Deploy TtsReader schema repair image

Co-Authored-By: Codex <codex@openai.com>

.gitattributes

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

.gitignore

@@ -0,0 +1,7 @@
+# .NET build outputs (lint test project)
+**/bin/
+**/obj/
+
+# Editor / temp
+.DS_Store
+*.swp

README.md

@@ -99,10 +99,36 @@ curl -sk -X DELETE https://dns.iamworkin.lan/api/v1/servers/<serverId>/zones/iam
 - **CoreDNS template + ndots:5 collision**: inside pods, `<svc>.<ns>.svc.cluster.local` with <5 dots gets search-expanded through `iamworkin.lan` FIRST and hits the wildcard template → resolves to Traefik VIP, not the real ClusterIP. Use short service names (`<svc>`) in K8s manifests. See memory `feedback_coredns_ndots_template_collision.md`.
 - **Image not on node**: pods stuck `ErrImageNeverPull` means the image wasn't imported to the node Kubernetes scheduled the pod onto. `ctr images import` on all of rke2-server, rke2-agent1, rke2-agent2.
 - **StatefulSet PVC drift**: `volumeClaimTemplates` needs explicit `volumeMode: Filesystem` or ArgoCD SSA self-heals forever. See memory `feedback_argocd_statefulset_pvc_drift.md`.
+- **IngressRoute namespace split**: this RKE2 Traefik install does not allow cross-namespace service refs. Keep the `IngressRoute`, backend `Service`, and TLS secret in the same namespace; if one host is shared across namespaces, duplicate the `Certificate` and move the route next to the destination service.
+- **Public read-only hosts**: if a public host fronts a service that also exposes admin writes internally, add a Traefik route match like `Host(...) && (Method(GET) || Method(HEAD))` on the public edge instead of trusting the app to reject unsafe methods.
+- **Public read-write allowlist hosts**: if a public host accepts a tightly bounded write surface (e.g. bootstrap-JWT POST), pin the allowlist as `(Method(GET) || Method(HEAD) || Method(POST) || Method(OPTIONS))`. PUT/PATCH/DELETE must still 404 at the route. Track A's `updatecenter.iamworkin.lan` / `updates.iamworkin.lan` are the canonical example. The lint test enforces this invariant.
+- **Traefik VIP netpols**: when a `NetworkPolicy` allows `10.0.56.200`, also allow the post-DNAT backend ports (`8443` for TLS plus `8080` or `8000` for HTTP) or Calico will drop the rewritten flow.
+- **Auth-safe probes**: services behind API-key or global auth middleware should prefer `tcpSocket` probes unless `/health` is explicitly exempted before the middleware runs.
 - **ArgoCD must use internal Gitea URL**: `http://gitea-clusterip.gitea.svc.cluster.local:3000/bluejay/bluejay-infra.git`, not the external HTTPS URL (step-ca cert isn't trusted by ArgoCD). The `ApplicationSet` and any hand-created `Application` must both use the internal URL.
 
+## Local manifest lint
+
+The repo now carries a local-first lint pass for the recurring K8s gotchas that have burned the fleet:
+
+```bash
+dotnet test tests/bluejay-infra-lint/BluejayInfraLint.Tests.csproj -c Release
+```
+
+That test project sweeps `bluejay-infra/apps/**` plus the canonical sibling `FlowerCore.*\\k8s` manifests that share the same workspace. Matching `conftest.dev` policy files live under `tests/bluejay-infra-lint/conftest.dev/` for environments that also have `conftest` or `opa`.
+
+## Non-K8s Pi Artifacts
+
+Some `apps/*` directories are deployment artifact bundles consumed by Puppet
+instead of Kubernetes workloads. `apps/fc-signage-pi-player/` carries the
+Chromium signage Pi player, `apps/fc-divoom-dm-pi-device/` carries the additive
+edge2 Divoom-as-DeviceManagement-device profile/Hiera contract, and
+`apps/fc-divoom-tv-pi/` carries the Divoom TV Pi HDMI systemd/Puppet shape.
+These bundles intentionally avoid Deployment, IngressRoute, Certificate, and
+OnePasswordItem resources.
+
 ## 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/agent-zero/agent-zero.yaml

@@ -127,6 +127,18 @@ metadata:
 spec:
   itemPath: "vaults/IAmWorkin/items/Print.Web API Keys"
 
+---
+# Knowledge MCP bearer token for the direct Agent Zero -> Knowledge.Web path.
+# The 1Password item currently stores the raw token in its concealed PASSWORD
+# field, which the operator syncs to Secret key `password`.
+apiVersion: onepassword.com/v1
+kind: OnePasswordItem
+metadata:
+  name: knowledge-mcp-tokens
+  namespace: agent-zero
+spec:
+  itemPath: "vaults/IAmWorkin/items/FlowerCore Knowledge MCP Tokens"
+
 ---
 apiVersion: apps/v1
 kind: Deployment
@@ -242,13 +254,30 @@ spec:
               sed -i 's/^              //' /a0/usr/plugins/_model_config/config.json
               # Phase 0 Chat MCP pilot: Agent Zero does not interpolate env vars
               # inside A0_SET_mcp_servers JSON, so build the final JSON here from
-              # the secret-backed CHAT_MCP_API_KEY env var before initialize.sh.
+              # the secret-backed env vars before initialize.sh. Keep the local
-              # Use the in-cluster Chat service URL rather than the public
+              # corpus_search.py tool mounted either way so outage fallback
-              # Traefik hostname so the pod stays off the private VIP lane that
+              # remains available even when fc_knowledge is not advertised.
-              # the default egress rule blocks.
+              export KNOWLEDGE_MCP_ENABLED=false
-              if [ -n "${CHAT_MCP_API_KEY:-}" ]; then
+              if [ -n "${KNOWLEDGE_MCP_BEARER_TOKEN:-}" ]; then
-                export A0_SET_mcp_servers="{\"mcpServers\":{\"fc-chat\":{\"type\":\"streamable-http\",\"url\":\"http://chat-web.fc-chat.svc/mcp\",\"headers\":{\"X-Api-Key\":\"${CHAT_MCP_API_KEY}\"}}}}"
+                if curl -sf --connect-timeout 3 "${KNOWLEDGE_MCP_HEALTH_URL}" > /dev/null && \
+                   curl -sf --connect-timeout 5 \
+                     -H "Authorization: Bearer ${KNOWLEDGE_MCP_BEARER_TOKEN}" \
+                     -H "Accept: application/json, text/event-stream" \
+                     -H "Content-Type: application/json" \
+                     -d '{"jsonrpc":"2.0","id":"fc-knowledge-bootstrap","method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"agent-zero-bootstrap","version":"1.0"}}}' \
+                     "${KNOWLEDGE_MCP_URL}" > /dev/null; then
+                  export KNOWLEDGE_MCP_ENABLED=true
+                  echo "fc_knowledge enabled from ${KNOWLEDGE_MCP_URL}."
+                else
+                  echo "fc_knowledge unavailable or unauthorized; keeping local corpus_search.py as the fallback path."
                 fi
+              else
+                echo "fc_knowledge token missing; keeping local corpus_search.py as the fallback path."
+              fi
+
+              export A0_SET_mcp_servers="$(
+                python3 -c 'import json, os; servers = {}; chat_key = os.getenv("CHAT_MCP_API_KEY"); knowledge_enabled = os.getenv("KNOWLEDGE_MCP_ENABLED", "false").lower() == "true"; token = os.getenv("KNOWLEDGE_MCP_BEARER_TOKEN", "") if knowledge_enabled else ""; chat_key and servers.setdefault("fc_chat", {"type": "streamable-http", "url": "http://chat-web.fc-chat.svc/mcp", "headers": {"X-Api-Key": chat_key}}); token and servers.setdefault("fc_knowledge", {"type": "streamable-http", "url": os.getenv("KNOWLEDGE_MCP_URL", "http://knowledge-web.knowledge.svc/mcp"), "headers": {"Authorization": f"Bearer {token}"}}); print(json.dumps({"mcpServers": servers}, separators=(",", ":")))'
+              )"
               # Run the original entrypoint
               exec /exe/initialize.sh $BRANCH
           ports:
@@ -351,6 +380,19 @@ spec:
                   name: chat-mcp-api-key
                   key: api-key
                   optional: true
+            # FlowerCore.Knowledge MCP Phase 1 — direct Agent Zero client path.
+            # Probe /healthz first, then try an authenticated initialize call.
+            # If either fails, Agent Zero boots without fc_knowledge and keeps
+            # the local corpus_search.py tool as the outage-safe path.
+            - name: KNOWLEDGE_MCP_URL
+              value: "http://knowledge-web.knowledge.svc/mcp"
+            - name: KNOWLEDGE_MCP_HEALTH_URL
+              value: "http://knowledge-web.knowledge.svc/healthz"
+            - name: KNOWLEDGE_MCP_BEARER_TOKEN
+              valueFrom:
+                secretKeyRef:
+                  name: knowledge-mcp-tokens
+                  key: password
             # Print.Web — Thermal printer service on edge2.
             # PRINT_WEB_URL: internal HTTP (bypasses Traefik TLS — print_web.py
             # runs in-cluster and can reach edge2 directly on the PROD VLAN).
@@ -575,6 +617,17 @@ spec:
           protocol: TCP
         - port: 8080
           protocol: TCP
+    # FlowerCore.Knowledge MCP (Phase 1) — in-cluster direct route with
+    # anonymous /healthz probe plus authenticated /mcp initialize/tool calls.
+    - to:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: knowledge
+      ports:
+        - port: 80
+          protocol: TCP
+        - port: 8080
+          protocol: TCP
     # Intranet search API — use in-cluster svc so traffic stays inside
     # the cluster and is not blocked by the private-range egress denylist.
     - to:

apps/asterisk/deployment.yaml

@@ -20,7 +20,19 @@ spec:
       nodeSelector:
         kubernetes.io/hostname: rke2-agent1
       hostNetwork: true
-      dnsPolicy: ClusterFirstWithHostNet
+      # Keep the search list free of iamworkin.lan so CoreDNS's wildcard
+      # template cannot hijack public egress like downloads.asterisk.org.
+      dnsPolicy: None
+      dnsConfig:
+        nameservers:
+          - 10.43.0.10
+        searches:
+          - telephony.svc.cluster.local
+          - svc.cluster.local
+          - cluster.local
+        options:
+          - name: ndots
+            value: "2"
       securityContext:
         fsGroup: 0
       # CoreDNS in this cluster has an iamworkin.lan wildcard that catches

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/cdi/README.md

@@ -0,0 +1,69 @@
+# CDI — Containerized Data Importer
+
+KubeVirt's `containerized-data-importer` for populating PVCs from external
+sources (HTTP, HTTPS, container registry, S3, virtctl upload). Required to
+import the Windows Server 2025 ISO into the `windows-server-2025-iso` PVC
+that `apps/kubevirt-vms/ci1.yaml` mounts as a CDROM.
+
+## Files
+
+| File              | Source                                                                                                            | Purpose                                            |
+| ----------------- | ----------------------------------------------------------------------------------------------------------------- | -------------------------------------------------- |
+| `cdi-operator.yaml` | [`v1.65.0`](https://github.com/kubevirt/containerized-data-importer/releases/tag/v1.65.0) — verbatim copy        | Installs operator + CRDs (5779 lines, large)       |
+| `cdi-cr.yaml`     | [`v1.65.0`](https://github.com/kubevirt/containerized-data-importer/releases/tag/v1.65.0) — annotated + commented | Tells operator to deploy CDI components          |
+
+`cdi-operator.yaml` is **vendored verbatim** from the upstream release for
+air-gap reproducibility (no internet fetch at deploy time, ArgoCD prune
+contracts hold). To bump versions:
+
+```bash
+CDI_VER=v1.66.0  # for example
+curl -sL "https://github.com/kubevirt/containerized-data-importer/releases/download/${CDI_VER}/cdi-operator.yaml" \
+  -o apps/cdi/cdi-operator.yaml
+curl -sL "https://github.com/kubevirt/containerized-data-importer/releases/download/${CDI_VER}/cdi-cr.yaml" \
+  -o /tmp/cdi-cr-new.yaml  # then re-apply project header diff
+git diff apps/cdi/  # review
+git commit + push
+```
+
+## Verify after deploy
+
+```bash
+kubectl -n cdi get pods               # operator + apiserver + deployment + uploadproxy
+kubectl get cdis cdi -o jsonpath='{.status.phase}'  # "Deployed"
+kubectl get crd | grep cdi.kubevirt.io
+# Expected CRDs: datavolumes.cdi.kubevirt.io, cdiconfigs.cdi.kubevirt.io,
+# storageprofiles.cdi.kubevirt.io, dataimportcrons.cdi.kubevirt.io,
+# datasources.cdi.kubevirt.io, objecttransfers.cdi.kubevirt.io
+```
+
+## Use after install
+
+```yaml
+# Example DataVolume that imports from HTTP
+apiVersion: cdi.kubevirt.io/v1beta1
+kind: DataVolume
+metadata:
+  name: my-iso
+spec:
+  source:
+    http:
+      url: "https://server/path/to.iso"
+  pvc:
+    accessModes: [ReadWriteOnce]
+    resources:
+      requests:
+        storage: 10Gi
+    storageClassName: longhorn
+```
+
+```bash
+# Or upload from local disk via virtctl
+virtctl image-upload pvc my-iso \
+  --image-path ./my.iso \
+  --size 10Gi \
+  --storage-class longhorn \
+  --access-mode ReadWriteOnce \
+  --uploadproxy-url https://cdi-uploadproxy.cdi.svc:443 \
+  --insecure
+```

apps/cdi/cdi-cr.yaml

@@ -0,0 +1,36 @@
+# =============================================================================
+# CDI CR — Tells the CDI operator to install CDI components into the cluster.
+# =============================================================================
+# After cdi-operator.yaml is applied, the operator watches for THIS resource
+# (CDI named "cdi"). When found, it deploys cdi-apiserver, cdi-deployment,
+# cdi-uploadproxy, cdi-cronjob, and the importer/uploadserver/cloner pods.
+#
+# Configuration:
+#   - HonorWaitForFirstConsumer: PVCs created by DataVolumes wait for first
+#     pod to schedule before binding (lets storage class pick best node).
+#   - WebhookPvcRendering: validates PVC creation against CDI policies.
+#   - imagePullPolicy IfNotPresent: re-pull only on tag rotation.
+#   - nodeSelector linux: pin to Linux nodes (no Windows worker support).
+#
+# Andrew may want to add a `uploadProxyURLOverride` later to expose the
+# uploadproxy via Traefik IngressRoute for `virtctl image-upload` from
+# BLUEJAY-WS without `kubectl port-forward`. Phase 2 enhancement.
+# =============================================================================
+apiVersion: cdi.kubevirt.io/v1beta1
+kind: CDI
+metadata:
+  name: cdi
+  annotations:
+    bluejay.iamworkin.lan/source: "kubevirt/containerized-data-importer v1.65.0"
+spec:
+  config:
+    featureGates:
+    - HonorWaitForFirstConsumer
+    - WebhookPvcRendering
+  imagePullPolicy: IfNotPresent
+  infra:
+    nodeSelector:
+      kubernetes.io/os: linux
+  workload:
+    nodeSelector:
+      kubernetes.io/os: linux

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-desktop/fc-desktop.yaml

@@ -1,5 +1,18 @@
 # FlowerCore Remote Desktop — TLS + Ingress
-# Deployment and Service managed by deploy script (not ArgoCD)
+#
+# Source-of-truth split:
+#   - bluejay-infra OWNS: Certificate, IngressRoute, all NetworkPolicies
+#     (see network-policies.yaml in this directory).
+#   - FlowerCore.RemoteDesktop scripts/deploy-web.sh OWNS: Deployment +
+#     Service. Reason: image refs like `localhost/fc-desktop:linux-xfce`
+#     only exist on each node's containerd after a manual import, so a
+#     Deployment manifest in bluejay-infra would race the image-import
+#     step and crash-loop.
+#
+# NetworkPolicies moved into bluejay-infra 2026-05-07 — previously they
+# were applied via the deploy script's kubectl apply calls, which broke
+# cluster-rebuild repeatability. See
+# feedback_networkpolicies_belong_in_bluejay_infra.md.
 ---
 apiVersion: cert-manager.io/v1
 kind: Certificate

apps/fc-desktop/network-policies.yaml

@@ -0,0 +1,332 @@
+# FlowerCore Remote Desktop — NetworkPolicies (GitOps-managed)
+#
+# Moved into bluejay-infra 2026-05-07 as part of the regroup audit. These
+# four policies were previously applied via FlowerCore.RemoteDesktop's
+# scripts/deploy-web.sh `kubectl apply` calls, which meant a fresh cluster
+# rebuild from bluejay-infra alone would miss them — Browser Lab session
+# isolation, control-plane allow-list, and HTTP-01 cert renewal would all
+# silently fail to come up.
+#
+# Source-of-truth contract:
+#   - bluejay-infra OWNS all NetworkPolicy + Certificate + IngressRoute
+#     resources for fc-desktop.
+#   - FlowerCore.RemoteDesktop's scripts/deploy-web.sh continues to own
+#     the Deployment + Service apply (because the image ref
+#     `localhost/fc-desktop:linux-xfce` only exists on each node's
+#     containerd after a manual import — it can't be pulled from a
+#     registry, so a Deployment manifest in bluejay-infra would race the
+#     image-import step and crash-loop).
+---
+# 1) desktop-isolation — Browser Lab session pods.
+#
+# Locks down pods labeled `app.kubernetes.io/name=remote-desktop` (every
+# session pod regardless of template). Allows guacd ingress for the VNC/RDP
+# display lane and remotedesktop-web's pre-handoff probing. Egress: NFS to
+# Synology, DNS, Traefik (cluster + LB VIP), Intranet (Browser Lab home).
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: desktop-isolation
+  namespace: fc-desktop
+  labels:
+    app.kubernetes.io/part-of: remotedesktop
+    app.kubernetes.io/component: isolation
+spec:
+  podSelector:
+    matchLabels:
+      app.kubernetes.io/name: remote-desktop
+  policyTypes:
+    - Ingress
+    - Egress
+  ingress:
+    - from:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: guacamole
+      ports:
+        - port: 3000
+          protocol: TCP
+        - port: 3001
+          protocol: TCP
+        - port: 5901
+          protocol: TCP
+        - port: 3389
+          protocol: TCP
+    - from:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: fc-desktop
+          podSelector:
+            matchLabels:
+              app.kubernetes.io/name: remotedesktop-web
+      ports:
+        - port: 3000
+          protocol: TCP
+        - port: 5901
+          protocol: TCP
+  egress:
+    # NFS to Synology
+    - 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
+    - to:
+        - ipBlock:
+            cidr: 10.0.58.3/32
+      ports:
+        - port: 445
+          protocol: TCP
+    - to: []
+      ports:
+        - port: 53
+          protocol: UDP
+        - port: 53
+          protocol: TCP
+    - to:
+        - ipBlock:
+            cidr: 10.0.56.200/32
+        - ipBlock:
+            cidr: 10.43.33.87/32
+        - 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: 8000
+          protocol: TCP
+        - port: 8443
+          protocol: TCP
+    - to:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: intranet
+          podSelector:
+            matchLabels:
+              app: intranet-web
+      ports:
+        - port: 5300
+          protocol: TCP
+---
+# 2) fc-desktop-default-deny — namespace-wide catch-all.
+#
+# Selects every pod EXCEPT remotedesktop-web (the public-surface control
+# plane) and applies default-deny semantics for both Ingress and Egress.
+# Closes the gap where session pods land WITHOUT the desktop-isolation
+# policy's `app.kubernetes.io/name=remote-desktop` label, plus prevents
+# arbitrary debug sidecars / kubectl debug images from getting cluster
+# access.
+#
+# CRITICAL: also catches transient cm-acme-http-solver pods (that's the
+# bug this whole regroup chased). The cm-acme-http-solver-allow policy
+# below is the explicit carve-out.
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: fc-desktop-default-deny
+  namespace: fc-desktop
+  labels:
+    app.kubernetes.io/part-of: remotedesktop
+    app.kubernetes.io/component: isolation
+spec:
+  podSelector:
+    matchExpressions:
+      - key: app.kubernetes.io/name
+        operator: NotIn
+        values:
+          - remotedesktop-web
+  policyTypes:
+    - Ingress
+    - Egress
+---
+# 3) remotedesktop-web-isolation — control plane explicit allow-list.
+#
+# remotedesktop-web is the only pod label the default-deny excludes, so
+# without this policy the control plane would have wide-open Ingress AND
+# Egress. This re-introduces a tight allow-list:
+#   - Ingress: Traefik only on TCP/8080
+#   - Egress: CoreDNS, K8s API, Guacamole admin, NFS, Intranet,
+#     Traefik (cluster + LB), and the fc-desktop namespace itself
+#     (for session pod readiness probing).
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: remotedesktop-web-isolation
+  namespace: fc-desktop
+  labels:
+    app.kubernetes.io/part-of: remotedesktop
+    app.kubernetes.io/component: isolation
+spec:
+  podSelector:
+    matchLabels:
+      app.kubernetes.io/name: remotedesktop-web
+  policyTypes:
+    - Ingress
+    - Egress
+  ingress:
+    - from:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: traefik-system
+          podSelector:
+            matchLabels:
+              app.kubernetes.io/name: traefik
+      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
+    # K8s API server
+    - to: []
+      ports:
+        - port: 443
+          protocol: TCP
+        - port: 6443
+          protocol: TCP
+    # Guacamole admin
+    - to:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: guacamole
+      ports:
+        - port: 8080
+          protocol: TCP
+    # NFS to Synology
+    - 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
+    # Intranet web
+    - to:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: intranet
+          podSelector:
+            matchLabels:
+              app: intranet-web
+      ports:
+        - port: 5300
+          protocol: TCP
+    # Cluster Traefik pods (in-cluster service resolution + Guacamole
+    # routing handoff where web app builds URLs against the public host
+    # but resolves internally).
+    - to:
+        - 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
+    # fc-desktop namespace — session pod probing during browser-access
+    # readiness checks.
+    - to:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: fc-desktop
+      ports:
+        - port: 3000
+          protocol: TCP
+        - port: 3001
+          protocol: TCP
+        - port: 5901
+          protocol: TCP
+        - port: 3389
+          protocol: TCP
+---
+# 4) cm-acme-http-solver-allow — cert-manager HTTP-01 carve-out.
+#
+# Without this, fc-desktop-default-deny catches the transient solver pods
+# cert-manager creates for each renewal (they don't carry the
+# remotedesktop-web label). Caused 8-day silent renewal failure on
+# desktop.iamworkin.lan in 2026-04-28..2026-05-07 (see
+# feedback_certmanager_renewal_stuck_when_solver_blocked_by_namespace_default_deny.md).
+#
+# Authorizes:
+#   - Ingress on TCP/8089 from cluster Traefik (which proxies the external
+#     HTTP-01 GET on port 80 through to the solver).
+#   - Egress for cluster DNS (defensive — newer cert-manager probes from
+#     inside the solver too).
+#
+# The `acme.cert-manager.io/http01-solver=true` label is set by
+# cert-manager itself on every solver pod automatically.
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: cm-acme-http-solver-allow
+  namespace: fc-desktop
+  labels:
+    app.kubernetes.io/part-of: remotedesktop
+    app.kubernetes.io/component: cert-renewal
+spec:
+  podSelector:
+    matchLabels:
+      acme.cert-manager.io/http01-solver: "true"
+  policyTypes:
+    - Ingress
+    - Egress
+  ingress:
+    - from:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: traefik-system
+          podSelector:
+            matchLabels:
+              app.kubernetes.io/name: traefik
+      ports:
+        - port: 8089
+          protocol: TCP
+  egress:
+    - to:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: kube-system
+          podSelector:
+            matchLabels:
+              k8s-app: kube-dns
+      ports:
+        - port: 53
+          protocol: UDP
+        - port: 53
+          protocol: TCP

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-distribution/fc-distribution.yaml

@@ -118,7 +118,7 @@ spec:
           #   dotnet.exe publish -c Release -o deploy/app \
           #     src/FlowerCore.Distribution.Web/FlowerCore.Distribution.Web.csproj
           #   podman build -t localhost/fc-distribution:v<tag> -f deploy/Dockerfile.deploy deploy
-          image: localhost/fc-distribution:v202604240010
+          image: localhost/fc-distribution:v202605061948
           imagePullPolicy: Never
           ports:
             - containerPort: 8080
@@ -151,6 +151,10 @@ spec:
               value: "/signing/aistation-field/chain.pem"
             - name: FlowerCore__Distribution__Signing__EditionCerts__aistation-field__KeyPath
               value: "/signing/aistation-field/private-key.pem"
+            # Public distribution host is GET/HEAD-only at Traefik; this
+            # entitlement list controls which editions are readable there.
+            - name: FlowerCore__Distribution__EntitlementPublic__PublicEditions__0
+              value: "*"
           resources:
             requests:
               cpu: 100m
@@ -262,8 +266,12 @@ spec:
     kind: ClusterIssuer
   dnsNames:
     - dist.iamworkin.lan
-  duration: 2160h    # 90d
+  # step-ca ACME caps lifetime at 30d; requesting 90d silently capped
-  renewBefore: 720h  # 30d
+  # made renewBefore=cert-lifetime → perpetual renewal loop (10880+ CRs
+  # in 18h on 2026-05-07). Match working 720h/240h pattern from other
+  # FC services.
+  duration: 720h     # 30d (step-ca cap)
+  renewBefore: 240h  # 10d
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute

apps/fc-divoom-dm-pi-device/README.md

@@ -0,0 +1,45 @@
+# FlowerCore Divoom DM Pi Device
+
+Source-controlled Puppet/Hiera deployment contract for registering the edge2
+Divoom MiniToo panel as a FlowerCore DeviceManagement-managed Pi device.
+
+This is not a Kubernetes application. The live panel remains the existing
+edge2 `flowercore-divoom.service` managed by `FlowerCore.Puppet`
+`profile::pi::service::divoom`, with the .NET payload deployed out of band
+and `/opt/flowercore/divoom/data` plus the Bluetooth shell wrappers preserved.
+Because edge2 is already Hiera-driven through `profile::pi::service::apps`,
+the deploy home is additive `profile::pi::service` data/profile source, not
+`profile::edge::service::apps` and not an ArgoCD/K8s app.
+
+## Scope
+
+- Stage DeviceManagement registration metadata for the edge2 Divoom MiniToo.
+- Stage a separate, disabled-by-default DM Agent executor unit for privileged
+  Bluetooth operations once the DM-RPC lane lands.
+- Keep `flowercore-divoom.service` and `flowercore-divoom-bt.service`
+  untouched: no service replacement, no restart subscription, no K8s surface.
+- Preserve the current wrapper contract:
+  `/opt/flowercore/divoom/bt-link.sh`,
+  `/opt/flowercore/divoom/bt-reset.sh`, and
+  `/opt/flowercore/divoom/audio-link.sh`.
+- Keep FM radio disabled and require visible render proof; device-info echo is
+  not render proof.
+
+## Artifact Map
+
+| Path | Use |
+| --- | --- |
+| `hiera/edge2-divoom-dm-device.overlay.yaml` | Additive Hiera overlay for edge2. Merge into the existing node YAML without removing `fc-pimanager` or `fc-divoom`. |
+| `puppet/profile/pi/service/divoom_dm_device.pp` | Puppet profile shape to vendor into `FlowerCore.Puppet` after the DM-RPC executor binary exists. |
+| `puppet/templates/divoom-device-registration.json.epp` | DM device registration metadata rendered on edge2. |
+| `puppet/templates/flowercore-divoom-dm-agent.service.epp` | Separate DM Agent systemd unit. Defaults are stopped and disabled until a later cutover. |
+
+## Rollout Notes
+
+1. Land these artifacts in bluejay-infra as the deploy contract.
+2. Vendor the Puppet profile and EPP templates into `FlowerCore.Puppet`.
+3. Merge the Hiera overlay into `data/nodes/edge2.iamworkin.lan.yaml`.
+4. Run Puppet in noop first, preferably with a node-local validation directory
+   under `~/.fcv` rather than `/tmp`.
+5. Only enable the DM Agent service after the DeviceManagement BT executor has
+   landed and passed operator-eyeball render proof.

apps/fc-divoom-dm-pi-device/hiera/edge2-divoom-dm-device.overlay.yaml

@@ -0,0 +1,32 @@
+---
+# Merge into FlowerCore.Puppet data/nodes/edge2.iamworkin.lan.yaml.
+# Additive overlay only: keep the existing fc-pimanager version/tarball entry,
+# keep fc-divoom enabled, and do not move Divoom into Kubernetes.
+
+profile::pi::service::apps:
+  fc-pimanager:
+    binary: 'FlowerCore.PiManager.Web'
+    install_dir: '/opt/fc-pimanager'
+    port: 5000
+    environment: 'edge2'
+    version: '2026.05.28.1646'
+    tarball_source: 'puppet:///modules/profile/pi/builds/fc-pimanager.tar.gz'
+  fc-divoom:
+    enabled: true
+
+profile::pi::service::divoom_dm_device::ensure: 'present'
+profile::pi::service::divoom_dm_device::service_enabled: false
+profile::pi::service::divoom_dm_device::service_ensure: 'stopped'
+profile::pi::service::divoom_dm_device::device_id: 'edge2-divoom-minitoo'
+profile::pi::service::divoom_dm_device::display_name: 'edge2 Divoom MiniToo'
+profile::pi::service::divoom_dm_device::host_fqdn: 'edge2.iamworkin.lan'
+profile::pi::service::divoom_dm_device::dm_web_url: 'https://devicemgmt.iamworkin.lan'
+profile::pi::service::divoom_dm_device::divoom_install_dir: '/opt/flowercore/divoom'
+profile::pi::service::divoom_dm_device::agent_install_dir: '/opt/flowercore/devicemanagement-agent'
+profile::pi::service::divoom_dm_device::bt_candidate_channels:
+  - '1'
+  - '10'
+profile::pi::service::divoom_dm_device::default_bt_channel: '1'
+profile::pi::service::divoom_dm_device::a2dp_default_state: 'off'
+profile::pi::service::divoom_dm_device::fm_radio_enabled: false
+profile::pi::service::divoom_dm_device::visible_render_proof_required: true

apps/fc-divoom-dm-pi-device/puppet/profile/pi/service/divoom_dm_device.pp

@@ -0,0 +1,140 @@
+# Drop into FlowerCore.Puppet site-modules/profile/manifests/pi/service/divoom_dm_device.pp.
+# This profile is additive to profile::pi::service::divoom. It must not manage,
+# restart, replace, or subscribe the existing flowercore-divoom.service.
+class profile::pi::service::divoom_dm_device (
+  Enum['present', 'absent'] $ensure = 'present',
+  Boolean $service_enabled = false,
+  Enum['running', 'stopped'] $service_ensure = 'stopped',
+  String $service_name = 'flowercore-divoom-dm-agent',
+  String $device_id = 'edge2-divoom-minitoo',
+  String $display_name = 'edge2 Divoom MiniToo',
+  String $host_fqdn = 'edge2.iamworkin.lan',
+  String $dm_web_url = 'https://devicemgmt.iamworkin.lan',
+  String $divoom_install_dir = '/opt/flowercore/divoom',
+  String $agent_install_dir = '/opt/flowercore/devicemanagement-agent',
+  String $agent_binary = 'FlowerCore.DeviceManagement.Agent',
+  Array[String] $bt_candidate_channels = ['1', '10'],
+  String $default_bt_channel = '1',
+  Enum['on', 'off'] $a2dp_default_state = 'off',
+  Boolean $fm_radio_enabled = false,
+  Boolean $visible_render_proof_required = true,
+) {
+  include profile::workstation::safe_account_exclusion
+
+  $safe_account = $profile::workstation::safe_account_exclusion::safe_account
+  $config_dir = '/etc/flowercore/device-management/devices'
+  $state_dir = '/var/lib/flowercore/divoom-dm-agent'
+  $log_dir = '/var/log/flowercore/divoom-dm-agent'
+  $registration_path = "${config_dir}/${device_id}.json"
+  $agent_binary_path = "${agent_install_dir}/${agent_binary}"
+  $bt_channels_json = inline_template('[<%= @bt_candidate_channels.map { |c| "\"#{c}\"" }.join(", ") %>]')
+
+  if $safe_account {
+    notify { 'fc-divoom-dm-device safe-account exclusion':
+      message => 'SAFE-ACCOUNT-EXCLUSION: Divoom DM Pi device profile refused to apply on operator workstation',
+    }
+
+    if $facts['os']['family'] != 'windows' {
+      ensure_resource('file', '/var/log/flowercore-audit', {
+          'ensure' => 'directory',
+          'owner'  => 'root',
+          'group'  => 'root',
+          'mode'   => '0755',
+      })
+
+      file { '/var/log/flowercore-audit/safe-account-noop-fc-divoom-dm-device.log':
+        ensure  => file,
+        owner   => 'root',
+        group   => 'root',
+        mode    => '0644',
+        content => "noop: divoom dm pi device profile refused to apply on safe-account host\n",
+        require => File['/var/log/flowercore-audit'],
+      }
+    }
+  } elsif $ensure == 'absent' {
+    service { $service_name:
+      ensure => stopped,
+      enable => false,
+    }
+
+    file { [
+        "/etc/systemd/system/${service_name}.service",
+        $registration_path,
+      ]:
+      ensure => absent,
+    }
+
+    exec { 'fc-divoom-dm-agent-systemd-reload':
+      command     => '/usr/bin/systemctl daemon-reload',
+      refreshonly => true,
+      path        => ['/usr/bin', '/bin'],
+    }
+  } else {
+    case $facts['os']['family'] {
+      'Debian': {}
+      default: { fail("profile::pi::service::divoom_dm_device only supports Debian-family OS, got ${facts['os']['family']}") }
+    }
+
+    file { [$config_dir, $state_dir, $log_dir]:
+      ensure => directory,
+      owner  => 'root',
+      group  => 'root',
+      mode   => '0755',
+    }
+
+    file { $registration_path:
+      ensure  => file,
+      owner   => 'root',
+      group   => 'root',
+      mode    => '0644',
+      content => epp('profile/pi/fc_divoom_dm/divoom-device-registration.json.epp', {
+        'device_id'                     => $device_id,
+        'display_name'                  => $display_name,
+        'host_fqdn'                     => $host_fqdn,
+        'divoom_install_dir'            => $divoom_install_dir,
+        'bt_channels_json'              => $bt_channels_json,
+        'default_bt_channel'            => $default_bt_channel,
+        'a2dp_default_state'            => $a2dp_default_state,
+        'fm_radio_enabled'              => $fm_radio_enabled,
+        'visible_render_proof_required' => $visible_render_proof_required,
+      }),
+      require => File[$config_dir],
+    }
+
+    file { "/etc/systemd/system/${service_name}.service":
+      ensure  => file,
+      owner   => 'root',
+      group   => 'root',
+      mode    => '0644',
+      content => epp('profile/pi/fc_divoom_dm/flowercore-divoom-dm-agent.service.epp', {
+        'service_name'       => $service_name,
+        'device_id'          => $device_id,
+        'dm_web_url'         => $dm_web_url,
+        'registration_path'  => $registration_path,
+        'divoom_install_dir' => $divoom_install_dir,
+        'agent_install_dir'  => $agent_install_dir,
+        'agent_binary_path'  => $agent_binary_path,
+        'state_dir'          => $state_dir,
+        'log_dir'            => $log_dir,
+      }),
+      notify  => Exec['fc-divoom-dm-agent-systemd-reload'],
+      require => File[$registration_path],
+    }
+
+    exec { 'fc-divoom-dm-agent-systemd-reload':
+      command     => '/usr/bin/systemctl daemon-reload',
+      refreshonly => true,
+      path        => ['/usr/bin', '/bin'],
+    }
+
+    service { $service_name:
+      ensure  => $service_ensure,
+      enable  => $service_enabled,
+      require => [
+        File["/etc/systemd/system/${service_name}.service"],
+        File[$registration_path],
+        Exec['fc-divoom-dm-agent-systemd-reload'],
+      ],
+    }
+  }
+}

apps/fc-divoom-dm-pi-device/puppet/templates/divoom-device-registration.json.epp

@@ -0,0 +1,34 @@
+{
+  "deviceId": "<%= $device_id %>",
+  "displayName": "<%= $display_name %>",
+  "hostFqdn": "<%= $host_fqdn %>",
+  "kind": "DivoomMiniToo",
+  "managedBy": "FlowerCore.DeviceManagement",
+  "executionMode": "Pi",
+  "transport": {
+    "kind": "BluetoothSerial",
+    "candidateChannels": <%= $bt_channels_json %>,
+    "defaultChannel": "<%= $default_bt_channel %>",
+    "deviceInfoIsRenderProof": false,
+    "visibleRenderProofRequired": <%= $visible_render_proof_required %>
+  },
+  "paths": {
+    "divoomInstallDir": "<%= $divoom_install_dir %>",
+    "btLink": "<%= $divoom_install_dir %>/bt-link.sh",
+    "btReset": "<%= $divoom_install_dir %>/bt-reset.sh",
+    "audioLink": "<%= $divoom_install_dir %>/audio-link.sh"
+  },
+  "capabilities": {
+    "supportsBluetoothSerial": true,
+    "supportsBtChannelRedetect": true,
+    "supportsBtHardReset": true,
+    "supportsBtAudioProfileSwitch": true,
+    "a2dpDefaultState": "<%= $a2dp_default_state %>",
+    "fmRadioEnabled": <%= $fm_radio_enabled %>
+  },
+  "safety": {
+    "preserveExistingService": "flowercore-divoom.service",
+    "preserveDataDirectory": "<%= $divoom_install_dir %>/data",
+    "doNotEnableFmRadio": true
+  }
+}

apps/fc-divoom-dm-pi-device/puppet/templates/flowercore-divoom-dm-agent.service.epp

@@ -0,0 +1,36 @@
+[Unit]
+Description=FlowerCore Divoom DM Agent Bluetooth executor
+Documentation=https://github.com/astoltz/FlowerCore.Notes/blob/master/docs/standards/divoom-tv-hdmi-multitarget-render-substrate.md
+Wants=network-online.target
+After=network-online.target bluetooth.service
+Requires=bluetooth.service
+ConditionPathExists=<%= $agent_binary_path %>
+ConditionPathExists=<%= $registration_path %>
+ConditionPathExists=<%= $divoom_install_dir %>/bt-link.sh
+ConditionPathExists=<%= $divoom_install_dir %>/bt-reset.sh
+ConditionPathExists=<%= $divoom_install_dir %>/audio-link.sh
+
+[Service]
+Type=simple
+User=stoltz
+Group=stoltz
+WorkingDirectory=<%= $agent_install_dir %>
+Environment=DOTNET_CLI_TELEMETRY_OPTOUT=1
+Environment=FLOWERCORE_DM_DEVICE_REGISTRATION=<%= $registration_path %>
+Environment=Divoom__Bluetooth__DeviceInfoIsRenderProof=false
+Environment=Divoom__Bluetooth__VisibleRenderProofRequired=true
+Environment=Divoom__Bluetooth__A2dpDefaultState=off
+ExecStart=<%= $agent_binary_path %> --mode=Pi --device-id=<%= $device_id %> --dm-web-url=<%= $dm_web_url %> --registration=<%= $registration_path %>
+Restart=on-failure
+RestartSec=10s
+StartLimitBurst=3
+StartLimitIntervalSec=300s
+SupplementaryGroups=bluetooth audio dialout
+NoNewPrivileges=true
+PrivateTmp=true
+ProtectSystem=strict
+ProtectHome=true
+ReadWritePaths=<%= $state_dir %> <%= $log_dir %>
+
+[Install]
+WantedBy=multi-user.target

apps/fc-divoom-tv-pi/README.md

@@ -0,0 +1,44 @@
+# FlowerCore Divoom TV Pi HDMI
+
+Source-controlled deploy shape for the native `FlowerCore.Divoom.Tv`
+Avalonia HDMI renderer on a Raspberry Pi connected to a TV.
+
+This is a Puppet/systemd appliance bundle, not a Kubernetes application. It
+mirrors the existing `fc-signage-pi-player` pattern: bluejay-infra carries the
+systemd units, scripts, Hiera shape, and Puppet profile source that
+`FlowerCore.Puppet` vendors and installs.
+
+## Scope
+
+- Launch the future `FlowerCore.Divoom.Tv` linux-arm64 self-contained payload
+  from `/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv`.
+- Prefer `cage` as the Wayland fullscreen compositor, with direct app launch as
+  a fallback for development images.
+- Restart the app after HDMI hotplug with a 2 second DRM settle delay.
+- Keep all runtime state local: `/var/lib/fc-divoom-tv` and
+  `/var/log/fc-divoom-tv`.
+- Avoid CDN/runtime fetches; the app renders the in-house Divoom scene catalog
+  locally.
+
+## Artifact Map
+
+| Path | Use |
+| --- | --- |
+| `systemd/flowercore-divoom-tv.service` | Fullscreen Avalonia HDMI app service. |
+| `systemd/flowercore-divoom-tv-hdmi.service` | HDMI hotplug responder service. |
+| `systemd/99-flowercore-divoom-tv-hdmi.rules` | DRM udev hotplug rule. |
+| `scripts/flowercore-divoom-tv-prelaunch.sh` | Preflight checks and local directory creation. |
+| `scripts/flowercore-divoom-tv-launch.sh` | Cage-first fullscreen launcher. |
+| `scripts/flowercore-divoom-tv-hdmi-respond.sh` | Hotplug settle and restart script. |
+| `puppet/profile/pi/service/divoom_tv.pp` | Puppet profile shape to vendor into `FlowerCore.Puppet`. |
+| `hiera/example-divoom-tv-pi.iamworkin.lan.yaml` | Example node Hiera for a Divoom TV Pi. |
+
+## Rollout Notes
+
+1. Build `FlowerCore.Divoom.Tv` with `dotnet.exe publish -c Release -r linux-arm64 --self-contained`.
+2. Stage the payload to `/opt/flowercore/divoom-tv/` through the standard noc1
+   jump path and avoid `/tmp` for unprivileged Pi scratch.
+3. Vendor the profile and static files into `FlowerCore.Puppet`.
+4. Run Puppet noop, then apply on the target Pi.
+5. Prove deployment with `systemctl is-active flowercore-divoom-tv.service`,
+   journal lines showing frames presented, and a visible HDMI display check.

apps/fc-divoom-tv-pi/hiera/example-divoom-tv-pi.iamworkin.lan.yaml

@@ -0,0 +1,19 @@
+---
+# Example node data for a dedicated Pi -> HDMI -> TV Divoom renderer.
+# Copy into FlowerCore.Puppet data/nodes/<hostname>.iamworkin.lan.yaml only
+# after the Pi has a static DHCP/DNS entry and the linux-arm64 payload exists.
+
+facts:
+  role: pi_prototype
+
+profile::motd::role: 'Divoom TV HDMI Renderer'
+
+profile::pi::service::divoom_tv::ensure: 'present'
+profile::pi::service::divoom_tv::service_enabled: true
+profile::pi::service::divoom_tv::service_ensure: 'running'
+profile::pi::service::divoom_tv::install_dir: '/opt/flowercore/divoom-tv'
+profile::pi::service::divoom_tv::state_dir: '/var/lib/fc-divoom-tv'
+profile::pi::service::divoom_tv::log_dir: '/var/log/fc-divoom-tv'
+profile::pi::service::divoom_tv::presentation_mode: 'PillarboxSquare'
+profile::pi::service::divoom_tv::startup_scene: 'bluejay-clock'
+profile::pi::service::divoom_tv::reduced_motion: false

apps/fc-divoom-tv-pi/puppet/profile/pi/service/divoom_tv.pp

@@ -0,0 +1,149 @@
+# Drop into FlowerCore.Puppet site-modules/profile/manifests/pi/service/divoom_tv.pp.
+# Static files come from profile/pi/fc_divoom_tv/ after this bluejay-infra
+# bundle is vendored into the Puppet control repo.
+class profile::pi::service::divoom_tv (
+  Enum['present', 'absent'] $ensure = 'present',
+  Boolean $service_enabled = false,
+  Enum['running', 'stopped'] $service_ensure = 'stopped',
+  String $service_name = 'flowercore-divoom-tv',
+  String $user = 'fc-divoom-tv',
+  String $group = 'fc-divoom-tv',
+  String $install_dir = '/opt/flowercore/divoom-tv',
+  String $state_dir = '/var/lib/fc-divoom-tv',
+  String $log_dir = '/var/log/fc-divoom-tv',
+  String $presentation_mode = 'PillarboxSquare',
+  String $startup_scene = 'bluejay-clock',
+  Boolean $reduced_motion = false,
+) {
+  include profile::workstation::safe_account_exclusion
+
+  $safe_account = $profile::workstation::safe_account_exclusion::safe_account
+
+  if $safe_account {
+    notify { 'fc-divoom-tv safe-account exclusion':
+      message => 'SAFE-ACCOUNT-EXCLUSION: Divoom TV Pi profile refused to apply on operator workstation',
+    }
+  } elsif $ensure == 'absent' {
+    service { $service_name:
+      ensure => stopped,
+      enable => false,
+    }
+
+    file { [
+        "/etc/systemd/system/${service_name}.service",
+        "/etc/systemd/system/${service_name}-hdmi.service",
+        '/etc/udev/rules.d/99-flowercore-divoom-tv-hdmi.rules',
+        '/usr/local/bin/flowercore-divoom-tv-prelaunch.sh',
+        '/usr/local/bin/flowercore-divoom-tv-launch.sh',
+        '/usr/local/bin/flowercore-divoom-tv-hdmi-respond.sh',
+        '/etc/flowercore/divoom-tv.env',
+      ]:
+      ensure => absent,
+    }
+  } else {
+    case $facts['os']['family'] {
+      'Debian': {}
+      default: { fail("profile::pi::service::divoom_tv only supports Debian-family OS, got ${facts['os']['family']}") }
+    }
+
+    package { ['cage', 'libgbm1', 'libdrm2', 'libxkbcommon0', 'fonts-dejavu-core']:
+      ensure => installed,
+    }
+
+    group { $group:
+      ensure => present,
+      system => true,
+    }
+
+    user { $user:
+      ensure     => present,
+      system     => true,
+      gid        => $group,
+      home       => $state_dir,
+      managehome => false,
+      shell      => '/usr/sbin/nologin',
+      require    => Group[$group],
+    }
+
+    file { [$install_dir, $state_dir, $log_dir, '/etc/flowercore']:
+      ensure => directory,
+      owner  => $user,
+      group  => $group,
+      mode   => '0755',
+    }
+
+    file { '/etc/flowercore/divoom-tv.env':
+      ensure  => file,
+      owner   => 'root',
+      group   => 'root',
+      mode    => '0644',
+      content => "FC_DIVOOM_TV_PRESENTATION_MODE=${presentation_mode}\nFC_DIVOOM_TV_START_SCENE=${startup_scene}\nFC_DIVOOM_TV_REDUCED_MOTION=${reduced_motion}\n",
+      require => File['/etc/flowercore'],
+    }
+
+    $script_map = {
+      '/usr/local/bin/flowercore-divoom-tv-prelaunch.sh'    => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv-prelaunch.sh',
+      '/usr/local/bin/flowercore-divoom-tv-launch.sh'       => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv-launch.sh',
+      '/usr/local/bin/flowercore-divoom-tv-hdmi-respond.sh' => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv-hdmi-respond.sh',
+    }
+
+    $script_map.each |$dest, $src| {
+      file { $dest:
+        ensure => file,
+        owner  => 'root',
+        group  => 'root',
+        mode   => '0755',
+        source => "puppet:///modules/${src}",
+      }
+    }
+
+    $unit_map = {
+      "/etc/systemd/system/${service_name}.service"      => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv.service',
+      "/etc/systemd/system/${service_name}-hdmi.service" => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv-hdmi.service',
+    }
+
+    $unit_map.each |$dest, $src| {
+      file { $dest:
+        ensure => file,
+        owner  => 'root',
+        group  => 'root',
+        mode   => '0644',
+        source => "puppet:///modules/${src}",
+        notify => Exec['fc-divoom-tv-systemd-reload'],
+      }
+    }
+
+    file { '/etc/udev/rules.d/99-flowercore-divoom-tv-hdmi.rules':
+      ensure => file,
+      owner  => 'root',
+      group  => 'root',
+      mode   => '0644',
+      source => 'puppet:///modules/profile/pi/fc_divoom_tv/99-flowercore-divoom-tv-hdmi.rules',
+      notify => Exec['fc-divoom-tv-udev-reload'],
+    }
+
+    exec { 'fc-divoom-tv-systemd-reload':
+      command     => '/usr/bin/systemctl daemon-reload',
+      refreshonly => true,
+      path        => ['/usr/bin', '/bin'],
+    }
+
+    exec { 'fc-divoom-tv-udev-reload':
+      command     => '/usr/bin/udevadm control --reload-rules',
+      refreshonly => true,
+      path        => ['/usr/bin', '/bin'],
+    }
+
+    service { $service_name:
+      ensure  => $service_ensure,
+      enable  => $service_enabled,
+      require => [
+        File["/etc/systemd/system/${service_name}.service"],
+        File['/etc/flowercore/divoom-tv.env'],
+        File['/usr/local/bin/flowercore-divoom-tv-prelaunch.sh'],
+        File['/usr/local/bin/flowercore-divoom-tv-launch.sh'],
+        Exec['fc-divoom-tv-systemd-reload'],
+      ],
+    }
+  }
+}

apps/fc-divoom-tv-pi/scripts/flowercore-divoom-tv-hdmi-respond.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+sleep 2
+systemctl restart flowercore-divoom-tv.service

apps/fc-divoom-tv-pi/scripts/flowercore-divoom-tv-launch.sh

@@ -0,0 +1,25 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+APP_BIN="${FC_DIVOOM_TV_BIN:-/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv}"
+STATE_DIR="${FC_DIVOOM_TV_STATE_DIR:-/var/lib/fc-divoom-tv}"
+LOG_DIR="${FC_DIVOOM_TV_LOG_DIR:-/var/log/fc-divoom-tv}"
+PRESENTATION_MODE="${FC_DIVOOM_TV_PRESENTATION_MODE:-PillarboxSquare}"
+START_SCENE="${FC_DIVOOM_TV_START_SCENE:-bluejay-clock}"
+REDUCED_MOTION="${FC_DIVOOM_TV_REDUCED_MOTION:-false}"
+
+COMMON_ARGS=(
+  "--target=hdmi"
+  "--presentation-mode=${PRESENTATION_MODE}"
+  "--startup-scene=${START_SCENE}"
+  "--reduced-motion=${REDUCED_MOTION}"
+  "--state-dir=${STATE_DIR}"
+  "--log-dir=${LOG_DIR}"
+)
+
+if command -v cage >/dev/null 2>&1; then
+  exec cage -- "${APP_BIN}" "${COMMON_ARGS[@]}" "$@"
+fi
+
+echo "[$(date -Is)] cage not found; launching FlowerCore.Divoom.Tv directly" >&2
+exec "${APP_BIN}" "${COMMON_ARGS[@]}" "$@"

apps/fc-divoom-tv-pi/scripts/flowercore-divoom-tv-prelaunch.sh

@@ -0,0 +1,23 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+APP_BIN="${FC_DIVOOM_TV_BIN:-/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv}"
+STATE_DIR="${FC_DIVOOM_TV_STATE_DIR:-/var/lib/fc-divoom-tv}"
+LOG_DIR="${FC_DIVOOM_TV_LOG_DIR:-/var/log/fc-divoom-tv}"
+
+mkdir -p "${STATE_DIR}" "${LOG_DIR}"
+
+if [[ ! -x "${APP_BIN}" ]]; then
+  echo "[$(date -Is)] missing executable ${APP_BIN}" >&2
+  exit 1
+fi
+
+if [[ -d /sys/class/drm ]] && ! find /sys/class/drm -maxdepth 1 -name 'card*-HDMI-A-*' -print -quit | grep -q .; then
+  echo "[$(date -Is)] no HDMI connector visible yet; continuing so the app can wait for display" >&2
+fi
+
+if command -v cage >/dev/null 2>&1; then
+  echo "[$(date -Is)] cage available for fullscreen Wayland launch"
+else
+  echo "[$(date -Is)] cage not installed; direct launch fallback will be used" >&2
+fi

apps/fc-divoom-tv-pi/systemd/99-flowercore-divoom-tv-hdmi.rules

@@ -0,0 +1,2 @@
+# Settle DRM for 2s before restarting the fullscreen Avalonia renderer.
+SUBSYSTEM=="drm", KERNEL=="card?-HDMI-A-?", ACTION=="change", RUN+="/usr/bin/systemctl start flowercore-divoom-tv-hdmi.service"

apps/fc-divoom-tv-pi/systemd/flowercore-divoom-tv-hdmi.service

@@ -0,0 +1,7 @@
+[Unit]
+Description=FlowerCore Divoom TV HDMI hotplug responder
+DefaultDependencies=no
+
+[Service]
+Type=oneshot
+ExecStart=/usr/local/bin/flowercore-divoom-tv-hdmi-respond.sh

apps/fc-divoom-tv-pi/systemd/flowercore-divoom-tv.service

@@ -0,0 +1,40 @@
+[Unit]
+Description=FlowerCore Divoom TV HDMI Renderer (Avalonia fullscreen)
+Documentation=https://github.com/astoltz/FlowerCore.Notes/blob/master/docs/standards/divoom-tv-hdmi-multitarget-render-substrate.md
+Wants=network-online.target
+After=network-online.target systemd-user-sessions.service
+ConditionPathExists=/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv
+
+[Service]
+Type=simple
+User=fc-divoom-tv
+Group=fc-divoom-tv
+WorkingDirectory=/opt/flowercore/divoom-tv
+EnvironmentFile=-/etc/flowercore/divoom-tv.env
+Environment=DOTNET_CLI_TELEMETRY_OPTOUT=1
+Environment=XDG_RUNTIME_DIR=/run/fc-divoom-tv
+RuntimeDirectory=fc-divoom-tv
+RuntimeDirectoryMode=0700
+ExecStartPre=/usr/local/bin/flowercore-divoom-tv-prelaunch.sh
+ExecStart=/usr/local/bin/flowercore-divoom-tv-launch.sh
+Restart=always
+RestartSec=10s
+StartLimitBurst=5
+StartLimitIntervalSec=300s
+MemoryMax=2G
+MemoryHigh=1500M
+PrivateTmp=true
+NoNewPrivileges=true
+ProtectSystem=strict
+ProtectHome=true
+ReadWritePaths=/var/lib/fc-divoom-tv /var/log/fc-divoom-tv /run/fc-divoom-tv
+TTYPath=/dev/tty1
+StandardInput=tty
+StandardOutput=journal
+StandardError=journal
+TTYReset=yes
+TTYVHangup=yes
+TTYVTDisallocate=yes
+
+[Install]
+WantedBy=graphical.target

apps/fc-llm-bridge/fc-llm-bridge.yaml

@@ -87,6 +87,20 @@ spec:
         prometheus.io/port: "8080"
         prometheus.io/path: "/metrics"
     spec:
+      # Use an explicit DNS policy so external FQDNs like api.anthropic.com are
+      # resolved directly instead of being expanded through the cluster search
+      # path that includes iamworkin.lan.
+      dnsPolicy: None
+      dnsConfig:
+        nameservers:
+          - 10.43.0.10
+        searches:
+          - fc-llm-bridge.svc.cluster.local
+          - svc.cluster.local
+          - cluster.local
+        options:
+          - name: ndots
+            value: "2"
       securityContext:
         fsGroup: 1654
         fsGroupChangePolicy: OnRootMismatch
@@ -97,7 +111,7 @@ spec:
           #   dotnet.exe publish -c Release -o deploy/app \
           #     src/FlowerCore.LlmBridge.Web/FlowerCore.LlmBridge.Web.csproj
           #   podman build -t localhost/fc-llm-bridge:v<tag> -f deploy/Dockerfile.deploy deploy
-          image: localhost/fc-llm-bridge:v202604292028
+          image: localhost/fc-llm-bridge:v202604300022
           imagePullPolicy: Never
           ports:
             - containerPort: 8080
@@ -211,17 +225,6 @@ spec:
               port: 8080
             initialDelaySeconds: 15
             periodSeconds: 30
-      # Lower ndots so external FQDNs like api.anthropic.com are tried BEFORE
-      # the ndots:5 default expands them through the cluster search path, which
-      # includes iamworkin.lan. CoreDNS has a `template IN A iamworkin.lan`
-      # wildcard that answers `api.anthropic.com.iamworkin.lan` with the
-      # Traefik VIP, which then serves a TRAEFIK-DEFAULT-CERT TLS cert and
-      # breaks egress to the real Anthropic API (memory:
-      # feedback_coredns_ndots_template_collision, generalized to external DNS).
-      dnsConfig:
-        options:
-          - name: ndots
-            value: "2"
       volumes:
         - name: data
           persistentVolumeClaim:

apps/fc-messageboard/fc-messageboard.yaml

@@ -69,16 +69,14 @@ spec:
               memory: "512Mi"
               cpu: "500m"
           livenessProbe:
-            httpGet:
+            tcpSocket:
-              path: /health
               port: 8080
             initialDelaySeconds: 10
             periodSeconds: 30
             timeoutSeconds: 5
             failureThreshold: 3
           readinessProbe:
-            httpGet:
+            tcpSocket:
-              path: /health
               port: 8080
             initialDelaySeconds: 10
             periodSeconds: 10

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-signalcontrol/fc-signalcontrol.yaml

@@ -76,15 +76,13 @@ spec:
               memory: "512Mi"
               cpu: "500m"
           livenessProbe:
-            httpGet:
+            tcpSocket:
-              path: /health
               port: http
             initialDelaySeconds: 30
             periodSeconds: 30
             timeoutSeconds: 5
           readinessProbe:
-            httpGet:
+            tcpSocket:
-              path: /health
               port: http
             initialDelaySeconds: 10
             periodSeconds: 10

apps/fc-ttsreader/biblical-tts/app.py

@@ -30,6 +30,7 @@ import logging
 import re
 import shlex
 import subprocess
+import unicodedata
 from typing import Optional
 
 from fastapi import FastAPI, HTTPException
@@ -60,6 +61,189 @@ class TtsRequest(BaseModel):
     volume: int = 100     # 0-200
 
 
+HEBREW_CHAR_RE = re.compile(r"[\u0590-\u05FF]")
+HEBREW_WORD_RE = re.compile(r"[\u0590-\u05FF]+")
+
+# eSpeak-NG's Hebrew voice can spell unpointed Hebrew as Unicode character
+# names on some builds. For source-text study reads, prefer a stable
+# scholarly transliteration so words sound like words even without niqqud.
+HEBREW_WORD_TRANSLITERATIONS = {
+    "אב": "av",
+    "אבא": "abba",
+    "אברהם": "Avraham",
+    "אדמה": "adamah",
+    "אדני": "Adonai",
+    "אדם": "adam",
+    "אור": "or",
+    "אלהים": "Elohim",
+    "אלוהים": "Elohim",
+    "אמן": "amen",
+    "אם": "em",
+    "אמת": "emet",
+    "ארץ": "eretz",
+    "אש": "esh",
+    "את": "et",
+    "בית": "beit",
+    "בן": "ben",
+    "ברא": "bara",
+    "בראשית": "bereshit",
+    "ברית": "berit",
+    "ברוך": "barukh",
+    "בת": "bat",
+    "גוי": "goy",
+    "גוים": "goyim",
+    "גויים": "goyim",
+    "דבר": "davar",
+    "דברים": "devarim",
+    "דוד": "David",
+    "הלל": "hallel",
+    "הארץ": "ha-aretz",
+    "הברית": "ha-berit",
+    "החדשה": "ha-chadashah",
+    "השמים": "ha-shamayim",
+    "השמיים": "ha-shamayim",
+    "ויאמר": "vayomer",
+    "יהוה": "Adonai",
+    "יוסף": "Yosef",
+    "יוחנן": "Yochanan",
+    "ישראל": "Yisrael",
+    "ישוע": "Yeshua",
+    "יצחק": "Yitzchak",
+    "יעקב": "Yaakov",
+    "ירושלים": "Yerushalayim",
+    "כהן": "kohen",
+    "כהנים": "kohanim",
+    "מים": "mayim",
+    "מות": "mavet",
+    "מושיע": "moshia",
+    "מלך": "melekh",
+    "מלכות": "malkhut",
+    "מרים": "Miriam",
+    "משה": "Moshe",
+    "משיח": "Mashiach",
+    "נביא": "navi",
+    "נביאים": "neviim",
+    "עם": "am",
+    "עולם": "olam",
+    "צדק": "tzedek",
+    "קדוש": "qadosh",
+    "קדושים": "qedoshim",
+    "קול": "qol",
+    "רוח": "ruach",
+    "שאול": "Shaul",
+    "שמים": "shamayim",
+    "שמיים": "shamayim",
+    "שמעון": "Shimon",
+    "שלום": "Shalom",
+    "תורה": "torah",
+    "חכמה": "chokhmah",
+    "חסד": "chesed",
+    "חיים": "chayim",
+    "חושך": "choshekh",
+}
+
+HEBREW_LETTERS = {
+    "א": "a",
+    "ב": "b",
+    "ג": "g",
+    "ד": "d",
+    "ה": "h",
+    "ו": "v",
+    "ז": "z",
+    "ח": "kh",
+    "ט": "t",
+    "י": "y",
+    "כ": "kh",
+    "ך": "kh",
+    "ל": "l",
+    "מ": "m",
+    "ם": "m",
+    "נ": "n",
+    "ן": "n",
+    "ס": "s",
+    "ע": "a",
+    "פ": "p",
+    "ף": "f",
+    "צ": "ts",
+    "ץ": "ts",
+    "ק": "q",
+    "ר": "r",
+    "ש": "sh",
+    "ת": "t",
+}
+
+HEBREW_VOWELISH = {"a", "e", "i", "o", "u"}
+
+
+def _strip_hebrew_marks(value: str) -> str:
+    decomposed = unicodedata.normalize("NFD", value)
+    return "".join(
+        ch for ch in decomposed
+        if unicodedata.category(ch) != "Mn" and ch not in {"׳", "״", "־"}
+    )
+
+
+def _fallback_hebrew_transliteration(word: str) -> str:
+    tokens: list[str] = []
+    chars = list(word)
+    for index, ch in enumerate(chars):
+        token = HEBREW_LETTERS.get(ch)
+        if token is None:
+            continue
+        if ch == "ה" and index == len(chars) - 1:
+            token = "ah"
+        elif ch == "י" and index > 0:
+            token = "i"
+        elif ch == "ו" and index > 0:
+            token = "o"
+        tokens.append(token)
+
+    if not tokens:
+        return word
+
+    spoken: list[str] = []
+    for index, token in enumerate(tokens):
+        spoken.append(token)
+        next_token = tokens[index + 1] if index + 1 < len(tokens) else ""
+        if (
+            token[-1:] not in HEBREW_VOWELISH
+            and next_token
+            and next_token[:1] not in HEBREW_VOWELISH
+        ):
+            spoken.append("a")
+    return "".join(spoken)
+
+
+def _transliterate_hebrew_word(match: re.Match[str]) -> str:
+    original = match.group(0)
+    normalized = _strip_hebrew_marks(original)
+    if not normalized:
+        return original
+
+    direct = HEBREW_WORD_TRANSLITERATIONS.get(normalized)
+    if direct:
+        return direct
+
+    if normalized.startswith("ו") and len(normalized) > 1:
+        rest = HEBREW_WORD_TRANSLITERATIONS.get(normalized[1:])
+        if rest:
+            return f"ve-{rest}"
+
+    if normalized.startswith("ה") and len(normalized) > 1:
+        rest = HEBREW_WORD_TRANSLITERATIONS.get(normalized[1:])
+        if rest:
+            return f"ha-{rest}"
+
+    return _fallback_hebrew_transliteration(normalized)
+
+
+def _prepare_synthesis_input(text: str, language: str, voice: str) -> tuple[str, str]:
+    if language.lower().startswith("he") and HEBREW_CHAR_RE.search(text):
+        spoken = HEBREW_WORD_RE.sub(_transliterate_hebrew_word, text)
+        return spoken, "en-us"
+    return text, voice
+
+
 def _resolve_voice(req: TtsRequest) -> str:
     if req.voice:
         return req.voice.strip()
@@ -115,14 +299,15 @@ def tts(req: TtsRequest) -> Response:
         raise HTTPException(status_code=400, detail="text is required")
 
     voice = _resolve_voice(req)
+    spoken_text, synth_voice = _prepare_synthesis_input(req.text, req.language, voice)
     args = [
         "--stdout",
-        "-v", voice,
+        "-v", synth_voice,
         "-s", str(max(80, min(450, req.rate))),
         "-p", str(max(0, min(99, req.pitch))),
         "-a", str(max(0, min(200, req.volume))),
     ]
-    wav = _run_espeak(args, req.text.encode("utf-8"))
+    wav = _run_espeak(args, spoken_text.encode("utf-8"))
     if not wav:
         raise HTTPException(status_code=500, detail="espeak-ng returned empty stdout")
     return Response(content=wav, media_type="audio/wav")
@@ -153,9 +338,9 @@ def tts(req: TtsRequest) -> Response:
 PHONEME_DURATION_RE = re.compile(r"^\s*\S+\s+(\d+)\s+", re.MULTILINE)
 
 
-def _estimate_total_ms(req: TtsRequest, voice: str) -> int:
+def _estimate_total_ms(req: TtsRequest, voice: str, spoken_text: str) -> int:
     args = ["--pho", "--quiet", "-v", voice, "-s", str(req.rate)]
-    out = _run_espeak(args, req.text.encode("utf-8"))
+    out = _run_espeak(args, spoken_text.encode("utf-8"))
     text = out.decode("utf-8", errors="replace")
     total = 0
     for match in PHONEME_DURATION_RE.finditer(text):
@@ -175,7 +360,8 @@ def timings(req: TtsRequest):
     if not req.text.strip():
         raise HTTPException(status_code=400, detail="text is required")
     voice = _resolve_voice(req)
-    total_ms = _estimate_total_ms(req, voice)
+    spoken_text, synth_voice = _prepare_synthesis_input(req.text, req.language, voice)
+    total_ms = _estimate_total_ms(req, synth_voice, spoken_text)
 
     # Distribute total_ms across whitespace-split words proportional to
     # character count. Punctuation-only tokens are folded into the previous
@@ -204,7 +390,7 @@ def timings(req: TtsRequest):
         {
             "text": req.text,
             "language": req.language,
-            "voice": voice,
+            "voice": synth_voice,
             "words": out_words,
             "durationMs": total_ms,
         }

apps/fc-ttsreader/fc-ttsreader.yaml

@@ -37,6 +37,19 @@ spec:
         app.kubernetes.io/name: ttsreader-piper
         app.kubernetes.io/part-of: flowercore
     spec:
+      # Bypass CoreDNS's *.iamworkin.lan wildcard so the init container reaches
+      # huggingface.co directly when it seeds voice models.
+      dnsPolicy: None
+      dnsConfig:
+        nameservers:
+          - 10.43.0.10
+        searches:
+          - fc-ttsreader.svc.cluster.local
+          - svc.cluster.local
+          - cluster.local
+        options:
+          - name: ndots
+            value: "2"
       initContainers:
         - name: seed-voices
           image: rhasspy/wyoming-piper:latest
@@ -346,7 +359,7 @@ spec:
         runAsUser: 1654
       containers:
         - name: biblical-tts
-          image: localhost/fc-biblical-tts:v1
+          image: localhost/fc-biblical-tts:v20260506-hebrew-translit
           imagePullPolicy: Never
           ports:
             - containerPort: 10402
@@ -519,7 +532,7 @@ spec:
         fsGroupChangePolicy: OnRootMismatch
       containers:
         - name: web
-          image: localhost/fc-ttsreader-web:v202604291817
+          image: localhost/fc-ttsreader-web:v20260603-s54cx14-pr29-schema
           imagePullPolicy: Never
           ports:
             - containerPort: 5217
@@ -537,12 +550,20 @@ spec:
               value: "/usr/bin/ffmpeg"
             - name: TtsReader__Bible__CorpusRoot
               value: "/data/corpus-cache/world-english-bible/eng/usx"
+            - name: TtsReader__ChapterContext__DatabasePath
+              value: "/data/chapter-context.db"
             - name: TtsReader__Jobs__Root
               value: "/data/jobs"
+            - name: TtsReader__Export__LocalCasRoot
+              value: "/data/bundles/cas"
             - 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
@@ -553,6 +574,14 @@ spec:
               value: "http://ttsreader-kokoro.fc-ttsreader.svc.cluster.local.:8880"
             - name: TtsReader__Kokoro__TimeoutSeconds
               value: "120"
+            - name: FlowerCore__Tts__BiblicalTts__Enabled
+              value: "true"
+            - name: FlowerCore__Tts__BiblicalTts__BaseUrl
+              value: "http://ttsreader-biblical.fc-ttsreader.svc.cluster.local.:10402"
+            - name: FlowerCore__Tts__BiblicalTts__TimeoutSeconds
+              value: "60"
+            - name: FlowerCore__Tts__BiblicalTts__DefaultLanguage
+              value: "grc"
             - name: Speech__Alignment__Enabled
               # Cluster-native faster-whisper (Lane F, 2026-04-25). The
               # ttsreader-align deployment in this manifest wraps
@@ -588,6 +617,8 @@ spec:
             # the writable PVC mount.
             - name: TtsReader__Preview__CacheDirectory
               value: "/data/voice-previews"
+            - name: TtsReader__VoiceLibrary__ReferenceClip__Directory
+              value: "/data/voice-reference-clips"
             # Sprint E XXL Phase 4γ — content-addressed CDN bundle dir for
             # POST /api/v1/render. Default "wwwroot/cdn" resolves under the
             # read-only app filesystem, so pin to the writable PVC mount
@@ -609,7 +640,10 @@ spec:
                   optional: true
           resources:
             requests:
-              cpu: 100m
+              # The cluster is currently saturated on requested CPU by
+              # remotedesktop workloads even when real usage is low.
+              # Keep the web frontend schedulable under that pressure.
+              cpu: 10m
               memory: 256Mi
             limits:
               cpu: 500m

apps/fc-updater/README.md

@@ -0,0 +1,47 @@
+# fc-updater — Update Center GitOps adoption
+
+**Status:** adopted into `bluejay-infra` on 2026-05-06. The live ArgoCD
+Application is `infra-fc-updater`, generated by the `bluejay-infra`
+ApplicationSet with automated sync, `prune: true`, and `selfHeal: true`.
+
+## Managed manifest set
+
+`apps/fc-updater/fc-updater.yaml` manages:
+
+- `Namespace/fc-updater`
+- `PersistentVolumeClaim/updatecenter-data`
+- `Deployment/updatecenter-web`
+- `Service/updatecenter-web`
+- `Certificate/updatecenter-web-tls`
+- `Certificate/updatecenter-web-internal-tls`
+- `IngressRoute/updatecenter-web`
+- `IngressRoute/updatecenter-web-internal`
+- `IngressRoute/updatecenter-web-public`
+
+The Deployment intentionally sets `revisionHistoryLimit: 3` and
+`strategy.type: Recreate`. The service is singleton + SQLite/local bundle
+storage on `PersistentVolumeClaim/updatecenter-data`, pinned to
+`rke2-server`.
+
+## Runtime dependencies intentionally not stored here
+
+These live Secrets are pre-existing runtime material and are not committed to
+Git:
+
+- `updater-bootstrap-auth`
+- `updater-signing`
+- `updater-webhooks`
+- `cf-origin-flowercore-io`
+
+Rotate the Cloudflare Origin Certificate through
+`FlowerCore.Notes/docs/standards/code-signing-rotation-runbook.md`; the
+shared origin cert must exist in every namespace that serves a
+`*.flowercore.io` public IngressRoute.
+
+## Verification
+
+```powershell
+kubectl.exe --kubeconfig C:\Users\AndrewStoltz\.kube\rke2.yaml -n argocd get application infra-fc-updater
+kubectl.exe --kubeconfig C:\Users\AndrewStoltz\.kube\rke2.yaml -n fc-updater get deploy,svc,ingressroute,certificate,pvc
+curl.exe -sk https://update.flowercore.io/api/v1/manifests/_schema
+```

apps/fc-updater/fc-updater.yaml

@@ -0,0 +1,271 @@
+# FlowerCore Update Center
+# GitOps adoption of the live fc-updater namespace after PUB-1/PUB-3.
+# Runtime credentials remain in existing K8s Secrets; do not store them here.
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: fc-updater
+  labels:
+    app.kubernetes.io/part-of: flowercore
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: updatecenter-data
+  namespace: fc-updater
+  labels:
+    app.kubernetes.io/name: updatecenter-web
+    app.kubernetes.io/part-of: flowercore
+spec:
+  accessModes:
+    - ReadWriteOnce
+  storageClassName: longhorn
+  volumeMode: Filesystem
+  resources:
+    requests:
+      # Sized for fleet bundle storage (LocalFsBundleStore.MaxTotalBytes
+      # soft cap at 25 GiB per project_uc_remaining_4_apps_signed_2026_05_06).
+      # Mike Bundle alone is ~5.1 GiB; cluster live capacity is already
+      # 20 GiB after a manual expand. PVCs cannot shrink, so git must track
+      # at least the live size to avoid the OutOfSync loop.
+      storage: 25Gi
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: updatecenter-web
+  namespace: fc-updater
+  labels:
+    app: updatecenter-web
+    app.kubernetes.io/name: updatecenter-web
+    app.kubernetes.io/part-of: flowercore
+spec:
+  replicas: 1
+  revisionHistoryLimit: 3
+  strategy:
+    # SQLite + local bundle storage live on a single RWO PVC. Recreate avoids
+    # two pods overlapping the same write path during future image bumps.
+    type: Recreate
+  selector:
+    matchLabels:
+      app: updatecenter-web
+  template:
+    metadata:
+      labels:
+        app: updatecenter-web
+    spec:
+      nodeName: rke2-server
+      containers:
+        - name: web
+          image: localhost/fc-updater-web:v202605310029-7974fc4
+          imagePullPolicy: Never
+          ports:
+            - containerPort: 8080
+              name: http
+          env:
+            - name: ASPNETCORE_URLS
+              value: http://+:8080
+            - name: FlowerCore__Updater__Database__Provider
+              value: sqlite
+            - name: FlowerCore__Updater__Database__ConnectionString
+              value: Data Source=/data/updatecenter.db
+            - name: FlowerCore__Updater__BundleStorage__LocalFs__RootDirectory
+              value: /data/bundles
+            - name: FlowerCore__Updater__PublicShares__RequirePublicVisibilityOnPublicHosts
+              value: "true"
+            - name: FlowerCore__Updater__PublicShares__Links__0__Code
+              value: 8f3c2a9e7d41
+            - name: FlowerCore__Updater__PublicShares__Links__0__AppId
+              value: flowercore.faith-ai-mike
+            - name: FlowerCore__Updater__PublicShares__Links__0__Channel
+              value: stable
+            - name: FlowerCore__Updater__PublicShares__Links__0__RuntimeId
+              value: win-x64
+            - name: FlowerCore__Updater__PublicShares__Links__0__DisplayName
+              value: Faith AI Mike Edition
+            - name: FlowerCore__Updater__PublicShares__Links__0__Headline
+              value: Faith AI Mike Edition
+            - name: FlowerCore__Updater__PublicShares__Links__0__Description
+              value: Private release link for Mike's Faith AI bundle.
+            - name: FlowerCore__Audit__Sinks__Loki__Enabled
+              value: "false"
+            - name: FlowerCore__Updater__Auth__Bootstrap__Enabled
+              value: "true"
+            - name: FlowerCore__Updater__Auth__Bootstrap__Username
+              valueFrom:
+                secretKeyRef:
+                  name: updater-bootstrap-auth
+                  key: username
+            - name: FlowerCore__Updater__Auth__Bootstrap__Password
+              valueFrom:
+                secretKeyRef:
+                  name: updater-bootstrap-auth
+                  key: password
+            - name: FlowerCore__Updater__Auth__Bootstrap__SigningKey
+              valueFrom:
+                secretKeyRef:
+                  name: updater-bootstrap-auth
+                  key: signing-key
+            - name: FlowerCore__Updater__Signing__AutoSignOnPublish
+              value: "true"
+            - name: FlowerCore__Updater__Signing__RequireSignatureOnPublish
+              value: "true"
+            - name: FlowerCore__Updater__Signing__PfxBase64
+              valueFrom:
+                secretKeyRef:
+                  name: updater-signing
+                  key: pfx-base64
+            - name: FlowerCore__Updater__Signing__PfxPassword
+              valueFrom:
+                secretKeyRef:
+                  name: updater-signing
+                  key: pfx-password
+            - name: FlowerCore__Updater__Signing__OpItemReference
+              value: op://FlowerCore/step-ca-codesign
+            - name: FlowerCore__Updater__Signing__TrustAnchorPath
+              value: /etc/flowercore-updater/signing/root-ca.pem
+            - name: FlowerCore__Updater__GitHub__Token
+              valueFrom:
+                secretKeyRef:
+                  name: updater-webhooks
+                  key: github-token
+            - name: FlowerCore__Updater__GitHub__WebhookSecret
+              valueFrom:
+                secretKeyRef:
+                  name: updater-webhooks
+                  key: github-webhook-secret
+            - name: FlowerCore__Updater__Gitea__Token
+              valueFrom:
+                secretKeyRef:
+                  name: updater-webhooks
+                  key: gitea-token
+            - name: FlowerCore__Updater__Gitea__WebhookSecret
+              valueFrom:
+                secretKeyRef:
+                  name: updater-webhooks
+                  key: gitea-webhook-secret
+          readinessProbe:
+            tcpSocket:
+              port: http
+            initialDelaySeconds: 10
+            periodSeconds: 15
+          livenessProbe:
+            tcpSocket:
+              port: http
+            initialDelaySeconds: 30
+            periodSeconds: 30
+          volumeMounts:
+            - name: data
+              mountPath: /data
+            - name: signing
+              mountPath: /etc/flowercore-updater/signing
+              readOnly: true
+      volumes:
+        - name: data
+          persistentVolumeClaim:
+            claimName: updatecenter-data
+        - name: signing
+          secret:
+            secretName: updater-signing
+            items:
+              - key: root-ca.pem
+                path: root-ca.pem
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: updatecenter-web
+  namespace: fc-updater
+  labels:
+    app: updatecenter-web
+    app.kubernetes.io/name: updatecenter-web
+    app.kubernetes.io/part-of: flowercore
+spec:
+  type: ClusterIP
+  selector:
+    app: updatecenter-web
+  ports:
+    - name: http
+      port: 8080
+      targetPort: http
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: updatecenter-web-tls
+  namespace: fc-updater
+spec:
+  secretName: updatecenter-web-tls
+  issuerRef:
+    name: step-ca-acme
+    kind: ClusterIssuer
+  dnsNames:
+    - updatecenter.iamworkin.lan
+    - updates.iamworkin.lan
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: updatecenter-web-internal-tls
+  namespace: fc-updater
+spec:
+  secretName: updatecenter-web-internal-tls
+  issuerRef:
+    name: step-ca-acme
+    kind: ClusterIssuer
+  dnsNames:
+    - updatecenter-internal.iamworkin.lan
+---
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: updatecenter-web
+  namespace: fc-updater
+spec:
+  entryPoints:
+    - web
+    - websecure
+  routes:
+    - match: (Host(`updatecenter.iamworkin.lan`) || Host(`updates.iamworkin.lan`)) && (Method(`GET`) || Method(`HEAD`) || Method(`POST`) || Method(`OPTIONS`))
+      kind: Rule
+      services:
+        - name: updatecenter-web
+          port: 8080
+  tls:
+    secretName: updatecenter-web-tls
+---
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: updatecenter-web-internal
+  namespace: fc-updater
+spec:
+  entryPoints:
+    - web
+    - websecure
+  routes:
+    - match: Host(`updatecenter-internal.iamworkin.lan`)
+      kind: Rule
+      services:
+        - name: updatecenter-web
+          port: 8080
+  tls:
+    secretName: updatecenter-web-internal-tls
+---
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: updatecenter-web-public
+  namespace: fc-updater
+spec:
+  entryPoints:
+    - websecure
+  routes:
+    - match: (Host(`update.flowercore.io`) || Host(`updates.flowercore.io`)) && (Method(`GET`) || Method(`HEAD`) || Method(`POST`) || Method(`OPTIONS`))
+      kind: Rule
+      services:
+        - name: updatecenter-web
+          port: 8080
+  tls:
+    secretName: cf-origin-flowercore-io

apps/fc-updater/kustomization.yaml

@@ -0,0 +1,7 @@
+# ArgoCD's bluejay-infra ApplicationSet uses a directory generator and does
+# not require kustomization.yaml. Keep this anyway as the manifest inventory
+# and for local `kubectl kustomize apps/fc-updater` previews.
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - fc-updater.yaml

apps/flowercore/flowercore.yaml

@@ -1,5 +1,10 @@
-# FlowerCore Tenant — flowercore.io (main brand)
+# FlowerCore Tenant — retired flowercore.io placeholder.
-# Public-facing placeholder landing page served by nginx
+#
+# Public flowercore.io/www.flowercore.io routing is now owned by
+# apps/fc-landing/fc-landing.yaml. This tenant placeholder remains available
+# only as an in-cluster service; do not create a duplicate public
+# IngressRoute here because it competes with fc-landing and requires a
+# namespace-local cf-origin-flowercore-io Secret.
 # ArgoCD managed - BlueJay Lab
 ---
 apiVersion: v1
@@ -10,12 +15,6 @@ metadata:
     app.kubernetes.io/part-of: bluejay-infra
     flowercore.io/tenant: flowercore
 ---
-# NOTE: The existing cf-origin-flowercore-io secret (covering *.flowercore.io)
-# must be copied into this namespace. It already exists in other namespaces.
-# Copy with: kubectl get secret cf-origin-flowercore-io -n fc-system -o yaml \
-#   | sed 's/namespace: .*/namespace: tenant-flowercore/' \
-#   | kubectl apply -f -
----
 # Landing page HTML
 apiVersion: v1
 kind: ConfigMap
@@ -311,22 +310,3 @@ spec:
     - port: 80
       targetPort: 80
       name: http
----
-# Traefik IngressRoute — public via Cloudflare
-# Uses existing cf-origin-flowercore-io cert (must be copied to this namespace)
-apiVersion: traefik.io/v1alpha1
-kind: IngressRoute
-metadata:
-  name: flowercore-web
-  namespace: tenant-flowercore
-spec:
-  entryPoints:
-    - websecure
-  routes:
-    - match: Host(`flowercore.io`) || Host(`www.flowercore.io`)
-      kind: Rule
-      services:
-        - name: flowercore-web
-          port: 80
-  tls:
-    secretName: cf-origin-flowercore-io

apps/github-runner/.gitattributes

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

apps/github-runner/Dockerfile

@@ -0,0 +1,54 @@
+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:${PATH}"
+
+USER root
+
+# Bake the IAmWorkin step-ca root CA into the system trust store. Without
+# this, .NET HttpClient calls from CI tests against *.iamworkin.lan
+# (e.g. https://selenium.iamworkin.lan/session) fail with `PartialChain`
+# because the runner image's default Ubuntu trust bundle doesn't include
+# our internal Root CA. update-ca-certificates regenerates
+# /etc/ssl/certs/ca-certificates.crt, which OpenSSL + .NET on Linux read
+# automatically — no SSL_CERT_FILE env var needed.
+COPY step-ca-root.crt /usr/local/share/ca-certificates/iamworkin-step-ca-root.crt
+
+RUN apt-get update \
+    && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
+        autoconf \
+        bison \
+        build-essential \
+        ca-certificates \
+        curl \
+        libdb-dev \
+        libffi-dev \
+        libgdbm-dev \
+        libgmp-dev \
+        libncurses-dev \
+        libreadline-dev \
+        libssl-dev \
+        libyaml-dev \
+        patch \
+        pkg-config \
+        uuid-dev \
+        zlib1g-dev \
+    && update-ca-certificates \
+    && curl -fsSL "https://github.com/rbenv/ruby-build/archive/refs/tags/${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 +1,133 @@
+# 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:v20260525-ruby3.3.11-stepca`, 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.
+
+The IAmWorkin step-ca root CA is also baked into the system trust store
+(`/usr/local/share/ca-certificates/iamworkin-step-ca-root.crt`, registered by
+`update-ca-certificates`). Without it, .NET HttpClient calls from CI tests
+against `*.iamworkin.lan` (e.g. `https://selenium.iamworkin.lan/session`)
+fail with `PartialChain`. To refresh the bundled cert when the root rotates,
+re-extract from the cluster and overwrite `step-ca-root.crt`:
+
+```bash
+kubectl get secret -n cert-manager step-ca-root \
+  -o jsonpath='{.data.ca\.crt}' | base64 -d > step-ca-root.crt
+```
+
+```bash
+cd apps/github-runner
+podman build -t localhost/fc-github-runner:v20260525-ruby3.3.11-stepca .
+podman run --rm localhost/fc-github-runner:v20260525-ruby3.3.11-stepca ruby -v
+podman run --rm localhost/fc-github-runner:v20260525-ruby3.3.11-stepca \
+  test -f /opt/runner-toolcache/Ruby/3.3/x64.complete
+podman save localhost/fc-github-runner:v20260525-ruby3.3.11-stepca \
+  -o fc-github-runner-v20260525-ruby3.3.11-stepca.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-v20260525-ruby3.3.11-stepca.tar "$node:/tmp/"
+  ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images rm localhost/fc-github-runner:v20260525-ruby3.3.11-stepca || true'
+  ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images import /tmp/fc-github-runner-v20260525-ruby3.3.11-stepca.tar'
+done
+```
+
+## Post-Merge Proof
+
+After the PR is merged and ArgoCD syncs, verify the runner fleet:
+
+```bash
+kubectl -n github-runner get deploy,pods,pvc
+```
+
+Verify the Ruby toolcache in a fresh pod:
+
+```bash
+kubectl -n github-runner exec deploy/github-runner-puppet -c runner -- ruby -v
+kubectl -n github-runner exec deploy/github-runner-puppet -c runner -- sh -c \
+  'echo "$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/github-runner/step-ca-root.crt

@@ -0,0 +1,12 @@
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----

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/intranet/intranet.yaml

@@ -46,7 +46,7 @@ spec:
     spec:
       containers:
         - name: intranet-web
-          image: localhost/fc-intranet-web:v20260429-1646
+          image: localhost/fc-intranet-web:v20260531-ttsreader-bridge
           imagePullPolicy: Never
           ports:
             - containerPort: 5300

apps/knowledge/README.md

@@ -5,7 +5,9 @@ Phase 2.4 closed. Pod running, certificate issued (step-ca-acme), PVC
 bound (Longhorn 20Gi RWO), ArgoCD `infra-knowledge` synced. `/healthz`
 returns 200, `/api/v1/editions` returns `[]` (initial-deploy state — no
 *.db files in the PVC yet; Phase 2.5+ admin UI handles bulk
-population).
+population). Phase 1 of the Agent Zero MCP rollout keeps `/healthz`
+anonymous and gates `/mcp` behind `Authorization: Bearer <token>` built
+from the 1Password item `FlowerCore Knowledge MCP Tokens`.
 
 - Plan: [`../../../FlowerCore.Notes/docs/ai-agents/flowercore-knowledge-service-plan.md`](../../../FlowerCore.Notes/docs/ai-agents/flowercore-knowledge-service-plan.md)
 - Sprint: [`../../../FlowerCore.Notes/docs/ai-station/sprint-e-xxl-plan.md`](../../../FlowerCore.Notes/docs/ai-station/sprint-e-xxl-plan.md) (Track B)
@@ -19,6 +21,12 @@ search to the rest of the FC ecosystem (Agent Zero, Chat.Web persona
 memory, AiStation embeddings explorer, TtsReader chapter context, BMO
 bot, Pi nodes via `fc-index sync`).
 
+Phase 1 MCP routing is explicit:
+
+- in-cluster Agent Zero → `http://knowledge-web.knowledge.svc/mcp`
+- workstation Agent Zero → `https://knowledge.iamworkin.lan/mcp`
+- probe URL for both lanes → `/healthz`
+
 ## Deployment order (do NOT skip / reorder)
 
 ### 1. FlowerCore.DNS public A record — knowledge.iamworkin.lan -> 10.0.56.200

apps/knowledge/knowledge.yaml

@@ -40,16 +40,16 @@ metadata:
   labels:
     app.kubernetes.io/part-of: bluejay-infra
 ---
-# MCP API key — synced from 1Password so /mcp stays gated without baking
+# MCP bearer token for the read-only Agent Zero Phase 1 lane. The 1Password
-# secrets into Git. The PASSWORD category maps the concealed field to Secret
+# item currently stores the raw token in its concealed PASSWORD field, which
-# key `password`, which the Deployment reads into FlowerCore:Mcp:ApiKey:Key.
+# the operator syncs into the namespaced Secret key `password`.
 apiVersion: onepassword.com/v1
 kind: OnePasswordItem
 metadata:
-  name: knowledge-mcp-api-key
+  name: knowledge-mcp-tokens
   namespace: knowledge
 spec:
-  itemPath: "vaults/IAmWorkin/items/KnowledgeApiKey"
+  itemPath: "vaults/IAmWorkin/items/FlowerCore Knowledge MCP Tokens"
 ---
 apiVersion: v1
 kind: PersistentVolumeClaim
@@ -102,8 +102,17 @@ spec:
         - name: web
           # Placeholder tag — bump to the image you built + imported to ALL
           # RKE2 nodes via scripts/deploy-knowledge.sh before applying.
-          image: localhost/fc-knowledge-web:v202604272200
+          image: localhost/fc-knowledge-web:v20260429232635
           imagePullPolicy: Never
+          command:
+            - /bin/sh
+            - -c
+          args:
+            - |
+              if [ -n "${KNOWLEDGE_MCP_BEARER_TOKEN:-}" ]; then
+                export FlowerCore__Mcp__ApiKey__Key="Bearer ${KNOWLEDGE_MCP_BEARER_TOKEN}"
+              fi
+              exec dotnet FlowerCore.Knowledge.Web.dll
           ports:
             - containerPort: 8080
               name: http
@@ -115,7 +124,7 @@ spec:
             - name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
               value: "false"
             # Vector-store directory + embedding model + edition profile dir.
-            # Profile JSON is baked into the image at /app/editions via the
+            # Profile JSON is baked into the image at /home/app/editions via the
             # csproj Content-link from FlowerCore.Common/editions/.
             - name: Knowledge__VectorStoresDirectory
               value: "/data/vector-stores"
@@ -126,7 +135,7 @@ spec:
             - name: Knowledge__MaxLimit
               value: "50"
             - name: FlowerCore__Editions__ProfileDirectory
-              value: "/app/editions"
+              value: "/home/app/editions"
             # Embed via edge1 Pi 5 + AI HAT+ (10.0.57.17:11434). Cluster
             # services do not depend on BLUEJAY-WS (private dev hardware) per
             # bluejay-infra@0f9d56e. Query-time embedding is fast enough on
@@ -138,7 +147,14 @@ spec:
             - name: FlowerCore__Mcp__ApiKey__Key
               valueFrom:
                 secretKeyRef:
-                  name: knowledge-mcp-api-key
+                  name: knowledge-mcp-tokens
+                  key: password
+            - name: FlowerCore__Mcp__ApiKey__HeaderName
+              value: "Authorization"
+            - name: KNOWLEDGE_MCP_BEARER_TOKEN
+              valueFrom:
+                secretKeyRef:
+                  name: knowledge-mcp-tokens
                   key: password
           resources:
             requests:
@@ -185,7 +201,7 @@ spec:
             - name: tmp
               mountPath: /tmp
             - name: logs
-              mountPath: /app/logs
+              mountPath: /home/app/logs
       volumes:
         - name: vector-store
           persistentVolumeClaim:
@@ -225,8 +241,12 @@ spec:
     kind: ClusterIssuer
   dnsNames:
     - knowledge.iamworkin.lan
-  duration: 2160h    # 90d
+  # step-ca ACME caps lifetime at 30d; requesting 90d silently capped
-  renewBefore: 720h  # 30d
+  # made renewBefore=cert-lifetime → perpetual renewal loop (10888+ CRs
+  # in 18h on 2026-05-07). Match working 720h/240h pattern from other
+  # FC services.
+  duration: 720h     # 30d (step-ca cap)
+  renewBefore: 240h  # 10d
 ---
 apiVersion: traefik.io/v1alpha1
 kind: IngressRoute

apps/kubevirt-vms/ci1.yaml

@@ -0,0 +1,93 @@
+# =============================================================================
+# ci1 - Windows Server 2025 KubeVirt VM (GitHub Actions Self-Hosted Runner)
+# =============================================================================
+# Boots from the sysprepped containerDisk template built by the Windows VM
+# sysprep pipeline. See docs/infrastructure/windows-vm-sysprep-pipeline.md.
+# Path A/B/C install history is preserved in git log only.
+# =============================================================================
+
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: kubevirt-vms
+  labels:
+    app.kubernetes.io/part-of: kubevirt-stack
+    pod-security.kubernetes.io/enforce: privileged
+
+---
+apiVersion: kubevirt.io/v1
+kind: VirtualMachine
+metadata:
+  name: ci1
+  namespace: kubevirt-vms
+  labels:
+    app: ci-runner
+    role: github-actions-runner
+    flowercore.io/managed-by: bluejay-infra
+spec:
+  runStrategy: Halted
+  template:
+    metadata:
+      labels:
+        app: ci-runner
+        role: github-actions-runner
+        kubevirt.io/vm: ci1
+    spec:
+      domain:
+        cpu:
+          cores: 8
+          sockets: 1
+          threads: 1
+        memory:
+          guest: 16Gi
+        resources:
+          requests:
+            memory: 16Gi
+          limits:
+            memory: 16Gi
+        clock:
+          utc: {}
+          timer:
+            hpet:
+              present: false
+            pit:
+              tickPolicy: delay
+            rtc:
+              tickPolicy: catchup
+            hyperv: {}
+        features:
+          acpi: {}
+          apic: {}
+          hyperv:
+            relaxed: {}
+            vapic: {}
+            spinlocks:
+              spinlocks: 8191
+          smm: {}
+        firmware:
+          bootloader:
+            efi:
+              secureBoot: false
+        devices:
+          tpm: {}
+          disks:
+            - name: rootdisk
+              disk:
+                bus: virtio
+          interfaces:
+            # Pod-network fallback for CI runner outbound traffic. Switch to
+            # prod-vlan57 once the bridge/NAD lane is ready for L2 access.
+            - name: default
+              masquerade: {}
+              model: virtio
+        machine:
+          type: q35
+      networks:
+        - name: default
+          pod: {}
+      volumes:
+        - name: rootdisk
+          containerDisk:
+            image: localhost/fc-win-server-2025:v1
+            imagePullPolicy: Never
+      terminationGracePeriodSeconds: 3600

apps/kubevirt-vms/kustomization.yaml

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

apps/kubevirt-vms/prod-vlan57-nad.yaml

@@ -0,0 +1,69 @@
+# =============================================================================
+# NetworkAttachmentDefinition — PROD VLAN 57 bridge
+# =============================================================================
+# Purpose: makes KubeVirt VMs reachable on the PROD VLAN (10.0.57.0/24)
+# alongside the existing pod network. Required for ci1 to bridge onto PROD
+# (e.g. to provision/scrape edge1, edge2, kiosks, Pis on the same L2 segment).
+#
+# **DEPLOY GATE — Phase 1.5 host work required first**:
+#   On every RKE2 node (rke2-server, rke2-agent1, rke2-agent2):
+#     1. Switch port (UniFi USL16LP) trunks VLAN 57 to the node — usually
+#        already true since BLUEJAY-WS reaches 10.0.57.x services. Verify
+#        with `ip link show enp86s0.57` after configuring sub-interface, OR
+#        `tcpdump -ni enp86s0 vlan 57` and ping a known PROD host.
+#     2. Linux bridge `br-prod` enslaving `enp86s0.57` (VLAN sub-interface).
+#        NetworkManager profile examples in the runbook below.
+#     3. Verify Multus DaemonSet `kube-multus-ds` is Ready on all nodes.
+#
+# Without those, applying this NAD has no effect except to register the CRD.
+# A VM that requests this NAD with no bridge present will fail with:
+#   `error adding pod kubevirt-vms_ci1 to CNI network "prod-vlan57": failed to
+#    plumb VLAN: open /sys/class/net/br-prod/master: no such file or directory`
+#
+# Configuration notes:
+#   - cniVersion 0.3.1 to match Multus daemon-config.json
+#   - mtu 1500 (matches enp86s0 default; bump if jumbo frames configured)
+#   - bridge name `br-prod` is convention; if Puppet picks a different name
+#     (e.g. `br57`, `br-vlan57`), edit BOTH this NAD and the ci1.yaml
+#     interface block. Keep them in sync.
+#   - vlan: 0 because the host bridge already strips VLAN tag (br-prod sits
+#     on top of `enp86s0.57`). If we instead used a VLAN-aware bridge with
+#     trunk port, set vlan: 57 here. Current convention is VLAN-stripped at
+#     the sub-interface, so the bridge passes untagged frames.
+#
+# Apply:
+#   kubectl --kubeconfig $env:USERPROFILE\.kube\rke2.yaml apply -f apps/kubevirt-vms/prod-vlan57-nad.yaml
+#
+# Then update ci1.yaml networks: stanza to:
+#   - name: prod-net
+#     multus:
+#       networkName: kubevirt-vms/prod-vlan57
+# and the interface block from `masquerade` to `bridge`.
+# =============================================================================
+
+---
+# Namespace must exist already (created by ci1.yaml's first document).
+# This file imports a NAD into that same namespace.
+apiVersion: k8s.cni.cncf.io/v1
+kind: NetworkAttachmentDefinition
+metadata:
+  name: prod-vlan57
+  namespace: kubevirt-vms
+  annotations:
+    bluejay.iamworkin.lan/host-bridge: "br-prod (enslaves enp86s0.57)"
+    bluejay.iamworkin.lan/cidr: "10.0.57.0/24"
+    bluejay.iamworkin.lan/gateway: "10.0.57.1"
+    bluejay.iamworkin.lan/dns: "10.0.56.1 (pfSense Unbound)"
+spec:
+  config: |
+    {
+      "cniVersion": "0.3.1",
+      "name": "prod-vlan57",
+      "type": "bridge",
+      "bridge": "br-prod",
+      "ipam": {},
+      "mtu": 1500,
+      "vlan": 0,
+      "promiscMode": true,
+      "preserveDefaultVlan": false
+    }

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/mail/mail.yaml

@@ -207,20 +207,13 @@ spec:
     - port: 993
       targetPort: 993
       name: imaps
----
+# --- mail-tls Certificate REMOVED 2026-06-01 ---
-# TLS Certificate via cert-manager
+# mail-tls is now managed OUTSIDE cert-manager: issued from step-ca's JWK 'admin'
-apiVersion: cert-manager.io/v1
+# provisioner and auto-renewed by a systemd timer on noc1 (step ca renew), which
-kind: Certificate
+# writes the mail-tls secret directly. step-ca-acme only has an HTTP-01 (Traefik)
-metadata:
+# solver, but mail.iamworkin.lan must resolve to the dedicated MetalLB IP 10.0.56.202
-  name: mail-tls
+# (SMTP/IMAP), so HTTP-01 cannot validate. Do NOT re-add a cert-manager Certificate
-  namespace: mail
+# here unless a DNS-01 solver is deployed for step-ca-acme.
-spec:
-  secretName: mail-tls
-  issuerRef:
-    name: step-ca-acme
-    kind: ClusterIssuer
-  dnsNames:
-    - mail.iamworkin.lan
 ---
 # Traefik IngressRoute - Webmail placeholder
 apiVersion: traefik.io/v1alpha1

apps/monitoring/fc-updatecenter-dashboard.grafana.txt

@@ -0,0 +1,762 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [
+    {
+      "icon": "external link",
+      "includeVars": false,
+      "keepTime": false,
+      "targetBlank": true,
+      "title": "Open Service",
+      "type": "link",
+      "url": "https://updatecenter.iamworkin.lan/"
+    }
+  ],
+  "panels": [
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "fffjikve8llhce"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [
+            {
+              "options": {
+                "0": {
+                  "color": "#f87171",
+                  "index": 1,
+                  "text": "DOWN"
+                },
+                "1": {
+                  "color": "#4ade80",
+                  "index": 0,
+                  "text": "UP"
+                }
+              },
+              "type": "value"
+            }
+          ],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "#f87171",
+                "value": null
+              },
+              {
+                "color": "#4ade80",
+                "value": 1
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 8,
+        "x": 0,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "colorMode": "background",
+        "graphMode": "none",
+        "justifyMode": "center",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "value_and_name"
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "fffjikve8llhce"
+          },
+          "expr": "probe_success{job=\"probe-traefik-services\",instance=\"updatecenter.iamworkin.lan\"}",
+          "refId": "A",
+          "legendFormat": "Availability"
+        }
+      ],
+      "title": "Service Availability",
+      "transparent": true,
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "fffjikve8llhce"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "decimals": 2,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "#f87171",
+                "value": null
+              },
+              {
+                "color": "#fbbf24",
+                "value": 95
+              },
+              {
+                "color": "#FFB300",
+                "value": 99
+              },
+              {
+                "color": "#4ade80",
+                "value": 99.9
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 8,
+        "x": 8,
+        "y": 0
+      },
+      "id": 2,
+      "options": {
+        "colorMode": "background_solid",
+        "graphMode": "area",
+        "justifyMode": "center",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "value_and_name"
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "fffjikve8llhce"
+          },
+          "expr": "avg_over_time(probe_success{job=\"probe-traefik-services\",instance=\"updatecenter.iamworkin.lan\"}[24h]) * 100",
+          "refId": "A",
+          "legendFormat": "24h Uptime"
+        }
+      ],
+      "title": "24-Hour Uptime",
+      "transparent": true,
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "fffjikve8llhce"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "max": 30,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "#f87171",
+                "value": null
+              },
+              {
+                "color": "#fbbf24",
+                "value": 2
+              },
+              {
+                "color": "#4ade80",
+                "value": 7
+              }
+            ]
+          },
+          "unit": "d"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 8,
+        "x": 16,
+        "y": 0
+      },
+      "id": 3,
+      "options": {
+        "minVizHeight": 75,
+        "minVizWidth": 75,
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showThresholdLabels": false,
+        "showThresholdMarkers": true
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "fffjikve8llhce"
+          },
+          "expr": "(probe_ssl_earliest_cert_expiry{job=\"probe-traefik-services\",instance=\"updatecenter.iamworkin.lan\"} - time()) / 86400",
+          "refId": "A",
+          "legendFormat": "Days Remaining"
+        }
+      ],
+      "title": "Cert Expiry (Days)",
+      "transparent": true,
+      "type": "gauge"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "fffjikve8llhce"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Response Time (seconds)",
+            "drawStyle": "line",
+            "fillOpacity": 12,
+            "gradientMode": "scheme",
+            "lineInterpolation": "smooth",
+            "lineWidth": 2,
+            "pointSize": 4,
+            "showPoints": "never",
+            "spanNulls": true,
+            "thresholdsStyle": {
+              "mode": "dashed"
+            }
+          },
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "#4ade80",
+                "value": null
+              },
+              {
+                "color": "#fbbf24",
+                "value": 2
+              },
+              {
+                "color": "#f87171",
+                "value": 5
+              }
+            ]
+          },
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 14,
+        "x": 0,
+        "y": 4
+      },
+      "id": 4,
+      "options": {
+        "legend": {
+          "calcs": [
+            "lastNotNull",
+            "mean",
+            "max"
+          ],
+          "displayMode": "table",
+          "placement": "right"
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "fffjikve8llhce"
+          },
+          "expr": "probe_duration_seconds{job=\"probe-traefik-services\",instance=\"updatecenter.iamworkin.lan\"}",
+          "refId": "A",
+          "legendFormat": "Probe Duration"
+        }
+      ],
+      "timeFrom": "1h",
+      "title": "Response Time (1h Trend)",
+      "transparent": true,
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "fffjikve8llhce"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 10,
+        "x": 14,
+        "y": 4
+      },
+      "id": 5,
+      "options": {
+        "alertInstanceLabelFilter": "{instance=\"updatecenter.iamworkin.lan\"}",
+        "alertName": "",
+        "dashboardAlerts": false,
+        "groupBy": [],
+        "groupMode": "default",
+        "maxItems": 10,
+        "sortOrder": 1,
+        "stateFilter": {
+          "error": true,
+          "firing": true,
+          "noData": true,
+          "normal": false,
+          "pending": true
+        },
+        "viewMode": "list"
+      },
+      "title": "Active Alerts",
+      "type": "alertlist"
+    },
+    {
+      "collapsed": false,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 12
+      },
+      "id": 20,
+      "title": "OTEL Counters — Track 1D",
+      "type": "row"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "fffjikve8llhce"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "lineWidth": 1,
+            "fillOpacity": 10
+          },
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 13
+      },
+      "id": 21,
+      "options": {
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["mean", "lastNotNull"]
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "fffjikve8llhce"
+          },
+          "expr": "sum by (status) (rate(updatecenter_manifest_requests_total[5m]))",
+          "refId": "A",
+          "legendFormat": "status={{status}}"
+        }
+      ],
+      "title": "Manifest Requests rate by status (5m)",
+      "transparent": true,
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "fffjikve8llhce"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "lineWidth": 1,
+            "fillOpacity": 10
+          },
+          "unit": "Bps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 13
+      },
+      "id": 22,
+      "options": {
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["mean", "lastNotNull"]
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "fffjikve8llhce"
+          },
+          "expr": "sum by (slug) (rate(updatecenter_bundle_download_bytes_total[5m]))",
+          "refId": "A",
+          "legendFormat": "{{slug}}"
+        }
+      ],
+      "title": "Bundle Download Throughput by slug (5m)",
+      "transparent": true,
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "fffjikve8llhce"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "lineWidth": 1,
+            "fillOpacity": 10
+          },
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 21
+      },
+      "id": 23,
+      "options": {
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["mean", "lastNotNull"]
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "fffjikve8llhce"
+          },
+          "expr": "sum by (status) (rate(updatecenter_checkins_total[5m]))",
+          "refId": "A",
+          "legendFormat": "status={{status}}"
+        }
+      ],
+      "title": "Agent Check-in Rate by status (5m)",
+      "transparent": true,
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "fffjikve8llhce"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              { "color": "#4ade80", "value": null },
+              { "color": "#f87171", "value": 1 }
+            ]
+          },
+          "unit": "none",
+          "decimals": 2
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 6,
+        "x": 12,
+        "y": 21
+      },
+      "id": 24,
+      "options": {
+        "colorMode": "background",
+        "graphMode": "area",
+        "justifyMode": "center",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": ["sum"],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "value_and_name"
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "fffjikve8llhce"
+          },
+          "expr": "increase(updatecenter_signature_verify_failures_total[1h])",
+          "refId": "A",
+          "legendFormat": "Sig Verify Failures (1h)"
+        }
+      ],
+      "title": "Signature Verify Failures (1h)",
+      "transparent": true,
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "fffjikve8llhce"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "lineWidth": 1,
+            "fillOpacity": 10
+          },
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 6,
+        "x": 18,
+        "y": 21
+      },
+      "id": 25,
+      "options": {
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["mean", "lastNotNull"]
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "fffjikve8llhce"
+          },
+          "expr": "sum by (slug, channel) (rate(updatecenter_release_publishes_total[5m]))",
+          "refId": "A",
+          "legendFormat": "{{slug}}/{{channel}}"
+        }
+      ],
+      "title": "Release Publishes rate by slug/channel (5m)",
+      "transparent": true,
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "fffjikve8llhce"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "lineWidth": 1,
+            "fillOpacity": 10
+          },
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 29
+      },
+      "id": 26,
+      "options": {
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["mean", "lastNotNull"]
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "fffjikve8llhce"
+          },
+          "expr": "sum by (kind, status) (rate(updatecenter_bundle_downloads_total[5m]))",
+          "refId": "A",
+          "legendFormat": "{{kind}} / {{status}}"
+        }
+      ],
+      "title": "Bundle Download Requests by kind/status (5m)",
+      "transparent": true,
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "fffjikve8llhce"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "lineWidth": 2,
+            "fillOpacity": 20
+          },
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              { "color": "#4ade80", "value": null },
+              { "color": "#f87171", "value": 0.01 }
+            ]
+          },
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 29
+      },
+      "id": 27,
+      "options": {
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["mean", "lastNotNull"]
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "fffjikve8llhce"
+          },
+          "expr": "rate(updatecenter_signature_verify_failures_total[5m])",
+          "refId": "A",
+          "legendFormat": "Sig verify failures/s"
+        }
+      ],
+      "title": "Signature Verify Failure Rate (5m) — Critical if >0",
+      "transparent": true,
+      "type": "timeseries"
+    }
+  ],
+  "refresh": "30s",
+  "schemaVersion": 39,
+  "style": "dark",
+  "tags": [
+    "blue-jay",
+    "flowercore",
+    "synthetic",
+    "updatecenter",
+    "otel"
+  ],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-24h",
+    "to": "now"
+  },
+  "timezone": "browser",
+  "title": "FlowerCore.UpdateCenter Dashboard",
+  "uid": "fc-updatecenter",
+  "version": 2
+}

apps/monitoring/flowercore-remotedesktop-grafana-dashboard.grafana.txt

@@ -0,0 +1,226 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "legend": {
+          "displayMode": "table",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "single"
+        }
+      },
+      "targets": [
+        {
+          "editorMode": "code",
+          "expr": "sum by (event) (increase(fc_desktop_session_events_total[$__rate_interval]))",
+          "legendFormat": "{{event}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "RemoteDesktop Session Events",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "id": 2,
+      "options": {
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showUnfilled": true
+      },
+      "targets": [
+        {
+          "editorMode": "code",
+          "expr": "sum by (template, event) (increase(fc_desktop_session_events_total[24h]))",
+          "legendFormat": "{{template}} {{event}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "24h Session Events By Template",
+      "type": "bargauge"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "id": 3,
+      "options": {
+        "legend": {
+          "displayMode": "table",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "single"
+        }
+      },
+      "targets": [
+        {
+          "editorMode": "code",
+          "expr": "fc_desktop_pool_ready",
+          "legendFormat": "{{template}} ready",
+          "range": true,
+          "refId": "A"
+        },
+        {
+          "editorMode": "code",
+          "expr": "fc_desktop_pool_desired",
+          "legendFormat": "{{template}} desired",
+          "range": true,
+          "refId": "B"
+        }
+      ],
+      "title": "Warm Pool Ready vs Desired",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 1
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "id": 4,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "none",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "targets": [
+        {
+          "editorMode": "code",
+          "expr": "sum(increase(fc_desktop_session_events_total{event=\"connect\",browser_datasource=\"json\"}[24h])) - sum(increase(fc_desktop_session_events_total{event=\"disconnect\"}[24h]))",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "24h Connect Minus Disconnect",
+      "type": "stat"
+    }
+  ],
+  "refresh": "30s",
+  "schemaVersion": 39,
+  "style": "dark",
+  "tags": [
+    "flowercore",
+    "remotedesktop",
+    "guacamole"
+  ],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-24h",
+    "to": "now"
+  },
+  "timezone": "browser",
+  "title": "FlowerCore RemoteDesktop",
+  "uid": "flowercore-remotedesktop",
+  "version": 1
+}

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"
@@ -464,11 +479,11 @@ data:
               - "https://gitea.iamworkin.lan/"
               - "https://argocd.iamworkin.lan/"
               - "https://intranet.iamworkin.lan/"
-              - "https://signage.iamworkin.lan/"
+              - "https://signage.iamworkin.lan/healthz"   # root 401 auth-gated 2026-06-01; /healthz anon 200
               - "https://kiosk.iamworkin.lan/"
               - "https://media.iamworkin.lan/"
-              - "https://mysql.iamworkin.lan/"
+              - "https://mysql.iamworkin.lan/healthz"   # root 401 auth-gated 2026-06-01; /healthz anon 200
-              - "https://php.iamworkin.lan/"
+              - "https://php.iamworkin.lan/healthz"     # root 401 auth-gated 2026-06-01; /healthz anon 200
               - "https://zabbix.iamworkin.lan/"
               - "https://desktop.iamworkin.lan/"
               - "https://print.iamworkin.lan/"
@@ -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
@@ -974,6 +1065,39 @@ 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
@@ -1024,6 +1148,72 @@ data:
               summary: "Longhorn node {{ $labels.node }} not Ready"
               description: "Node {{ $labels.node }} reports ready=false (reason: {{ $labels.condition_reason }}). Volumes scheduled to this node will be unavailable until it recovers."
 
+      # ============================================================
+      # FC Signage Marquee Performance — Track 3 + 8 (2026-05-06)
+      # Live-mirrored from FlowerCore.Notes/scripts/monitoring/alerts.yml.
+      # Source-of-truth for the live Podman Prometheus on noc1 is the
+      # Notes file; this K8s ConfigMap exists so a future migration to
+      # in-cluster Prometheus inherits the ruleset automatically.
+      # See feedback_monitoring_k8s_target_vs_live_podman.
+      # ============================================================
+      - name: fc-signage-marquee
+        rules:
+          - alert: MarqueeDroppedFramesHigh
+            expr: |
+              (
+                sum by (renderer, phase, node_id) (rate(marquee_dropped_frames_total[5m]))
+                /
+                sum by (renderer, phase, node_id) (rate(marquee_render_latency_ms_count[5m]))
+              ) > 0.05
+              unless on()
+              absent_over_time(marquee_dropped_frames_total[7d])
+            for: 5m
+            labels:
+              severity: warning
+              service: signage
+              alert_channel: irc
+            annotations:
+              summary: "Marquee dropped-frame rate >5% on {{ $labels.renderer }}/{{ $labels.node_id }} ({{ $labels.phase }})"
+              description: "Renderer {{ $labels.renderer }} on {{ $labels.node_id }} drops >5% of frames during {{ $labels.phase }}. Animation visibly stuttery."
+
+          - alert: MarqueeRenderLatencyP99High
+            expr: |
+              histogram_quantile(
+                0.99,
+                sum by (renderer, phase, node_id, le) (rate(marquee_render_latency_ms_bucket[5m]))
+              ) > 16
+              unless on()
+              absent_over_time(marquee_render_latency_ms_bucket[7d])
+            for: 10m
+            labels:
+              severity: warning
+              service: signage
+              alert_channel: irc
+            annotations:
+              summary: "Marquee render latency p99 > 16ms on {{ $labels.renderer }}/{{ $labels.node_id }} ({{ $labels.phase }})"
+              description: "Per-frame render latency p99 has exceeded the Pi-class 16ms budget for 10 minutes."
+
+          - alert: MarqueeAnimationDurationDrift
+            expr: |
+              abs(
+                histogram_quantile(0.5, sum by (renderer, phase, le) (rate(marquee_animation_duration_ms_bucket[15m])))
+                -
+                on (phase) group_left() avg by (phase) (marquee_animation_duration_target_ms)
+              )
+              /
+              on (phase) group_left() avg by (phase) (marquee_animation_duration_target_ms)
+              > 0.10
+              unless on()
+              absent_over_time(marquee_animation_duration_ms_bucket[7d])
+            for: 15m
+            labels:
+              severity: info
+              service: signage
+              alert_channel: irc
+            annotations:
+              summary: "Marquee animation duration drifting > 10% on {{ $labels.renderer }} ({{ $labels.phase }})"
+              description: "Median observed cycle duration deviates from target DurationMs by >10%. Could indicate browser tab throttling, GPU pressure, or phase-advancement bug."
+
 # =============================================================================
 # ConfigMap: Blackbox Exporter Configuration
 # =============================================================================
@@ -1084,24 +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())
@@ -1134,52 +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", []):
@@ -1194,22 +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()
 
 # =============================================================================
@@ -3296,6 +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
@@ -3328,6 +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/multus/multus.yaml

@@ -0,0 +1,297 @@
+# =============================================================================
+# Multus CNI — Meta-CNI for multi-network attachment to pods/VMs
+# =============================================================================
+# Purpose: enable KubeVirt VMs (and any future workload) to attach additional
+# network interfaces beyond the default Calico-managed pod network. Required
+# for ci1 (Windows Server 2025 KubeVirt VM) to bridge onto PROD VLAN 57.
+#
+# Source: upstream k8snetworkplumbingwg/multus-cni v4.2.2
+#   https://github.com/k8snetworkplumbingwg/multus-cni/blob/v4.2.2/deployments/multus-daemonset-thick.yml
+#
+# Inlined verbatim (with project header + version pin annotation) for
+# reproducibility and air-gap safety. Bumping versions = edit this file +
+# git push. ArgoCD picks up via the bluejay-infra ApplicationSet
+# (apps/* directory generator on main).
+#
+# Why thick plugin (not thin):
+#   - Thick = daemon + thin shim binary; daemon handles NAD watch + CRD reads
+#     centrally so each pod's CNI ADD doesn't hit the K8s API server. Better
+#     for clusters with many NAD-using pods.
+#   - Thin = each CNI ADD process directly contacts K8s API. Simpler but
+#     scales worse and has more failure modes.
+#   - KubeVirt + multi-VM workload pattern fits thick perfectly.
+#
+# Cluster context (verified 2026-05-08):
+#   - RKE2 v1.34.5 on 3 nodes (rke2-server, rke2-agent1, rke2-agent2)
+#   - Calico CNI (Tigera-managed) at /etc/cni/net.d + /opt/cni/bin (default)
+#   - openSUSE Leap 16, kernel 6.12, containerd 2.1.5
+#   - host bridge for PROD VLAN 57 = `br-prod` (PUPPET HOST WORK — see Phase 1.5
+#     in docs/infrastructure/windows-server-build-runner-plan.md)
+#
+# Version pin: snapshot-thick → pinning to v4.2.2 release tag at deploy time
+# would require a private mirror of the image. Upstream `snapshot-thick` tag
+# is updated on every release, so for now we trust upstream + Calico's
+# established pattern. Pin to a specific SHA256 once we mirror to Gitea OCI.
+#
+# Apply (once committed to bluejay-infra main, ApplicationSet auto-syncs):
+#   git add apps/multus/multus.yaml && git commit && git push origin main
+#   # ArgoCD `infra-multus` Application appears within 3 min via ApplicationSet
+#
+# Verify:
+#   kubectl -n kube-system get ds kube-multus-ds
+#   kubectl -n kube-system rollout status ds kube-multus-ds
+#   kubectl get crd network-attachment-definitions.k8s.cni.cncf.io
+# =============================================================================
+
+---
+apiVersion: apiextensions.k8s.io/v1
+kind: CustomResourceDefinition
+metadata:
+  name: network-attachment-definitions.k8s.cni.cncf.io
+  annotations:
+    bluejay.iamworkin.lan/source: "k8snetworkplumbingwg/multus-cni v4.2.2"
+spec:
+  group: k8s.cni.cncf.io
+  scope: Namespaced
+  names:
+    plural: network-attachment-definitions
+    singular: network-attachment-definition
+    kind: NetworkAttachmentDefinition
+    shortNames:
+      - net-attach-def
+  versions:
+    - name: v1
+      served: true
+      storage: true
+      schema:
+        openAPIV3Schema:
+          description: 'NetworkAttachmentDefinition is a CRD schema specified by the Network Plumbing
+            Working Group to express the intent for attaching pods to one or more logical or physical
+            networks. More information available at: https://github.com/k8snetworkplumbingwg/multi-net-spec'
+          type: object
+          properties:
+            apiVersion:
+              type: string
+            kind:
+              type: string
+            metadata:
+              type: object
+            spec:
+              description: 'NetworkAttachmentDefinition spec defines the desired state of a network attachment'
+              type: object
+              properties:
+                config:
+                  description: 'NetworkAttachmentDefinition config is a JSON-formatted CNI configuration'
+                  type: string
+---
+kind: ClusterRole
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: multus
+rules:
+  - apiGroups: ["k8s.cni.cncf.io"]
+    resources:
+      - '*'
+    verbs:
+      - '*'
+  - apiGroups:
+      - ""
+    resources:
+      - pods
+      - pods/status
+    verbs:
+      - get
+      - list
+      - update
+      - watch
+  - apiGroups:
+      - ""
+      - events.k8s.io
+    resources:
+      - events
+    verbs:
+      - create
+      - patch
+      - update
+---
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: multus
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: multus
+subjects:
+  - kind: ServiceAccount
+    name: multus
+    namespace: kube-system
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: multus
+  namespace: kube-system
+---
+kind: ConfigMap
+apiVersion: v1
+metadata:
+  name: multus-daemon-config
+  namespace: kube-system
+  labels:
+    tier: node
+    app: multus
+data:
+  daemon-config.json: |
+    {
+        "chrootDir": "/hostroot",
+        "cniVersion": "0.3.1",
+        "logLevel": "verbose",
+        "logToStderr": true,
+        "cniConfigDir": "/host/etc/cni/net.d",
+        "multusAutoconfigDir": "/host/etc/cni/net.d",
+        "multusConfigFile": "auto",
+        "socketDir": "/host/run/multus/"
+    }
+---
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: kube-multus-ds
+  namespace: kube-system
+  labels:
+    tier: node
+    app: multus
+    name: multus
+spec:
+  selector:
+    matchLabels:
+      name: multus
+  updateStrategy:
+    type: RollingUpdate
+  template:
+    metadata:
+      labels:
+        tier: node
+        app: multus
+        name: multus
+    spec:
+      hostNetwork: true
+      hostPID: true
+      tolerations:
+        - operator: Exists
+          effect: NoSchedule
+        - operator: Exists
+          effect: NoExecute
+      serviceAccountName: multus
+      containers:
+        - 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: "512Mi"
+            limits:
+              cpu: "100m"
+              memory: "1Gi"
+          securityContext:
+            privileged: true
+          terminationMessagePolicy: FallbackToLogsOnError
+          volumeMounts:
+            - name: cni
+              mountPath: /host/etc/cni/net.d
+            # multus-daemon expects that cnibin path must be identical between pod and container host.
+            # e.g. if the cni bin is in '/opt/cni/bin' on the container host side, then it should be mount to '/opt/cni/bin' in multus-daemon,
+            # not to any other directory, like '/opt/bin' or '/usr/bin'.
+            - name: cnibin
+              mountPath: /opt/cni/bin
+            - name: host-run
+              mountPath: /host/run
+            - name: host-var-lib-cni-multus
+              mountPath: /var/lib/cni/multus
+            - name: host-var-lib-kubelet
+              mountPath: /var/lib/kubelet
+              mountPropagation: HostToContainer
+            - name: host-run-k8s-cni-cncf-io
+              mountPath: /run/k8s.cni.cncf.io
+            - name: host-run-netns
+              mountPath: /run/netns
+              mountPropagation: HostToContainer
+            - name: multus-daemon-config
+              mountPath: /etc/cni/net.d/multus.d
+              readOnly: true
+            - name: hostroot
+              mountPath: /hostroot
+              mountPropagation: HostToContainer
+            - mountPath: /etc/cni/multus/net.d
+              name: multus-conf-dir
+          env:
+            - name: MULTUS_NODE_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.nodeName
+      initContainers:
+        - name: install-multus-binary
+          image: ghcr.io/k8snetworkplumbingwg/multus-cni:snapshot-thick
+          command:
+            - "sh"
+            - "-c"
+            - "cp /usr/src/multus-cni/bin/multus-shim /host/opt/cni/bin/multus-shim && cp /usr/src/multus-cni/bin/passthru /host/opt/cni/bin/passthru"
+          resources:
+            requests:
+              cpu: "10m"
+              memory: "15Mi"
+          securityContext:
+            privileged: true
+          terminationMessagePolicy: FallbackToLogsOnError
+          volumeMounts:
+            - name: cnibin
+              mountPath: /host/opt/cni/bin
+              mountPropagation: Bidirectional
+      terminationGracePeriodSeconds: 10
+      volumes:
+        - name: cni
+          hostPath:
+            path: /etc/cni/net.d
+        - name: cnibin
+          hostPath:
+            path: /opt/cni/bin
+        - name: hostroot
+          hostPath:
+            path: /
+        - name: multus-daemon-config
+          configMap:
+            name: multus-daemon-config
+            items:
+            - key: daemon-config.json
+              path: daemon-config.json
+        - name: host-run
+          hostPath:
+            path: /run
+        - name: host-var-lib-cni-multus
+          hostPath:
+            path: /var/lib/cni/multus
+        - name: host-var-lib-kubelet
+          hostPath:
+            path: /var/lib/kubelet
+        - name: host-run-k8s-cni-cncf-io
+          hostPath:
+            path: /run/k8s.cni.cncf.io
+        - name: host-run-netns
+          hostPath:
+            path: /run/netns/
+        - name: multus-conf-dir
+          hostPath:
+            path: /etc/cni/multus/net.d

apps/selenium/network-policy.yaml

@@ -0,0 +1,226 @@
+# Selenium Grid NetworkPolicy.
+#
+# Captured into bluejay-infra 2026-05-07 during the regroup audit. This
+# NetworkPolicy was previously applied via `kubectl apply` directly to
+# the cluster with no source-of-truth anywhere — a fresh cluster rebuild
+# would have lost all of it (including the Selenium Grid → Traefik VIP
+# allow rule for AAT runs against `*.iamworkin.lan` services).
+#
+# The Selenium Grid Deployment + Services themselves are still managed
+# outside ArgoCD (deployed via raw kubectl from the original Selenium
+# Grid bring-up). Migrating those into bluejay-infra is a separate lane —
+# this commit only restores GitOps repeatability for the NetworkPolicy.
+#
+# Rules captured from the live cluster's `kubectl get netpol -n selenium
+# selenium-netpol -o yaml` on 2026-05-07. Originally applied 2026-03-15
+# (from `metadata.creationTimestamp` before the field was stripped).
+#
+# Allows:
+#   - Egress: CoreDNS, intra-namespace pod-to-pod (4442/4443/4444/5555),
+#     Traefik VIP for `*.iamworkin.lan` AAT runs, all FC namespaces on
+#     standard FC service ports (5100/5200/5300/5400/8080), pod CIDR
+#     (10.42.0.0/16) + service CIDR (10.43.0.0/16) for the same ports,
+#     LAN gateway range (10.0.56.0/24) for HTTPS, edge2 CUPS print
+#     (10.0.57.16:5200), public internet 80/443 (excluding RFC1918), and
+#     fc-signage:5190 for the signage AAT lane.
+#   - Ingress: Traefik (4444 + 8089 ACME-solver-style), intra-pod,
+#     telephony / gitea / fc-system / fc-signage / github-runner namespaces
+#     on 4444.
+#
+# 2026-05-25: added github-runner ingress on 4444 so CI jobs running in
+# self-hosted runner pods (e.g. FlowerCore.Print.Web `help-screenshots`)
+# can reach the grid. Without this allow, the session POST to
+# `selenium-hub.selenium.svc.cluster.local:4444` was DNAT'd to the hub
+# pod IP and then dropped at the Calico ingress hook — Selenium UI showed
+# 0/4 sessions while the .NET HTTP client timed out at 60s. Same family
+# as `feedback_netpol_dnat_backend_port`, wrong-source-namespace flavor.
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: selenium-netpol
+  namespace: selenium
+  labels:
+    app.kubernetes.io/part-of: selenium
+    app.kubernetes.io/component: isolation
+spec:
+  egress:
+  - ports:
+    - port: 53
+      protocol: UDP
+    - port: 53
+      protocol: TCP
+    to:
+    - namespaceSelector:
+        matchLabels:
+          kubernetes.io/metadata.name: kube-system
+  - ports:
+    - port: 4442
+      protocol: TCP
+    - port: 4443
+      protocol: TCP
+    - port: 4444
+      protocol: TCP
+    - port: 5555
+      protocol: TCP
+    to:
+    - podSelector: {}
+  - ports:
+    - port: 443
+      protocol: TCP
+    - port: 80
+      protocol: TCP
+    to:
+    - ipBlock:
+        cidr: 10.0.56.200/32
+  - ports:
+    - port: 443
+      protocol: TCP
+    - port: 80
+      protocol: TCP
+    - port: 5200
+      protocol: TCP
+    - port: 5300
+      protocol: TCP
+    - port: 5400
+      protocol: TCP
+    - port: 5100
+      protocol: TCP
+    - port: 8080
+      protocol: TCP
+    to:
+    - namespaceSelector: {}
+  - ports:
+    - port: 443
+      protocol: TCP
+    - port: 80
+      protocol: TCP
+    - port: 8443
+      protocol: TCP
+    - port: 8080
+      protocol: TCP
+    - port: 5200
+      protocol: TCP
+    - port: 5300
+      protocol: TCP
+    - port: 5400
+      protocol: TCP
+    - port: 5100
+      protocol: TCP
+    to:
+    - ipBlock:
+        cidr: 10.43.0.0/16
+  - ports:
+    - port: 443
+      protocol: TCP
+    - port: 80
+      protocol: TCP
+    - port: 8443
+      protocol: TCP
+    - port: 8080
+      protocol: TCP
+    - port: 5200
+      protocol: TCP
+    - port: 5300
+      protocol: TCP
+    - port: 5400
+      protocol: TCP
+    - port: 5100
+      protocol: TCP
+    to:
+    - ipBlock:
+        cidr: 10.42.0.0/16
+  - ports:
+    - port: 443
+      protocol: TCP
+    - port: 80
+      protocol: TCP
+    - port: 8443
+      protocol: TCP
+    to:
+    - ipBlock:
+        cidr: 10.0.56.0/24
+  - ports:
+    - port: 5200
+      protocol: TCP
+    to:
+    - ipBlock:
+        cidr: 10.0.57.16/32
+  - ports:
+    - port: 80
+      protocol: TCP
+    - port: 443
+      protocol: TCP
+    to:
+    - ipBlock:
+        cidr: 0.0.0.0/0
+        except:
+        - 172.16.0.0/12
+        - 192.168.0.0/16
+  - ports:
+    - port: 5190
+      protocol: TCP
+    to:
+    - namespaceSelector:
+        matchLabels:
+          kubernetes.io/metadata.name: fc-signage
+  ingress:
+  - from:
+    - namespaceSelector:
+        matchLabels:
+          kubernetes.io/metadata.name: traefik-system
+    ports:
+    - port: 4444
+      protocol: TCP
+    - port: 8089
+      protocol: TCP
+  - from:
+    - podSelector: {}
+    ports:
+    - port: 4442
+      protocol: TCP
+    - port: 4443
+      protocol: TCP
+    - port: 4444
+      protocol: TCP
+    - port: 5555
+      protocol: TCP
+  - from:
+    - namespaceSelector:
+        matchLabels:
+          kubernetes.io/metadata.name: telephony
+    ports:
+    - port: 4444
+      protocol: TCP
+  - from:
+    - namespaceSelector:
+        matchLabels:
+          kubernetes.io/metadata.name: gitea
+    ports:
+    - port: 4444
+      protocol: TCP
+  - from:
+    - namespaceSelector:
+        matchLabels:
+          kubernetes.io/metadata.name: fc-system
+    ports:
+    - port: 4444
+      protocol: TCP
+  - from:
+    - namespaceSelector:
+        matchLabels:
+          kubernetes.io/metadata.name: fc-signage
+    ports:
+    - port: 4444
+      protocol: TCP
+  - from:
+    - namespaceSelector:
+        matchLabels:
+          kubernetes.io/metadata.name: github-runner
+    ports:
+    - port: 4444
+      protocol: TCP
+  podSelector: {}
+  policyTypes:
+  - Ingress
+  - Egress
+

apps/selenium/selenium-grid.yaml

@@ -0,0 +1,427 @@
+# Selenium Grid 4 — RKE2 deployment
+#
+# Hub + chrome + firefox + edge browser nodes serving fleet-wide AAT runs from
+# the GitHub Actions self-hosted runners. ArgoCD owns this namespace from
+# 2026-05-25 (`infra-selenium` Application; previously these resources were
+# orphan kubectl-applied since 2026-03-15).
+#
+# Endpoints:
+#   - Internal cluster: http://selenium-hub.selenium.svc.cluster.local:4444
+#   - LAN LoadBalancer (MetalLB): http://10.0.56.208:4444
+#   - Traefik public: https://selenium.iamworkin.lan
+#
+# Browser maxSessions:
+#   - chrome 2  (bumped from 1 on 2026-05-25 morning-routine — AAT-heavy
+#                Print.Web help-screenshots was the global bottleneck;
+#                see commit history for ops/runner-replica-rightsize)
+#   - firefox 1
+#   - edge 1
+#
+# Screenshots + video recording write to NFS via the chrome video sidecar.
+# See: CLAUDE.md "Selenium Grid & Visual AAT Testing" + bluejay-infra ADR notes.
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: selenium-hub
+    app.kubernetes.io/name: selenium-hub
+    app.kubernetes.io/part-of: selenium-grid
+  name: selenium-hub
+  namespace: selenium
+spec:
+  ports:
+  - name: web
+    port: 4444
+    targetPort: 4444
+  - name: publish
+    port: 4442
+    targetPort: 4442
+  - name: subscribe
+    port: 4443
+    targetPort: 4443
+  selector:
+    app: selenium-hub
+  type: ClusterIP
+---
+apiVersion: v1
+kind: Service
+metadata:
+  annotations:
+    metallb.io/ip-allocated-from-pool: bluejay-pool
+    metallb.universe.tf/loadBalancerIPs: 10.0.56.208
+  labels:
+    app: selenium-hub
+    component: external-access
+  name: selenium-hub-external
+  namespace: selenium
+spec:
+  clusterIP: 10.43.90.147
+  clusterIPs:
+  - 10.43.90.147
+  externalTrafficPolicy: Local
+  healthCheckNodePort: 32213
+  ports:
+  - name: web
+    nodePort: 32411
+    port: 4444
+    targetPort: 4444
+  - name: publish
+    nodePort: 32068
+    port: 4442
+    targetPort: 4442
+  - name: subscribe
+    nodePort: 31000
+    port: 4443
+    targetPort: 4443
+  selector:
+    app: selenium-hub
+  type: LoadBalancer
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: selenium-hub
+    app.kubernetes.io/name: selenium-hub
+    app.kubernetes.io/part-of: selenium-grid
+  name: selenium-hub
+  namespace: selenium
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: selenium-hub
+  template:
+    metadata:
+      labels:
+        app: selenium-hub
+        app.kubernetes.io/name: selenium-hub
+        app.kubernetes.io/part-of: selenium-grid
+    spec:
+      containers:
+      - env:
+        - name: SE_NODE_SESSION_TIMEOUT
+          value: '300'
+        - name: SE_SESSION_REQUEST_TIMEOUT
+          value: '300'
+        - name: SE_SESSION_RETRY_INTERVAL
+          value: '5'
+        - name: JAVA_OPTS
+          value: -Xmx512m
+        image: selenium/hub:4.27.0
+        livenessProbe:
+          httpGet:
+            path: /wd/hub/status
+            port: 4444
+          initialDelaySeconds: 30
+          periodSeconds: 15
+          timeoutSeconds: 5
+        name: selenium-hub
+        ports:
+        - containerPort: 4444
+          name: web
+        - containerPort: 4442
+          name: publish
+        - containerPort: 4443
+          name: subscribe
+        readinessProbe:
+          httpGet:
+            path: /wd/hub/status
+            port: 4444
+          initialDelaySeconds: 10
+          periodSeconds: 5
+          timeoutSeconds: 5
+        # Hub baseline working set ~766Mi on 2026-05-25 (75% of prior 1Gi
+        # limit). Bump to 1.5Gi / 1Gi to keep ~50% headroom; matches the
+        # stampede-buffer pattern documented for multus
+        # (feedback_k8s_cni_multus_sizing). CPU left alone — observed 54m
+        # against a 500m limit, no contention.
+        resources:
+          limits:
+            cpu: 500m
+            memory: 1536Mi
+          requests:
+            cpu: 250m
+            memory: 1Gi
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: selenium-node-chrome
+    app.kubernetes.io/name: selenium-node-chrome
+    app.kubernetes.io/part-of: selenium-grid
+  name: selenium-node-chrome
+  namespace: selenium
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: selenium-node-chrome
+  template:
+    metadata:
+      labels:
+        app: selenium-node-chrome
+        app.kubernetes.io/name: selenium-node-chrome
+        app.kubernetes.io/part-of: selenium-grid
+    spec:
+      containers:
+      - env:
+        - name: SE_EVENT_BUS_HOST
+          value: selenium-hub
+        - name: SE_EVENT_BUS_PUBLISH_PORT
+          value: '4442'
+        - name: SE_EVENT_BUS_SUBSCRIBE_PORT
+          value: '4443'
+        - name: SE_NODE_MAX_SESSIONS
+          value: '2'
+        - name: SE_NODE_OVERRIDE_MAX_SESSIONS
+          value: 'false'
+        - name: SE_VNC_NO_PASSWORD
+          value: '1'
+        - name: SE_SCREEN_WIDTH
+          value: '1920'
+        - name: SE_SCREEN_HEIGHT
+          value: '1080'
+        - name: SE_NODE_SESSION_TIMEOUT
+          value: '300'
+        image: selenium/node-chrome:4.27.0
+        livenessProbe:
+          httpGet:
+            path: /status
+            port: 5555
+          initialDelaySeconds: 30
+          periodSeconds: 15
+        name: selenium-chrome
+        ports:
+        - containerPort: 5555
+          name: node
+        readinessProbe:
+          httpGet:
+            path: /status
+            port: 5555
+          initialDelaySeconds: 15
+          periodSeconds: 5
+        # Chromium-based browser node. Bumped from 1Gi -> 2Gi (req 512Mi
+        # -> 1Gi) on 2026-05-25 — Edge had 51 OOMKills in 5d on the
+        # original 1Gi cap (~1 OOM every 2.4h), and Chrome at maxSessions=2
+        # was running 684Mi idle on the same cap. Matches the Firefox node's
+        # tested-stable 2Gi limit. CPU unchanged.
+        resources:
+          limits:
+            cpu: '1'
+            memory: 2Gi
+          requests:
+            cpu: 500m
+            memory: 1Gi
+        volumeMounts:
+        - mountPath: /dev/shm
+          name: dshm
+      - env:
+        - name: DISPLAY_CONTAINER_NAME
+          value: localhost
+        - name: SE_SCREEN_WIDTH
+          value: '1920'
+        - name: SE_SCREEN_HEIGHT
+          value: '1080'
+        - name: SE_VIDEO_FILE_NAME
+          value: auto
+        - name: SE_VIDEO_UPLOAD_ENABLED
+          value: 'false'
+        image: selenium/video:ffmpeg-7.1-20250101
+        name: video
+        resources:
+          limits:
+            cpu: 500m
+            memory: 768Mi
+          requests:
+            cpu: 250m
+            memory: 384Mi
+        volumeMounts:
+        - mountPath: /videos
+          name: selenium-videos
+      volumes:
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 2Gi
+        name: dshm
+      - emptyDir:
+          sizeLimit: 5Gi
+        name: selenium-videos
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: selenium-node-firefox
+    app.kubernetes.io/name: selenium-node-firefox
+    app.kubernetes.io/part-of: selenium-grid
+  name: selenium-node-firefox
+  namespace: selenium
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: selenium-node-firefox
+  template:
+    metadata:
+      labels:
+        app: selenium-node-firefox
+        app.kubernetes.io/name: selenium-node-firefox
+        app.kubernetes.io/part-of: selenium-grid
+    spec:
+      containers:
+      - env:
+        - name: SE_EVENT_BUS_HOST
+          value: selenium-hub
+        - name: SE_EVENT_BUS_PUBLISH_PORT
+          value: '4442'
+        - name: SE_EVENT_BUS_SUBSCRIBE_PORT
+          value: '4443'
+        - name: SE_NODE_MAX_SESSIONS
+          value: '1'
+        - name: SE_NODE_OVERRIDE_MAX_SESSIONS
+          value: 'true'
+        - name: SE_VNC_NO_PASSWORD
+          value: '1'
+        - name: SE_START_VNC
+          value: 'false'
+        - name: SE_SCREEN_WIDTH
+          value: '1920'
+        - name: SE_SCREEN_HEIGHT
+          value: '1080'
+        - name: SE_NODE_SESSION_TIMEOUT
+          value: '300'
+        image: selenium/node-firefox:4.27.0
+        livenessProbe:
+          failureThreshold: 5
+          httpGet:
+            path: /status
+            port: 5555
+          initialDelaySeconds: 30
+          periodSeconds: 15
+          timeoutSeconds: 5
+        name: selenium-firefox
+        ports:
+        - containerPort: 5555
+          name: node
+        readinessProbe:
+          failureThreshold: 5
+          httpGet:
+            path: /status
+            port: 5555
+          initialDelaySeconds: 15
+          periodSeconds: 5
+          timeoutSeconds: 5
+        resources:
+          limits:
+            cpu: '1'
+            memory: 2Gi
+          requests:
+            cpu: 500m
+            memory: 1Gi
+        volumeMounts:
+        - mountPath: /dev/shm
+          name: dshm
+      volumes:
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 2Gi
+        name: dshm
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: selenium-node-edge
+    app.kubernetes.io/name: selenium-node-edge
+    app.kubernetes.io/part-of: selenium-grid
+  name: selenium-node-edge
+  namespace: selenium
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: selenium-node-edge
+  template:
+    metadata:
+      labels:
+        app: selenium-node-edge
+        app.kubernetes.io/name: selenium-node-edge
+        app.kubernetes.io/part-of: selenium-grid
+    spec:
+      containers:
+      - env:
+        - name: SE_EVENT_BUS_HOST
+          value: selenium-hub
+        - name: SE_EVENT_BUS_PUBLISH_PORT
+          value: '4442'
+        - name: SE_EVENT_BUS_SUBSCRIBE_PORT
+          value: '4443'
+        - name: SE_NODE_MAX_SESSIONS
+          value: '1'
+        - name: SE_NODE_OVERRIDE_MAX_SESSIONS
+          value: 'true'
+        - name: SE_VNC_NO_PASSWORD
+          value: '1'
+        - name: SE_SCREEN_WIDTH
+          value: '1920'
+        - name: SE_SCREEN_HEIGHT
+          value: '1080'
+        - name: SE_NODE_SESSION_TIMEOUT
+          value: '300'
+        image: selenium/node-edge:4.27.0
+        livenessProbe:
+          httpGet:
+            path: /status
+            port: 5555
+          initialDelaySeconds: 30
+          periodSeconds: 15
+        name: selenium-edge
+        ports:
+        - containerPort: 5555
+          name: node
+        readinessProbe:
+          httpGet:
+            path: /status
+            port: 5555
+          initialDelaySeconds: 15
+          periodSeconds: 5
+        # Chromium-based browser node. Bumped from 1Gi -> 2Gi (req 512Mi
+        # -> 1Gi) on 2026-05-25 — Edge had 51 OOMKills in 5d on the
+        # original 1Gi cap (~1 OOM every 2.4h), and Chrome at maxSessions=2
+        # was running 684Mi idle on the same cap. Matches the Firefox node's
+        # tested-stable 2Gi limit. CPU unchanged.
+        resources:
+          limits:
+            cpu: '1'
+            memory: 2Gi
+          requests:
+            cpu: 500m
+            memory: 1Gi
+        volumeMounts:
+        - mountPath: /dev/shm
+          name: dshm
+      volumes:
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 2Gi
+        name: dshm
+---
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: selenium-hub
+  namespace: selenium
+spec:
+  entryPoints:
+  - websecure
+  routes:
+  - kind: Rule
+    match: Host(`selenium.iamworkin.lan`)
+    services:
+    - name: selenium-hub
+      port: 4444
+  tls:
+    secretName: selenium-tls

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

apps/worldbuilder/README.md

@@ -0,0 +1,68 @@
+# FlowerCore.WorldBuilder
+
+ArgoCD-managed manifest for FlowerCore.WorldBuilder.Web — comic / storyboard
+authoring service that drives ComfyUI for panel image generation and
+QuestPDF for letter / A4 export.
+
+Source: `D:\git\FlowerCore\FlowerCore.WorldBuilder` (master)
+
+## Deployment order
+
+1. **DNS preflight** — `worldbuilder.iamworkin.lan -> 10.0.56.200` MUST exist
+   in pfSense Unbound before this manifest is applied, or cert-manager
+   HTTP-01 silently exponential-backs-off ~2h.
+   Memory: `feedback_pfsense_dns_required_for_acme`.
+2. **Image import to ALL RKE2 nodes** — pod can schedule to any of
+   `rke2-server` (10.0.56.11), `rke2-agent1` (10.0.56.12),
+   `rke2-agent2` (10.0.56.13). Build with:
+   ```bash
+   bash deploy/build.sh   # in FlowerCore.WorldBuilder repo
+   podman save localhost/fc-worldbuilder:v<TAG> -o /tmp/fc-worldbuilder-v<TAG>.tar
+   for h in 10.0.56.11 10.0.56.12 10.0.56.13; do
+     scp /tmp/fc-worldbuilder-v<TAG>.tar fcadmin@$h:/tmp/
+     ssh fcadmin@$h \
+       "sudo /var/lib/rancher/rke2/bin/ctr -a /run/k3s/containerd/containerd.sock \
+         -n k8s.io images import /tmp/fc-worldbuilder-v<TAG>.tar"
+   done
+   ```
+   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/studio/c32e0000-0000-4000-8000-000000000004`
+   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
+
+- `startupProbe` + `readinessProbe`: `httpGet /healthz` (registered explicitly
+  in Program.cs — anonymous, no DB or OpenAPI dependency).
+- `livenessProbe`: `tcpSocket` as a cheap fallback.
+  Memory: `feedback_k8s_probes_must_not_hit_openapi`,
+  `feedback_k8s_probes_behind_auth_middleware`.
+
+## Storage
+
+- Longhorn RWO PVC `worldbuilder-data` (5Gi) mounted at `/data`. SQLite DB
+  lives at `/data/worldbuilder.db`, generated images under `/data/gallery/`,
+  PDF/PNG exports under `/data/exports/`.
+- DataProtection keys persist to the same SQLite via
+  `AddFlowerCoreDataProtection<WorldBuilderDbContext>` — explicit migration
+  `20260429133417_Initial` already creates `fc_dp_keys`.
+  Memory: `feedback_dataprotection_keys_persist_to_app_dbcontext`,
+  `feedback_intranet_dataprotection_table_must_have_explicit_migration`.
+
+## Image generation backend
+
+Sprint 32 pins the Kubernetes profile to
+`FlowerCore:WorldBuilder:ImageGeneration:ClientMode=fake` with
+`BaseUrl=http://127.0.0.1:1`. That keeps the public/internal visitor demo
+deterministic, avoids GPU exposure, and still exercises the studio/gallery
+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

@@ -0,0 +1,256 @@
+# FlowerCore.WorldBuilder — comic / storyboard authoring service.
+#
+# Deployment + Service + PVC + Certificate + IngressRoute. ArgoCD-managed
+# end-to-end. See apps/worldbuilder/README.md for the per-deploy runbook.
+#
+# Image build (BLUEJAY-WS):
+#   bash deploy/build.sh                 # in FlowerCore.WorldBuilder repo
+#   podman save localhost/fc-worldbuilder:v<TAG> -o /tmp/fc-worldbuilder-v<TAG>.tar
+#   for h in 10.0.56.11 10.0.56.12 10.0.56.13; do
+#     scp /tmp/fc-worldbuilder-v<TAG>.tar fcadmin@$h:/tmp/
+#     ssh fcadmin@$h "sudo /var/lib/rancher/rke2/bin/ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images import /tmp/fc-worldbuilder-v<TAG>.tar"
+#   done
+---
+apiVersion: v1
+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.
+apiVersion: v1
+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
+  storageClassName: longhorn
+  resources:
+    requests:
+      storage: 5Gi
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: worldbuilder-web
+  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
+  strategy:
+    # RWO PVC + single replica. Recreate avoids multi-attach overlap.
+    type: Recreate
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: worldbuilder-web
+  template:
+    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
+        fsGroupChangePolicy: OnRootMismatch
+      containers:
+        - name: web
+          # Bump tag for each rebuild. Initial deploy: v202605062048
+          image: localhost/fc-worldbuilder:v202605062048
+          imagePullPolicy: Never
+          ports:
+            - containerPort: 8080
+              name: http
+          env:
+            - name: ASPNETCORE_URLS
+              value: "http://+:8080"
+            - name: ASPNETCORE_ENVIRONMENT
+              value: "Production"
+            - name: DOTNET_RUNNING_IN_CONTAINER
+              value: "true"
+            - name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
+              value: "false"
+            # SQLite path overrides (default appsettings uses relative paths).
+            - name: ConnectionStrings__DefaultConnection
+              value: "Data Source=/data/worldbuilder.db"
+            - name: FlowerCore__Database__Provider
+              value: "Sqlite"
+            - name: FlowerCore__Database__ConnectionStrings__Sqlite
+              value: "Data Source=/data/worldbuilder.db"
+            # Generated image gallery + exports persist on /data.
+            - name: FlowerCore__WorldBuilder__ImageStore__RootPath
+              value: "/data/gallery"
+            - name: FlowerCore__WorldBuilder__Export__RootPath
+              value: "/data/exports"
+            # 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://127.0.0.1:1"
+            - name: FlowerCore__WorldBuilder__ImageGeneration__ClientMode
+              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
+            # Server + SignalR + a single ComfyUI poller uses ~5m, so 25m is
+            # generous. Re-evaluate if active rendering/export workers ever
+            # push past the limit.
+            requests:
+              cpu: 25m
+              memory: 256Mi
+            limits:
+              cpu: 1000m
+              memory: 768Mi
+          # /healthz is registered explicitly in Program.cs (anonymous, no DB
+          # or OpenAPI dependency). Liveness uses tcpSocket as a cheap fallback
+          # in case future middleware changes accidentally gate /healthz.
+          # Memory: feedback_k8s_probes_must_not_hit_openapi,
+          #         feedback_k8s_probes_behind_auth_middleware.
+          startupProbe:
+            httpGet:
+              path: /healthz
+              port: 8080
+            initialDelaySeconds: 5
+            periodSeconds: 5
+            failureThreshold: 30
+          readinessProbe:
+            httpGet:
+              path: /healthz
+              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: data
+              mountPath: /data
+            - name: tmp
+              mountPath: /tmp
+            - name: logs
+              mountPath: /app/logs
+      volumes:
+        - name: data
+          persistentVolumeClaim:
+            claimName: worldbuilder-data
+        - name: tmp
+          emptyDir: {}
+        - name: logs
+          emptyDir: {}
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: worldbuilder-web
+  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:
+    app.kubernetes.io/name: worldbuilder-web
+  ports:
+    - name: http
+      port: 80
+      targetPort: 8080
+---
+apiVersion: cert-manager.io/v1
+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:
+    name: step-ca-acme
+    kind: ClusterIssuer
+  dnsNames:
+    - worldbuilder.iamworkin.lan
+  # step-ca ACME provisioner caps lifetime at 30d. Requesting 90d
+  # silently capped to 30d, making renewBefore 720h (30d) equal to the
+  # actual cert lifetime — triggered a perpetual renewal loop that
+  # generated 2365+ CertificateRequest objects in 18h. Match the working
+  # 720h/240h pattern used by every other FC service cert.
+  duration: 720h     # 30d (step-ca cap)
+  renewBefore: 240h  # 10d
+---
+apiVersion: traefik.io/v1alpha1
+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
+  routes:
+    - match: Host(`worldbuilder.iamworkin.lan`)
+      kind: Rule
+      services:
+        - name: worldbuilder-web
+          port: 80
+  tls:
+    secretName: worldbuilder-web-tls

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/BluejayInfraLint.Tests.csproj

@@ -0,0 +1,24 @@
+<Project Sdk="Microsoft.NET.Sdk">
+  <PropertyGroup>
+    <TargetFramework>net10.0</TargetFramework>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+    <IsPackable>false</IsPackable>
+    <TreatWarningsAsErrors>true</TreatWarningsAsErrors>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="coverlet.collector" Version="6.0.2">
+      <PrivateAssets>all</PrivateAssets>
+      <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
+    </PackageReference>
+    <PackageReference Include="FluentAssertions" Version="6.12.1" />
+    <PackageReference Include="Microsoft.NET.Test.Sdk" Version="17.12.0" />
+    <PackageReference Include="xunit" Version="2.9.2" />
+    <PackageReference Include="xunit.runner.visualstudio" Version="2.8.2">
+      <PrivateAssets>all</PrivateAssets>
+      <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
+    </PackageReference>
+    <PackageReference Include="YamlDotNet" Version="16.2.0" />
+  </ItemGroup>
+</Project>

tests/bluejay-infra-lint/DivoomPiDeployArtifactTests.cs

@@ -0,0 +1,206 @@
+using FluentAssertions;
+using Xunit;
+
+namespace BluejayInfraLint.Tests;
+
+[Trait("Category", "Unit")]
+public sealed class DivoomPiDeployArtifactTests
+{
+    private static readonly string Root = FindRepoRoot();
+    private static readonly string DmRoot = Path.Combine(Root, "apps", "fc-divoom-dm-pi-device");
+    private static readonly string TvRoot = Path.Combine(Root, "apps", "fc-divoom-tv-pi");
+
+    public static TheoryData<string> DmRequiredArtifacts => new()
+    {
+        "README.md",
+        "hiera/edge2-divoom-dm-device.overlay.yaml",
+        "puppet/profile/pi/service/divoom_dm_device.pp",
+        "puppet/templates/divoom-device-registration.json.epp",
+        "puppet/templates/flowercore-divoom-dm-agent.service.epp",
+    };
+
+    public static TheoryData<string> TvRequiredArtifacts => new()
+    {
+        "README.md",
+        "hiera/example-divoom-tv-pi.iamworkin.lan.yaml",
+        "puppet/profile/pi/service/divoom_tv.pp",
+        "systemd/flowercore-divoom-tv.service",
+        "systemd/flowercore-divoom-tv-hdmi.service",
+        "systemd/99-flowercore-divoom-tv-hdmi.rules",
+        "scripts/flowercore-divoom-tv-prelaunch.sh",
+        "scripts/flowercore-divoom-tv-launch.sh",
+        "scripts/flowercore-divoom-tv-hdmi-respond.sh",
+    };
+
+    [Theory]
+    [MemberData(nameof(DmRequiredArtifacts))]
+    public void DmDeviceArtifacts_ArePresent(string relativePath)
+    {
+        File.Exists(Path.Combine(DmRoot, relativePath.Replace('/', Path.DirectorySeparatorChar))).Should().BeTrue(relativePath);
+    }
+
+    [Theory]
+    [MemberData(nameof(TvRequiredArtifacts))]
+    public void TvPiArtifacts_ArePresent(string relativePath)
+    {
+        File.Exists(Path.Combine(TvRoot, relativePath.Replace('/', Path.DirectorySeparatorChar))).Should().BeTrue(relativePath);
+    }
+
+    [Fact]
+    public void DmDeviceReadme_DeclaresPuppetSystemdNotKubernetes()
+    {
+        var readme = ReadDm("README.md");
+
+        readme.Should().Contain("not a Kubernetes application");
+        readme.Should().Contain("profile::pi::service::divoom");
+        readme.Should().Contain("no K8s surface");
+    }
+
+    [Fact]
+    public void DmHieraOverlay_PreservesExistingEdge2DivoomService()
+    {
+        var hiera = ReadDm("hiera/edge2-divoom-dm-device.overlay.yaml");
+
+        hiera.Should().Contain("fc-pimanager:");
+        hiera.Should().Contain("fc-divoom:");
+        hiera.Should().Contain("enabled: true");
+        hiera.Should().Contain("profile::pi::service::divoom_dm_device::service_enabled: false");
+        hiera.Should().Contain("profile::pi::service::divoom_dm_device::service_ensure: 'stopped'");
+    }
+
+    [Fact]
+    public void DmPuppetProfile_DefaultsToStoppedDisabledService()
+    {
+        var profile = ReadDm("puppet/profile/pi/service/divoom_dm_device.pp");
+
+        profile.Should().Contain("Boolean $service_enabled = false");
+        profile.Should().Contain("Enum['running', 'stopped'] $service_ensure = 'stopped'");
+        profile.Should().Contain("service { $service_name:");
+        profile.Should().Contain("ensure  => $service_ensure");
+        profile.Should().Contain("enable  => $service_enabled");
+    }
+
+    [Fact]
+    public void DmPuppetProfile_DoesNotManageLiveDivoomWebUnit()
+    {
+        var profile = ReadDm("puppet/profile/pi/service/divoom_dm_device.pp");
+
+        profile.Should().NotContain("Service['flowercore-divoom.service']");
+        profile.Should().NotContain("service { 'flowercore-divoom.service'");
+        profile.Should().NotContain("notify  => Service");
+    }
+
+    [Fact]
+    public void DmAgentUnit_IsSeparateAndGatedByExistingWrappers()
+    {
+        var unit = ReadDm("puppet/templates/flowercore-divoom-dm-agent.service.epp");
+
+        unit.Should().Contain("ConditionPathExists=<%= $divoom_install_dir %>/bt-link.sh");
+        unit.Should().Contain("ConditionPathExists=<%= $divoom_install_dir %>/bt-reset.sh");
+        unit.Should().Contain("ConditionPathExists=<%= $divoom_install_dir %>/audio-link.sh");
+        unit.Should().Contain("ExecStart=<%= $agent_binary_path %> --mode=Pi");
+        unit.Should().NotContain("flowercore-divoom.service");
+    }
+
+    [Fact]
+    public void DmRegistration_CarriesRenderProofAndSafetyPolicy()
+    {
+        var registration = ReadDm("puppet/templates/divoom-device-registration.json.epp");
+
+        registration.Should().Contain("\"candidateChannels\": <%= $bt_channels_json %>");
+        registration.Should().Contain("\"deviceInfoIsRenderProof\": false");
+        registration.Should().Contain("\"visibleRenderProofRequired\": <%= $visible_render_proof_required %>");
+        registration.Should().Contain("\"preserveExistingService\": \"flowercore-divoom.service\"");
+        registration.Should().Contain("\"doNotEnableFmRadio\": true");
+    }
+
+    [Fact]
+    public void TvService_UsesAvaloniaHdmiSafetyGates()
+    {
+        var unit = ReadTv("systemd/flowercore-divoom-tv.service");
+
+        unit.Should().Contain("ConditionPathExists=/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv");
+        unit.Should().Contain("Environment=XDG_RUNTIME_DIR=/run/fc-divoom-tv");
+        unit.Should().Contain("RuntimeDirectoryMode=0700");
+        unit.Should().Contain("ExecStartPre=/usr/local/bin/flowercore-divoom-tv-prelaunch.sh");
+        unit.Should().Contain("ExecStart=/usr/local/bin/flowercore-divoom-tv-launch.sh");
+        unit.Should().Contain("MemoryMax=2G");
+        unit.Should().Contain("PrivateTmp=true");
+        unit.Should().NotContain("/tmp");
+    }
+
+    [Fact]
+    public void TvLauncher_PrefersCageAndFallsBackToDirectLaunch()
+    {
+        var script = ReadTv("scripts/flowercore-divoom-tv-launch.sh");
+
+        script.Should().Contain("command -v cage");
+        script.Should().Contain("exec cage --");
+        script.Should().Contain("launching FlowerCore.Divoom.Tv directly");
+        script.Should().Contain("--target=hdmi");
+        script.Should().Contain("--presentation-mode=${PRESENTATION_MODE}");
+    }
+
+    [Fact]
+    public void TvHotplugRule_SettlesAndRestartsRenderer()
+    {
+        var rule = ReadTv("systemd/99-flowercore-divoom-tv-hdmi.rules");
+        var responder = ReadTv("scripts/flowercore-divoom-tv-hdmi-respond.sh");
+
+        rule.Should().Contain("KERNEL==\"card?-HDMI-A-?\"");
+        rule.Should().Contain("start flowercore-divoom-tv-hdmi.service");
+        responder.Should().Contain("sleep 2");
+        responder.Should().Contain("systemctl restart flowercore-divoom-tv.service");
+    }
+
+    [Fact]
+    public void TvPuppetProfile_InstallsCageAndStaticArtifacts()
+    {
+        var profile = ReadTv("puppet/profile/pi/service/divoom_tv.pp");
+
+        profile.Should().Contain("package { ['cage', 'libgbm1', 'libdrm2', 'libxkbcommon0', 'fonts-dejavu-core']");
+        profile.Should().Contain("'profile/pi/fc_divoom_tv/flowercore-divoom-tv.service'");
+        profile.Should().Contain("'profile/pi/fc_divoom_tv/flowercore-divoom-tv-launch.sh'");
+        profile.Should().Contain("profile/pi/fc_divoom_tv/99-flowercore-divoom-tv-hdmi.rules");
+        profile.Should().Contain("Boolean $service_enabled = false");
+    }
+
+    [Fact]
+    public void DivoomArtifacts_DoNotAddKubernetesWorkloads()
+    {
+        var allText = Directory.GetFiles(DmRoot, "*", SearchOption.AllDirectories)
+            .Concat(Directory.GetFiles(TvRoot, "*", SearchOption.AllDirectories))
+            .Select(File.ReadAllText);
+
+        foreach (var text in allText)
+        {
+            text.Should().NotContain("kind: Deployment");
+            text.Should().NotContain("kind: IngressRoute");
+            text.Should().NotContain("kind: Certificate");
+            text.Should().NotContain("kind: OnePasswordItem");
+        }
+    }
+
+    private static string ReadDm(string relativePath)
+        => File.ReadAllText(Path.Combine(DmRoot, relativePath.Replace('/', Path.DirectorySeparatorChar)));
+
+    private static string ReadTv(string relativePath)
+        => File.ReadAllText(Path.Combine(TvRoot, 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.");
+    }
+}