull("ACCESS_TOKEN must come from github-runner-token Secret, not a literal");
+            EnvSecretName(container, "ACCESS_TOKEN").Should().Be("github-runner-token");
+            EnvSecretKey(container, "ACCESS_TOKEN").Should().Be("credential");
+        }
+    }
+
+    [Fact]
+    public void GitHubRunnerFleet_MustSetWritableNonRootDotnetAndCachePaths()
+    {
+        foreach (var deployment in GitHubRunnerDeployments().Values)
+        {
+            var container = deployment.ContainerMappings().Should().ContainSingle().Subject;
+
+            foreach (var expectedEnv in WritableRunnerEnv)
+            {
+                EnvValue(container, expectedEnv.Key).Should().Be(expectedEnv.Value, $"{deployment.Name} must keep .NET paths writable for uid 1001");
+            }
+
+            var mounts = ManifestNodeExtensions.MappingSequence(container, "volumeMounts")
+                .ToDictionary(
+                    mount => ManifestNodeExtensions.Scalar(mount, "name") ?? string.Empty,
+                    mount => ManifestNodeExtensions.Scalar(mount, "mountPath") ?? string.Empty,
+                    StringComparer.Ordinal);
+
+            mounts.Should().Contain("runner-home", "/home/runner");
+            mounts.Should().Contain("nuget-cache", "/home/runner/.nuget/packages");
+            mounts.Should().Contain("tmp", "/tmp");
+        }
+    }
+
+    [Fact]
+    public void GitHubRunnerFleet_MustAvoidRwoMultiAttachForScaledDeployments()
+    {
+        var deployments = GitHubRunnerDeployments();
+
+        foreach (var deploymentName in ScaledLinuxRunnerDeployments)
+        {
+            var deployment = deployments[deploymentName];
+            ReplicaCount(deployment).Should().Be(2);
+
+            var volumes = deployment.MappingSequence("spec", "template", "spec", "volumes");
+            var claimNames = volumes
+                .Select(volume => ManifestNodeExtensions.Scalar(volume, "persistentVolumeClaim", "claimName"))
+                .Where(value => !string.IsNullOrWhiteSpace(value))
+                .ToList();
+
+            claimNames.Should().BeEmpty($"{deploymentName} is scaled and must not share a RWO PVC");
+            volumes.Should().Contain(volume =>
+                string.Equals(ManifestNodeExtensions.Scalar(volume, "name"), "nuget-cache", StringComparison.Ordinal)
+                && ManifestNodeExtensions.Mapping(volume, "emptyDir") != null);
+        }
+
+        var common = deployments["github-runner"];
+        ReplicaCount(common).Should().Be(1);
+        common.MappingSequence("spec", "template", "spec", "volumes")
+            .Select(volume => ManifestNodeExtensions.Scalar(volume, "persistentVolumeClaim", "claimName"))
+            .Where(value => !string.IsNullOrWhiteSpace(value))
+            .Should()
+            .ContainSingle()
+            .Which
+            .Should()
+            .Be("github-runner-nuget-cache");
+    }
+
+    [Fact]
+    public void Monitoring_MustAlertWhenLinuxRunnerDeploymentIsUnavailable()
+    {
+        var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
+
+        monitoring.Should().Contain("MacMiniRunnerOffline");
+        monitoring.Should().Contain("LinuxRunnerOffline");
+        monitoring.Should().Contain("kube_deployment_status_replicas_ready");
+        monitoring.Should().Contain("github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))");
+        monitoring.Should().Contain("folder: CI Alerts");
+        monitoring.Should().Contain("uid: linux-runner-offline");
+        monitoring.Should().Contain("alert_channel: irc");
+    }
+
     [Fact]
     public void StatefulSets_WithVolumeClaimTemplates_MustDeclareFilesystemDefaults()
     {
@@ -291,6 +421,184 @@ public sealed class FleetManifestLintTests
         violations.Should().BeEmpty();
     }
 
+    [Fact]
+    public void FcDeviceManagement_MustShipExpectedManifestSet()
+    {
+        var appRoot = Path.Combine(Inventory.BluejayRoot, "apps", "fc-devicemgmt");
+        Directory.Exists(appRoot).Should().BeTrue("Sprint 8 Cx-5 owns apps/fc-devicemgmt.");
+
+        var expectedFiles = new[]
+        {
+            "1password-item.yaml",
+            "argocd-application.yaml",
+            "certificate-web.yaml",
+            "clusterrole-operator.yaml",
+            "clusterrolebinding-operator.yaml",
+            "deployment-operator.yaml",
+            "deployment-web.yaml",
+            "ingressroute-web.yaml",
+            "namespace.yaml",
+            "network-policy.yaml",
+            "service-web.yaml",
+            "serviceaccount-operator.yaml",
+        };
+
+        Directory.GetFiles(appRoot, "*.yaml")
+            .Select(Path.GetFileName)
+            .Should()
+            .BeEquivalentTo(expectedFiles);
+
+        foreach (var expectedFile in expectedFiles)
+        {
+            FcDeviceManagementDocuments()
+                .Should()
+                .Contain(document => document.RelativePath == $"fc-devicemgmt/{expectedFile}");
+        }
+    }
+
+    [Fact]
+    public void FcDeviceManagement_ObjectsMustCarryStandardTraceabilityLabels()
+    {
+        var requiredLabels = new[]
+        {
+            "app.kubernetes.io/name",
+            "app.kubernetes.io/part-of",
+            "app.kubernetes.io/managed-by",
+            "flowercore.io/tenant-id",
+            "flowercore.io/created-by",
+        };
+
+        var violations = FcDeviceManagementDocuments()
+            .SelectMany(document => requiredLabels
+                .Where(label => string.IsNullOrWhiteSpace(document.Scalar("metadata", "labels", label)))
+                .Select(label => $"{document.Descriptor} is missing metadata.labels['{label}']."))
+            .Concat(FcDeviceManagementDocuments()
+                .Where(document => document.Kind == "Deployment")
+                .SelectMany(document => requiredLabels
+                    .Where(label => string.IsNullOrWhiteSpace(document.Scalar("spec", "template", "metadata", "labels", label)))
+                    .Select(label => $"{document.Descriptor} pod template is missing metadata.labels['{label}'].")))
+            .Concat(FcDeviceManagementDocuments()
+                .Where(document => document.Kind == "Deployment")
+                .Where(document => string.IsNullOrWhiteSpace(document.Scalar("spec", "template", "metadata", "annotations", "flowercore.io/audit-trace-id")))
+                .Select(document => $"{document.Descriptor} pod template is missing flowercore.io/audit-trace-id."))
+            .ToList();
+
+        violations.Should().BeEmpty();
+    }
+
+    [Fact]
+    public void FcDeviceManagement_IngressMustUseCertManagerAndKeepPublicHostDisabled()
+    {
+        var appText = string.Join(
+            Environment.NewLine,
+            Directory.GetFiles(Path.Combine(Inventory.BluejayRoot, "apps", "fc-devicemgmt"), "*.yaml")
+                .Select(File.ReadAllText));
+
+        appText.Should().NotContain("certResolver");
+        appText.Should().Contain("update.flowercore.io");
+        appText.Should().Contain("disabled-until-Q-OIDC-1");
+
+        FcDeviceManagementDocuments()
+            .Where(document => document.Kind == "IngressRoute")
+            .SelectMany(document => document.MappingSequence("spec", "routes"))
+            .Select(route => ManifestNodeExtensions.Scalar(route, "match") ?? string.Empty)
+            .Should()
+            .Contain(match => match.Contains("Host(`devices.iamworkin.lan`)", StringComparison.Ordinal))
+            .And.NotContain(match => match.Contains("Host(`update.flowercore.io`)", StringComparison.Ordinal));
+
+        var certificate = FcDeviceManagementDocuments()
+            .Single(document => document.Kind == "Certificate" && document.Name == "fc-devicemgmt-web-tls");
+
+        certificate.Scalar("spec", "issuerRef", "name").Should().Be("step-ca-acme");
+        certificate.Scalar("spec", "issuerRef", "kind").Should().Be("ClusterIssuer");
+        ManifestNodeExtensions.ScalarSequence(certificate.Root, "spec", "dnsNames")
+            .Should()
+            .ContainSingle("devices.iamworkin.lan");
+    }
+
+    [Fact]
+    public void FcDeviceManagement_OperatorRbacMustCoverDevicesAndOwnerLookup()
+    {
+        var clusterRole = FcDeviceManagementDocuments()
+            .Single(document => document.Kind == "ClusterRole" && document.Name == "fc-devicemgmt-operator");
+        var allScalars = clusterRole.AllScalars().ToList();
+
+        allScalars.Should().Contain("devices.flowercore.io");
+        allScalars.Should().Contain("*");
+        allScalars.Should().Contain("deployments");
+        allScalars.Should().Contain("get");
+
+        var operatorDeployment = FcDeviceManagementDocuments()
+            .Single(document => document.Kind == "Deployment" && document.Name == "fc-devicemgmt-operator");
+
+        operatorDeployment.AllScalars().Should().Contain("FLOWERCORE_KUBERNETES_OWNER_DEPLOYMENT");
+        operatorDeployment.AllScalars().Should().Contain("fc-devicemgmt-operator");
+    }
+
+    [Fact]
+    public void FcDeviceManagement_RuntimeSecretsMustUseOnePasswordItemPattern()
+    {
+        var item = FcDeviceManagementDocuments()
+            .Single(document => document.Kind == "OnePasswordItem" && document.Name == "fc-devicemgmt-runtime");
+
+        item.Scalar("spec", "itemPath")
+            .Should()
+            .Be("vaults/IAmWorkin/items/FlowerCore DeviceManagement Runtime");
+
+        var appText = string.Join(
+            Environment.NewLine,
+            Directory.GetFiles(Path.Combine(Inventory.BluejayRoot, "apps", "fc-devicemgmt"), "*.yaml")
+                .Select(File.ReadAllText));
+
+        FcDeviceManagementDocuments().Should().NotContain(document => document.Kind == "Secret");
+        appText.Should().Contain("secretKeyRef:");
+        appText.Should().Contain("secretName: fc-devicemgmt-runtime");
+        appText.Should().NotContain("stringData:");
+        appText.Should().NotContain("from-literal");
+        appText.Should().NotContain("tls.key:");
+    }
+
+    [Fact]
+    public void FcDeviceManagement_NetworkPoliciesMustAllowLanAgentsSynologyAndDnatPorts()
+    {
+        var policies = FcDeviceManagementDocuments()
+            .Where(document => document.Kind == "NetworkPolicy")
+            .ToList();
+
+        policies.Should().HaveCount(2);
+
+        var combinedScalars = policies.SelectMany(policy => policy.AllScalars()).ToList();
+        combinedScalars.Should().Contain("10.0.56.0/24");
+        combinedScalars.Should().Contain("10.0.57.0/24");
+        combinedScalars.Should().Contain("10.0.58.0/24");
+        combinedScalars.Should().Contain("10.0.68.0/27");
+        combinedScalars.Should().Contain("10.0.58.3/32");
+
+        var combinedEgressPorts = policies.SelectMany(policy => policy.EgressPorts()).ToHashSet(StringComparer.Ordinal);
+        combinedEgressPorts.Should().Contain(new[] { "80", "443", "8080", "8443", "2049", "111" });
+
+        var traefikVipPolicies = policies
+            .Where(policy => policy.AllScalars().Any(value => value.Contains("10.0.56.200", StringComparison.Ordinal)))
+            .ToList();
+
+        traefikVipPolicies.Should().ContainSingle();
+        traefikVipPolicies[0].EgressPorts().Should().Contain(new[] { "80", "443", "8080", "8443" });
+    }
+
+    [Fact]
+    public void FcDeviceManagement_ArgocdApplicationMustMatchApplicationSetDiscoveryConventions()
+    {
+        var application = FcDeviceManagementDocuments()
+            .Single(document => document.Kind == "Application" && document.Name == "infra-fc-devicemgmt");
+
+        application.Namespace.Should().Be("argocd");
+        application.Scalar("spec", "source", "repoURL")
+            .Should()
+            .Be("http://gitea-clusterip.gitea.svc.cluster.local:3000/bluejay/bluejay-infra.git");
+        application.Scalar("spec", "source", "path").Should().Be("apps/fc-devicemgmt");
+        application.Scalar("spec", "destination", "namespace").Should().Be("fc-devicemgmt");
+    }
+
     private static IEnumerable<string> ProbeViolations(
         ManifestDocument document,
         YamlMappingNode container,
@@ -314,6 +622,51 @@ public sealed class FleetManifestLintTests
             $"{document.Descriptor} container '{containerName}' still uses {probeKey}.httpGet on /health.",
         };
     }
+
+    private static IReadOnlyDictionary<string, ManifestDocument> GitHubRunnerDeployments()
+    {
+        return Inventory.Documents
+            .Where(document => document.Kind == "Deployment")
+            .Where(document => document.Namespace == "github-runner")
+            .ToDictionary(document => document.Name, StringComparer.Ordinal);
+    }
+
+    private static int ReplicaCount(ManifestDocument document)
+    {
+        return int.TryParse(document.Scalar("spec", "replicas"), out var replicas) ? replicas : 1;
+    }
+
+    private static string? EnvValue(YamlMappingNode container, string name)
+    {
+        return EnvMapping(container, name) is { } env ? ManifestNodeExtensions.Scalar(env, "value") : null;
+    }
+
+    private static string? EnvSecretName(YamlMappingNode container, string name)
+    {
+        return EnvMapping(container, name) is { } env
+            ? ManifestNodeExtensions.Scalar(env, "valueFrom", "secretKeyRef", "name")
+            : null;
+    }
+
+    private static string? EnvSecretKey(YamlMappingNode container, string name)
+    {
+        return EnvMapping(container, name) is { } env
+            ? ManifestNodeExtensions.Scalar(env, "valueFrom", "secretKeyRef", "key")
+            : null;
+    }
+
+    private static YamlMappingNode? EnvMapping(YamlMappingNode container, string name)
+    {
+        return ManifestNodeExtensions.MappingSequence(container, "env")
+            .SingleOrDefault(env => string.Equals(ManifestNodeExtensions.Scalar(env, "name"), name, StringComparison.Ordinal));
+    }
+
+    private static IReadOnlyList<ManifestDocument> FcDeviceManagementDocuments()
+    {
+        return Inventory.Documents
+            .Where(document => document.RelativePath.StartsWith("fc-devicemgmt/", StringComparison.Ordinal))
+            .ToList();
+    }
 }
 
 internal sealed class ManifestInventory

tests/bluejay-infra-lint/OpenVoxServerDurabilityTests.cs

@@ -0,0 +1,99 @@
+using FluentAssertions;
+using Xunit;
+
+namespace BluejayInfraLint.Tests;
+
+[Trait("Category", "Unit")]
+public sealed class OpenVoxServerDurabilityTests
+{
+    private static readonly string Root = FindRepoRoot();
+    private static readonly string RunbookPath = Path.Combine(Root, "docs", "runbooks", "openvoxserver-quadlet-durability.md");
+    private static readonly string SmokePath = Path.Combine(Root, "scripts", "monitoring", "openvox-recreate-smoke.sh");
+
+    [Fact]
+    public void Runbook_DocumentsHostArtifactAndNonArgoPath()
+    {
+        var runbook = File.ReadAllText(RunbookPath);
+
+        runbook.Should().Contain("noc1 host artifact");
+        runbook.Should().Contain("not an ArgoCD application");
+        runbook.Should().Contain("systemctl cat openvoxserver");
+        runbook.Should().Contain("/etc/containers/systemd/openvoxserver.container");
+    }
+
+    [Fact]
+    public void Runbook_DocumentsCx12LiveApplyState()
+    {
+        var runbook = File.ReadAllText(RunbookPath);
+
+        runbook.Should().Contain("Sprint 32 Cx-12");
+        runbook.Should().Contain("openvoxserver-safeconfig.service");
+        runbook.Should().Contain("/opt/puppet/r10k-deploy.sh");
+        runbook.Should().Contain("HEAD == origin/master");
+    }
+
+    [Fact]
+    public void SmokeScript_IsExplicitlyOptIn()
+    {
+        var smoke = File.ReadAllText(SmokePath);
+
+        smoke.Should().Contain("OPENVOX_RECREATE_SMOKE");
+        smoke.Should().Contain("exit 64");
+        smoke.IndexOf("OPENVOX_RECREATE_SMOKE", StringComparison.Ordinal)
+            .Should().BeLessThan(smoke.IndexOf("systemctl stop openvoxserver", StringComparison.Ordinal));
+    }
+
+    [Fact]
+    public void SmokeScript_RequiresGeneratedSystemdUnitBeforeRemovingContainer()
+    {
+        var smoke = File.ReadAllText(SmokePath);
+
+        smoke.Should().Contain("systemctl cat openvoxserver");
+        smoke.Should().Contain("refusing to remove a container without a verified systemd recreate path");
+        smoke.IndexOf("systemctl cat openvoxserver", StringComparison.Ordinal)
+            .Should().BeLessThan(smoke.IndexOf("podman rm openvoxserver", StringComparison.Ordinal));
+    }
+
+    [Fact]
+    public void Artifacts_DoNotStoreSecretsOrPaidRunnerLabels()
+    {
+        var forbidden = new[]
+        {
+            "BEGIN OPENSSH PRIVATE KEY",
+            "BEGIN RSA PRIVATE KEY",
+            "ubuntu-latest",
+            "windows-latest",
+            "macos-latest",
+        };
+
+        var violations = new[] { RunbookPath, SmokePath }
+            .SelectMany(path =>
+            {
+                var text = File.ReadAllText(path);
+                return forbidden
+                    .Where(token => text.Contains(token, StringComparison.OrdinalIgnoreCase))
+                    .Select(token => $"{Path.GetRelativePath(Root, path)} contains forbidden token {token}");
+            })
+            .ToList();
+
+        violations.Should().BeEmpty();
+    }
+
+    private static string FindRepoRoot()
+    {
+        var current = new DirectoryInfo(AppContext.BaseDirectory);
+        while (current is not null)
+        {
+            if (Directory.Exists(Path.Combine(current.FullName, "apps"))
+                && Directory.Exists(Path.Combine(current.FullName, "scripts"))
+                && File.Exists(Path.Combine(current.FullName, "README.md")))
+            {
+                return current.FullName;
+            }
+
+            current = current.Parent;
+        }
+
+        throw new DirectoryNotFoundException("Could not find bluejay-infra root.");
+    }
+}

tests/bluejay-infra-lint/PiSignagePlayerArtifactTests.cs

@@ -0,0 +1,269 @@
+using System.Text.Json;
+using FluentAssertions;
+using Xunit;
+
+namespace BluejayInfraLint.Tests;
+
+[Trait("Category", "Unit")]
+public sealed class PiSignagePlayerArtifactTests
+{
+    private static readonly string Root = FindRepoRoot();
+    private static readonly string AppRoot = Path.Combine(Root, "apps", "fc-signage-pi-player");
+
+    public static TheoryData<string> RequiredArtifacts => new()
+    {
+        "README.md",
+        "systemd/flowercore-signage-player-pi.service",
+        "systemd/flowercore-signage-player-pi-hdmi.service",
+        "systemd/flowercore-signage-bootstrap.service",
+        "systemd/flowercore-signage-renew.service",
+        "systemd/flowercore-signage-renew.timer",
+        "systemd/flowercore-signage-detect-display.service",
+        "systemd/flowercore-signage-detect-display.timer",
+        "systemd/99-flowercore-signage-hdmi.rules",
+        "chromium-policies/flowercore-signage.json",
+        "scripts/flowercore-signage-launch.sh",
+        "scripts/flowercore-signage-prelaunch.sh",
+        "scripts/flowercore-signage-bootstrap.sh",
+        "scripts/flowercore-signage-renew-cert.sh",
+        "scripts/flowercore-signage-hdmi-respond.sh",
+        "scripts/fc-signage-detect-display",
+    };
+
+    [Theory]
+    [MemberData(nameof(RequiredArtifacts))]
+    public void RequiredArtifacts_ArePresent(string relativePath)
+    {
+        File.Exists(Path.Combine(AppRoot, relativePath)).Should().BeTrue(relativePath);
+    }
+
+    [Fact]
+    public void PlayerService_UsesExpectedRestartAndMemoryGuards()
+    {
+        var unit = Read("systemd/flowercore-signage-player-pi.service");
+
+        unit.Should().Contain("Restart=always");
+        unit.Should().Contain("RestartSec=10s");
+        unit.Should().Contain("StartLimitBurst=5");
+        unit.Should().Contain("StartLimitIntervalSec=300s");
+        unit.Should().Contain("MemoryMax=2G");
+    }
+
+    [Fact]
+    public void PlayerService_IsGatedByNodeIdentityAndMtlsCertificate()
+    {
+        var unit = Read("systemd/flowercore-signage-player-pi.service");
+
+        unit.Should().Contain("ConditionPathExists=/etc/flowercore/signage-node.json");
+        unit.Should().Contain("ConditionPathExists=/etc/fc-signage-player/client.p12");
+        unit.Should().Contain("ExecStartPre=/usr/local/bin/flowercore-signage-prelaunch.sh");
+    }
+
+    [Fact]
+    public void LaunchScript_TriesEmbedThenFallsBackToBarePlayerRoute()
+    {
+        var script = Read("scripts/flowercore-signage-launch.sh");
+
+        script.Should().Contain("/player/${NODE_ID}/embed?token=${CERT_THUMB}");
+        script.Should().Contain("url-divergence.log");
+        script.Should().Contain("/player/${NODE_ID}?token=${CERT_THUMB}");
+    }
+
+    [Fact]
+    public void LaunchScript_DisablesChromiumPromptsAndRuntimeUpdates()
+    {
+        var script = Read("scripts/flowercore-signage-launch.sh");
+
+        script.Should().Contain("--noerrdialogs");
+        script.Should().Contain("--disable-infobars");
+        script.Should().Contain("--password-store=basic");
+        script.Should().Contain("--check-for-update-interval=2592000");
+    }
+
+    [Fact]
+    public void PrelaunchScript_AbortsWhenRequiredFilesAreMissing()
+    {
+        var script = Read("scripts/flowercore-signage-prelaunch.sh");
+
+        script.Should().Contain("for f in /etc/flowercore/signage-node.json /etc/fc-signage-player/client.p12 /etc/fc-signage-player/client.p12.pass");
+        script.Should().Contain("exit 1");
+        script.Should().Contain("-checkend $((7*24*3600))");
+    }
+
+    [Fact]
+    public void BootstrapScript_IsIdempotentWhenAlreadyEnrolled()
+    {
+        var script = Read("scripts/flowercore-signage-bootstrap.sh");
+
+        script.Should().Contain("already enrolled");
+        script.Should().Contain("exit 0");
+        script.Should().Contain(".enrolledAt");
+    }
+
+    [Fact]
+    public void BootstrapScript_GeneratesStableMachineIdFromUuid()
+    {
+        var script = Read("scripts/flowercore-signage-bootstrap.sh");
+
+        script.Should().Contain("uuidgen");
+        script.Should().Contain("cut -c1-16");
+        script.Should().Contain("machineId");
+    }
+
+    [Fact]
+    public void BootstrapScript_RetriesRegisterOnceForFirstCallRace()
+    {
+        var script = Read("scripts/flowercore-signage-bootstrap.sh");
+
+        script.Should().Contain("for attempt in 1 2");
+        script.Should().Contain("register attempt $attempt returned");
+        script.Should().Contain("sleep 5");
+    }
+
+    [Fact]
+    public void BootstrapScript_SupportsSetupCodeAndApprovalPollingBudget()
+    {
+        var script = Read("scripts/flowercore-signage-bootstrap.sh");
+
+        script.Should().Contain("signage-setup-code");
+        script.Should().Contain("approve-via-setup-code");
+        script.Should().Contain("+ 1800");
+        script.Should().Contain("sleep 15");
+    }
+
+    [Fact]
+    public void BootstrapScript_CsrSubjectIdentifiesPiPlayer()
+    {
+        var script = Read("scripts/flowercore-signage-bootstrap.sh");
+
+        script.Should().Contain("/CN=${NODE_ID}/O=FlowerCore/OU=SignagePlayer-Pi");
+    }
+
+    [Fact]
+    public void BootstrapScript_PersistsCertificateAsP12WithRestrictivePermissions()
+    {
+        var script = Read("scripts/flowercore-signage-bootstrap.sh");
+
+        script.Should().Contain("openssl pkcs12 -export");
+        script.Should().Contain("client.p12.pass");
+        script.Should().Contain("chmod 0600");
+        script.Should().Contain("chmod 0640");
+    }
+
+    [Fact]
+    public void RenewScript_OnlyRunsWhenCertHasLessThanThirtyDays()
+    {
+        var script = Read("scripts/flowercore-signage-renew-cert.sh");
+
+        script.Should().Contain("-checkend $((30*24*3600))");
+        script.Should().Contain("exit 0");
+        script.Should().Contain("/renew");
+    }
+
+    [Fact]
+    public void RenewScript_AtomicallySwapsNewCertificateFiles()
+    {
+        var script = Read("scripts/flowercore-signage-renew-cert.sh");
+
+        script.Should().Contain("client.key.new");
+        script.Should().Contain("mv \"$CERT_DIR/client.key.new\" \"$CERT_DIR/client.key\"");
+        script.Should().Contain("mv \"$CERT_DIR/client.p12.new\" \"$CERT_DIR/client.p12\"");
+    }
+
+    [Fact]
+    public void HdmiRule_RestartsPlayerAndRunsCapabilityDetection()
+    {
+        var rule = Read("systemd/99-flowercore-signage-hdmi.rules");
+        var responder = Read("scripts/flowercore-signage-hdmi-respond.sh");
+
+        rule.Should().Contain("KERNEL==\"card?-HDMI-A-?\"");
+        rule.Should().Contain("start flowercore-signage-player-pi-hdmi.service");
+        responder.Should().Contain("sleep 2");
+        responder.Should().Contain("start flowercore-signage-detect-display.service");
+        responder.Should().Contain("restart flowercore-signage-player-pi.service");
+    }
+
+    [Fact]
+    public void DetectDisplayServiceAndTimer_RunAtBootAndDaily()
+    {
+        var service = Read("systemd/flowercore-signage-detect-display.service");
+        var timer = Read("systemd/flowercore-signage-detect-display.timer");
+
+        service.Should().Contain("ExecStart=/usr/local/bin/fc-signage-detect-display");
+        timer.Should().Contain("OnBootSec=30s");
+        timer.Should().Contain("OnCalendar=daily");
+        timer.Should().Contain("RandomizedDelaySec=1h");
+    }
+
+    [Fact]
+    public void DetectDisplayScript_EmitsDisconnectedProfileWhenNoHdmiIsPresent()
+    {
+        var script = Read("scripts/fc-signage-detect-display");
+
+        script.Should().Contain("displayConnected: false");
+        script.Should().Contain("No HDMI display detected");
+    }
+
+    [Fact]
+    public void DetectDisplayScript_ParsesEdidForHdrResolutionAndAudio()
+    {
+        var script = Read("scripts/fc-signage-detect-display");
+
+        script.Should().Contain("edid-decode");
+        script.Should().Contain("HDR (Static|Dynamic) Metadata Block");
+        script.Should().Contain("maxResolution");
+        script.Should().Contain("hasAudioOutput");
+    }
+
+    [Fact]
+    public void DetectDisplayScript_TriesBothForwardCompatibleCapabilityEndpoints()
+    {
+        var script = Read("scripts/fc-signage-detect-display");
+
+        script.Should().Contain("/api/v1/nodes/${NODE_ID}/capabilities");
+        script.Should().Contain("/api/v1/displays/${NODE_ID}/capability-profile");
+        script.Should().Contain("no endpoint accepted the profile");
+    }
+
+    [Fact]
+    public void ChromiumPolicy_IsValidJsonAndDisablesCredentialPrompts()
+    {
+        using var doc = JsonDocument.Parse(Read("chromium-policies/flowercore-signage.json"));
+        var root = doc.RootElement;
+
+        root.GetProperty("AutofillAddressEnabled").GetBoolean().Should().BeFalse();
+        root.GetProperty("AutofillCreditCardEnabled").GetBoolean().Should().BeFalse();
+        root.GetProperty("PasswordManagerEnabled").GetBoolean().Should().BeFalse();
+        root.GetProperty("ExtensionInstallBlocklist")[0].GetString().Should().Be("*");
+    }
+
+    [Fact]
+    public void RenewalTimer_UsesDailyCadenceWithTwoHourJitter()
+    {
+        var timer = Read("systemd/flowercore-signage-renew.timer");
+
+        timer.Should().Contain("OnCalendar=daily");
+        timer.Should().Contain("RandomizedDelaySec=2h");
+        timer.Should().Contain("Persistent=true");
+    }
+
+    private static string Read(string relativePath)
+        => File.ReadAllText(Path.Combine(AppRoot, relativePath.Replace('/', Path.DirectorySeparatorChar)));
+
+    private static string FindRepoRoot()
+    {
+        var current = new DirectoryInfo(AppContext.BaseDirectory);
+        while (current is not null)
+        {
+            if (Directory.Exists(Path.Combine(current.FullName, "apps"))
+                && File.Exists(Path.Combine(current.FullName, "README.md")))
+            {
+                return current.FullName;
+            }
+
+            current = current.Parent;
+        }
+
+        throw new DirectoryNotFoundException("Could not find bluejay-infra root.");
+    }
+}

tests/bluejay-infra-lint/conftest.dev/02_public_method_allowlist.rego

@@ -1,6 +1,6 @@
 package bluejayinfra.public_method_allowlist
 
-public_hosts := {"dist.flowercore.io", "dns.iamworkin.lan"}
+public_hosts := {"brochure.flowercore.io", "dist.flowercore.io", "dns.iamworkin.lan"}
 
 deny[msg] {
   input.kind == "IngressRoute"