feat(fc-devicemgmt): add Kubernetes deployment manifests

Missing document separator caused YAML to merge the OnePasswordItem's
top-level `spec: itemPath:` block into the ConfigMap that follows.
Result: a ConfigMap with a `.spec` field whose K8s schema does not
declare one, triggering ArgoCD's structured-merge diff to fail since
2026-05-11T15:30:54Z:

  Failed to compare desired state to live state: failed to calculate
  diff: error calculating structured merge diff: error building typed
  value from config resource: .spec: field not declared in schema

App stayed Healthy (live K8s tolerated the extra field — ConfigMap
ignored it) but ArgoCD's diff calc was broken, leaving the app stuck at
sync=Unknown for all 21 resources. Adding the missing `---` separator
makes the OnePasswordItem and ConfigMap proper sibling YAML documents,
each with its own kind-correct schema.

Diagnosed during 2026-05-12 morning routine.

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

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/argocd-application.yaml

@@ -0,0 +1,33 @@
+# Explicit ArgoCD Application shape for bootstrap/review.
+#
+# The live bluejay-infra ApplicationSet already discovers apps/* directories
+# and creates this same Application name (`infra-fc-devicemgmt`) automatically.
+# Keep repoURL on the internal Gitea ClusterIP URL; ArgoCD does not trust the
+# external step-ca HTTPS endpoint.
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: infra-fc-devicemgmt
+  namespace: argocd
+  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
+spec:
+  project: default
+  source:
+    repoURL: http://gitea-clusterip.gitea.svc.cluster.local:3000/bluejay/bluejay-infra.git
+    targetRevision: main
+    path: apps/fc-devicemgmt
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: fc-devicemgmt
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+    syncOptions:
+      - CreateNamespace=true
+      - ServerSideApply=true

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:v20260512-cx5
+          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 +1,135 @@
+# 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.
+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: 2
+  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-updater/fc-updater.yaml

@@ -58,7 +58,7 @@ spec:
       nodeName: rke2-server
       containers:
         - name: web
-          image: localhost/fc-updater-web:v20260507-public-privacy
+          image: localhost/fc-updater-web:v20260509-4162dca-authgate
           imagePullPolicy: Never
           ports:
             - containerPort: 8080

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

@@ -6,14 +6,29 @@
 # `bluejay-ws-sandbox-1` runner placeholder. Andrew explicitly does NOT want
 # BLUEJAY-WS registered as a runner (workstation has personal/operator state).
 #
-# Status (2026-05-08): STAGED ONLY — DO NOT APPLY without operator review.
+# Storage layout (2026-05-08):
-# See docs/infrastructure/windows-server-build-runner-plan.md "Phase 1 readiness gate".
+#   * 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.
 #
-# Prerequisites that MUST be satisfied first:
+# Status (2026-05-08): LIVE — Phase 1 prereqs satisfied:
-#   1. Windows Server 2025 ISO populated into the `windows-server-2025-iso` PVC
+#   * Multus CNI v4.2.2 thick-plugin DaemonSet running on all 3 RKE2 nodes
-#      (operator interactive step — Microsoft Evaluation Center download).
+#     (apps/multus/multus.yaml; ApplicationSet `infra-multus` Synced/Healthy)
-#   2. Either Multus + PROD VLAN NAD (preferred) OR pod-network only (this YAML).
+#   * CDI v1.65.0 operator + CR Deployed (apps/cdi/; ApplicationSet
-#   3. KubeVirt CR feature gates: none required for non-persistent vTPM.
+#     `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
@@ -42,21 +57,49 @@ metadata:
     pod-security.kubernetes.io/enforce: privileged
 
 ---
-# ISO PVC — operator must populate this before applying the VM manifest.
+# ISO PVC — populated via CDI virtctl image-upload (CDI is now installed).
-# Population paths (see plan doc "Phase 1 readiness gate", section 2):
+#
-#   Path A — manual upload via helper pod + kubectl cp
+# **Volume mode (2026-05-08 status):** Filesystem-mode PVC. A migration to
-#   Path B — install CDI, then DataVolume HTTP import
+# `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: 6Gi
+      storage: 10Gi          # Server 2025 ISO is 7.7GB; 10Gi for headroom
   storageClassName: longhorn
 
 ---
@@ -220,10 +263,16 @@ data:
           </OOBE>
           <UserAccounts>
             <AdministratorPassword>
-              <!-- IMPORTANT: replace the Value below with a real password BEFORE applying.
+              <!-- Real password is in 1Password — vault qaphopopkryhbg353ukzhhuqoq,
-                   Generate via: $pw = "YourPasswordHere" + "AdministratorPassword";
+                   item id h3ix4mgfk65gmkcmvh6ly3d3hu, title:
-                                 [Convert]::ToBase64String([Text.Encoding]::Unicode.GetBytes($pw)) -->
+                   "ci1 Administrator (Windows Server 2025 KubeVirt VM)".
-              <Value>UABMAEEAQwBFAEgATwBMAEQARQBSAEEAZABtAGkAbgBpAHMAdAByAGEAdABvAHIAUABhAHMAcwB3AG8AcgBkAA==</Value>
+                   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>
@@ -260,7 +309,33 @@ metadata:
     role: github-actions-runner
     flowercore.io/managed-by: bluejay-infra
 spec:
-  running: false   # Set to true after operator approves + ISO loaded
+  # `running: true` is deprecated in favor of `runStrategy`. They are mutually
+  # 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:
@@ -302,18 +377,60 @@ spec:
         firmware:
           bootloader:
             efi:
-              secureBoot: true
+              # 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
           disks:
-            - name: rootdisk
+            # 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: windows-iso
-              bootOrder: 2
-              cdrom:
-                bus: sata
             - name: virtio-drivers
               cdrom:
                 bus: sata
@@ -340,11 +457,50 @@ spec:
           persistentVolumeClaim:
             claimName: ci1-rootdisk
         - name: windows-iso
-          persistentVolumeClaim:
+          # 2026-05-08 PM (Path C, CONTAINERDISK): the ISO is now packaged as
-            claimName: windows-server-2025-iso
+          # 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
+            imagePullPolicy: Never
         - name: virtio-drivers
           containerDisk:
-            image: quay.io/kubevirt/virtio-container-disk
+            # 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:

apps/kubevirt-vms/win2025-iso-nfs-pv.yaml

@@ -0,0 +1,99 @@
+# =============================================================================
+# Windows Server 2025 ISO — Static NFS PV (Path B for SATA-CDROM timeout)
+# =============================================================================
+# Purpose: Mount the ISO from Synology NAS via NFS instead of from a Longhorn-
+# backed Filesystem PVC.
+#
+# Why: SATA-CDROM emulation reading from a Longhorn-backed Filesystem PVC is
+# too slow for OVMF's boot read window — the DVD-ROM enumeration times out
+# before the bootloader can be read. Symptom on the serial console:
+#   BdsDxe: failed to start Boot0001 "UEFI QEMU DVD-ROM QM00001 " from ...
+#   BdsDxe: failed to start Boot0001 ... Time out
+#   BdsDxe: No bootable option or device was found
+# Diagnosis confirmed the ISO content is a perfectly valid bootable ISO9660
+# image — the bug is in the timing path between OVMF and Longhorn-backed
+# storage, not in the ISO itself.
+#
+# Block-mode PVC was tried (`volumeMode: Block` via DataVolume) and would
+# likely fix the timing, but CDI v1.65.0's upload-target pod cannot open the
+# block device due to runAsUser:107 + capabilities.drop:[ALL] and we got:
+#   blockdev: cannot open /dev/cdi-block-volume: Permission denied
+#
+# NFS-mounted ISO bypasses both issues: no Longhorn slowness, no CDI upload
+# pod permission concerns. The ISO is read directly from the NAS over a
+# native NFSv4.1 mount that QEMU's SATA emulator can read at full LAN speed.
+#
+# Layout on Synology:
+#   /volume1/ISOs/                                              (existing export, RKE2 ACL)
+#     en-us_windows_server_2025_updated_march_2026_x64_dvd_8e06425a.iso
+#     win2025-iso-disk/                                         (new subdir, 2026-05-08)
+#       disk.img -> hardlink to ../en-us_windows_server_2025_..._8e06425a.iso
+#
+# KubeVirt's launcher pod expects a PVC mounted at
+# /var/run/kubevirt-private/vmi-disks/<diskName>/disk.img — by mounting the
+# `win2025-iso-disk/` subdir as the NFS PV root, `disk.img` lives at the PV's
+# root and KubeVirt's CDROM emulator finds it without any path manipulation.
+#
+# A symlink would NOT work for sub-path NFS mounts (the relative target
+# `../...iso` falls outside the sub-mount root). A hardlink works because it
+# references the same inode regardless of mount point.
+#
+# Memory references:
+#   - feedback_synology_nfs_volume1_kubernetes_export_scoped (Synology export
+#     scoping pattern — but /volume1/ISOs export, unlike /volume1/kubernetes,
+#     does support sub-path mounts because Synology NFS is configured with
+#     pseudo-fs in NFSv4.1)
+#   - feedback_kubevirt_iso_first_install_bootorder_and_runstrategy (boot
+#     order / runStrategy gotchas, separate from the storage timing issue)
+#
+# Validation (2026-05-08, from rke2-server / rke2-agent1 / rke2-agent2):
+#   mount -t nfs -o nfsvers=4.1,ro 10.0.58.3:/volume1/ISOs/win2025-iso-disk /tmp/m
+#   file /tmp/m/disk.img
+#     -> ISO 9660 CD-ROM filesystem data 'SSS_X64FRE_EN-US_DV9' (bootable)
+# All 3 RKE2 nodes can mount and read.
+# =============================================================================
+
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: windows-server-2025-iso-nfs
+  labels:
+    flowercore.io/iso: windows-server-2025
+    flowercore.io/managed-by: bluejay-infra
+spec:
+  capacity:
+    storage: 8Gi
+  accessModes:
+    - ReadOnlyMany
+  volumeMode: Filesystem
+  persistentVolumeReclaimPolicy: Retain
+  storageClassName: ""              # static, no provisioner
+  mountOptions:
+    - nfsvers=4.1
+    - ro
+    - hard
+    - timeo=600
+    - retrans=3
+  nfs:
+    server: 10.0.58.3               # BlueJayNAS Synology DS1621+ on HOME VLAN 58
+    path: /volume1/ISOs/win2025-iso-disk
+    readOnly: true
+
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: windows-server-2025-iso-nfs
+  namespace: kubevirt-vms
+  labels:
+    app: ci-runner
+    flowercore.io/managed-by: bluejay-infra
+spec:
+  accessModes:
+    - ReadOnlyMany
+  volumeMode: Filesystem
+  resources:
+    requests:
+      storage: 8Gi
+  storageClassName: ""
+  volumeName: windows-server-2025-iso-nfs

apps/monitoring/noc-monitoring.yaml

@@ -974,6 +974,39 @@ data:
               summary: "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} replica mismatch"
               description: "Spec wants {{ $labels.spec_replicas }} but only {{ $value }} available. Likely a rollout stuck on probe failure, scheduling, or PVC."
 
+          # Q-MR-3 (2026-05-11): multus memory pressure — catches the next OOM
+          # cascade BEFORE multus is OOM-killed cluster-wide. The 2026-05-10
+          # outage (21h) hit because no alert fired on the rising multus working
+          # set — only downstream blackbox / Traefik / service alerts. With
+          # 1Gi limit (bluejay-infra@eb8693e), 80% = ~800MiB; steady-state
+          # runs ~150-250MiB so this only fires when an avalanche starts.
+          - alert: MultusMemoryPressure
+            expr: |
+              container_memory_working_set_bytes{container="kube-multus"}
+                / container_spec_memory_limit_bytes{container="kube-multus"} > 0.8
+            for: 5m
+            labels:
+              severity: critical
+              alert_channel: thermal_print
+            annotations:
+              summary: "kube-multus memory >80% of limit on {{ $labels.node }} for 5m"
+              description: "kube-multus working set is {{ $value | humanizePercentage }} of its memory limit on node {{ $labels.node }}. If this keeps climbing, multus will OOM and all new pod networking will halt cluster-wide (precedent: 2026-05-10 outage)."
+
+          # Q-MR-3 (2026-05-11): namespace pending-pod backlog — catches the
+          # operator-leak avalanche pattern BEFORE it cascades into a multus
+          # CNI OOM. Any FC operator (RemoteDesktop / Distribution / WorldBuilder)
+          # emitting pods without ownerReferences will accumulate them when
+          # the operator crashes. >25 pending pods in any namespace for 30m
+          # is the signal to investigate the reconciler.
+          - alert: NamespacePendingPodBacklog
+            expr: sum by (namespace) (kube_pod_status_phase{phase="Pending"}) > 25
+            for: 30m
+            labels:
+              severity: warning
+            annotations:
+              summary: "Namespace {{ $labels.namespace }} has {{ $value }} Pending pods for 30m"
+              description: "Pending pod count in {{ $labels.namespace }} exceeds 25 sustained for 30m. Likely operator-leak avalanche pattern — children emitted without ownerReferences. Risk of multus CNI OOM cascade."
+
       # Longhorn storage health alerts. Required: longhorn scrape job
       # (added 2026-04-26 — see scrape_configs above). The K8s events
       # for "snapshot becomes not ready to use" are transient lifecycle

apps/multus/multus.yaml

@@ -188,13 +188,24 @@ spec:
         - name: kube-multus
           image: ghcr.io/k8snetworkplumbingwg/multus-cni:snapshot-thick
           command: [ "/usr/src/multus-cni/bin/multus-daemon" ]
+          # 2026-05-11: upstream default of 50Mi memory limit OOM-cascades when
+          # an operator-owned namespace accumulates >100 pending pods retrying
+          # CNI ADD. RemoteDesktop emitted 219 orphan rd-browser-only pods
+          # (missing OwnerReferences), kubelet's CNI ADD avalanche pushed multus
+          # over 50Mi, OOMKilled, restarted with even bigger backlog → loop.
+          # 21h cluster outage. See FlowerCore.Notes:
+          #   feedback_multus_50mi_limit_oom_orphan_pod_avalanche.md
+          # 1Gi limit / 512Mi request comfortably handles a 200+ pod CNI
+          # catchup burst on 64GB nodes (nodes are <25% used in steady-state).
+          # Drop back toward 256Mi only after MultusMemoryPressure alert
+          # proves steady-state working set sits well below 200Mi.
           resources:
             requests:
               cpu: "100m"
-              memory: "50Mi"
+              memory: "512Mi"
             limits:
               cpu: "100m"
-              memory: "50Mi"
+              memory: "1Gi"
           securityContext:
             privileged: true
           terminationMessagePolicy: FallbackToLogsOnError

apps/telephony/telephony.yaml

@@ -127,10 +127,13 @@ spec:
       initContainers:
         - name: fix-data-perms
           image: busybox:latest
-          # Also chown /shared-tts (hostPath /tmp/tts-audio) so the non-root
+          # Must run as root to chown the hostPath /tmp/tts-audio that may be
-          # app user (uid 1654) can write Piper .sln16 files that Asterisk
+          # root-owned after node reboot. Pod-level runAsNonRoot:true would
-          # reads at /var/lib/asterisk/sounds/tts. World-readable (755) is
+          # otherwise inherit and chown would fail with EPERM (see Notes memory
-          # fine — Asterisk runs as a different uid in the other pod.
+          # feedback_hostpath_initcontainer_chown_perms).
+          securityContext:
+            runAsUser: 0
+            runAsNonRoot: false
           command: ["sh", "-c", "chown -R 1654:1654 /data && chown 1654:1654 /shared-tts && chmod 0755 /shared-tts"]
           volumeMounts:
             - name: telephony-data

tests/bluejay-infra-lint/FleetManifestLintTests.cs

@@ -291,6 +291,184 @@ 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 +492,13 @@ public sealed class FleetManifestLintTests
             $"{document.Descriptor} container '{containerName}' still uses {probeKey}.httpGet on /health.",
         };
     }
+
+    private static IReadOnlyList<ManifestDocument> FcDeviceManagementDocuments()
+    {
+        return Inventory.Documents
+            .Where(document => document.RelativePath.StartsWith("fc-devicemgmt/", StringComparison.Ordinal))
+            .ToList();
+    }
 }
 
 internal sealed class ManifestInventory