github-runner: add DM and WorldBuilder runners

apps/authentik/authentik.yaml

@@ -1,448 +0,0 @@
-# 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/brochure/README.md

@@ -0,0 +1,27 @@
+# FlowerCore Brochure
+
+`apps/brochure` hosts the public brochure split from `FlowerCore.Intranet.Web`.
+ArgoCD's `apps/*` ApplicationSet will create `infra-brochure` after this
+directory lands on `main`.
+
+## Runtime
+
+- Host: `https://brochure.flowercore.io`
+- Namespace: `brochure`
+- Deployment: `brochure-web`
+- Image: `localhost/fc-brochure-web:v20260524-sprint32`
+- Port: `8080`
+- Public route method allowlist: `GET` and `HEAD`
+
+## Operator Actions
+
+1. Publish and import `localhost/fc-brochure-web:v20260524-sprint32` to every
+   RKE2 node before sync, using the same podman save + `ctr images import`
+   flow as the Intranet deployment.
+2. Create the Cloudflare DNS record for `brochure.flowercore.io` pointing at
+   the FlowerCore public edge.
+3. Verify `infra-brochure` appears in ArgoCD, the certificate becomes Ready,
+   and `GET https://brochure.flowercore.io/` returns `200`.
+
+The route intentionally does not expose `/ops/*` or `/admin/*`; the Brochure
+web app returns `404` for those paths and Traefik only forwards read methods.

apps/brochure/brochure.yaml

@@ -0,0 +1,131 @@
+# FlowerCore Brochure public host
+#
+# Thin Blazor host for public What's New, walkthrough, and gallery content
+# carved out of FlowerCore.Intranet.Web. The ApplicationSet creates
+# infra-brochure from this directory after merge.
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: brochure
+  labels:
+    app.kubernetes.io/part-of: flowercore
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: brochure-web
+  namespace: brochure
+  labels:
+    app: brochure-web
+    app.kubernetes.io/name: brochure-web
+    app.kubernetes.io/part-of: flowercore
+spec:
+  replicas: 1
+  revisionHistoryLimit: 3
+  selector:
+    matchLabels:
+      app: brochure-web
+  template:
+    metadata:
+      labels:
+        app: brochure-web
+        app.kubernetes.io/name: brochure-web
+        app.kubernetes.io/part-of: flowercore
+    spec:
+      containers:
+        - name: brochure-web
+          image: localhost/fc-brochure-web:v20260524-sprint32
+          imagePullPolicy: Never
+          ports:
+            - containerPort: 8080
+              name: http
+          env:
+            - name: ASPNETCORE_ENVIRONMENT
+              value: Production
+            - name: ASPNETCORE_URLS
+              value: "http://+:8080"
+          resources:
+            requests:
+              cpu: "25m"
+              memory: "128Mi"
+            limits:
+              cpu: "500m"
+              memory: "512Mi"
+          readinessProbe:
+            httpGet:
+              path: /health
+              port: http
+            initialDelaySeconds: 10
+            periodSeconds: 10
+          livenessProbe:
+            httpGet:
+              path: /health
+              port: http
+            initialDelaySeconds: 30
+            periodSeconds: 30
+          securityContext:
+            runAsNonRoot: true
+            runAsUser: 1654
+            runAsGroup: 1654
+            allowPrivilegeEscalation: false
+            readOnlyRootFilesystem: true
+            capabilities:
+              drop:
+                - ALL
+          volumeMounts:
+            - name: tmp
+              mountPath: /tmp
+      volumes:
+        - name: tmp
+          emptyDir: {}
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: brochure-web
+  namespace: brochure
+  labels:
+    app: brochure-web
+    app.kubernetes.io/name: brochure-web
+    app.kubernetes.io/part-of: flowercore
+spec:
+  type: ClusterIP
+  selector:
+    app: brochure-web
+  ports:
+    - name: http
+      port: 8080
+      targetPort: http
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: brochure-web-tls
+  namespace: brochure
+spec:
+  secretName: brochure-web-tls
+  issuerRef:
+    name: step-ca-acme
+    kind: ClusterIssuer
+  dnsNames:
+    - brochure.flowercore.io
+  duration: 720h
+  renewBefore: 240h
+---
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: brochure-web-public
+  namespace: brochure
+spec:
+  entryPoints:
+    - websecure
+  routes:
+    - match: Host(`brochure.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
+      kind: Rule
+      services:
+        - name: brochure-web
+          port: 8080
+  tls:
+    secretName: brochure-web-tls

apps/fc-devicemgmt/argocd-application.yaml

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

apps/fc-devicemgmt/deployment-operator.yaml

@@ -47,7 +47,7 @@ spec:
         fsGroupChangePolicy: OnRootMismatch
       containers:
         - name: operator
-          image: localhost/fc-devicemgmt-operator:v20260519-sp34cl3-fix
+          image: localhost/fc-devicemgmt-operator:v20260512-cx5
           imagePullPolicy: Never
           ports:
             - name: metrics

apps/fc-devicemgmt/deployment-web.yaml

@@ -4,22 +4,6 @@
 # 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:
@@ -36,7 +20,7 @@ metadata:
   annotations:
     flowercore.io/traceability-standard: k8s-pod-ownership-and-traceability-standard
 spec:
-  replicas: 0
+  replicas: 2
   revisionHistoryLimit: 3
   selector:
     matchLabels:

apps/github-runner/.gitattributes

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

apps/github-runner/Dockerfile

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

apps/github-runner/README.md

@@ -7,17 +7,12 @@ Deployments with `kubectl`; update this manifest and let ArgoCD reconcile.
 
 All repo-scoped Linux runners use:
 
-- `localhost/fc-github-runner:v20260520-ruby3.3.11`, derived from
-  `myoung34/github-runner:latest`
 - `ACCESS_TOKEN` from the `github-runner-token` Secret
 - `RUN_AS_ROOT=false`
 - `EPHEMERAL=true`
 - `LABELS=self-hosted,linux,fc-build-linux`
 - writable non-root paths under `/home/runner` for .NET, NuGet, XDG cache, and
   Actions tool cache
-- Ruby 3.3.11 seeded into `/home/runner/_tool/Ruby/3.3/x64` from the baked
-  `/opt/runner-toolcache` copy so `ruby/setup-ruby@v1` can discover it on
-  self-hosted `ubuntu-20.04-x64` runners
 
 `github-runner` for `FlowerCore.Common` is single-replica because it retains the
 original Longhorn ReadWriteOnce NuGet PVC. Every other repo-scoped runner uses
@@ -33,33 +28,9 @@ Sprint 32 final long-tail wave adds 16 two-replica Deployments:
 `FlowerCore.Provisioning`, `FlowerCore.Redis`, `FlowerCore.MessageBoard`, and
 `FlowerCore.MenuBoard`.
 
-## Image Build
+Sprint 37 Cx-2 closes the audited Linux runner gaps for
-
+`FlowerCore.DeviceManagement` and `FlowerCore.WorldBuilder` with the same
-Ruby is baked with a pinned `ruby-build` release and Ruby patch version. The pod
+two-replica `emptyDir` pattern.
-still mounts an `emptyDir` over `/home/runner`, so the `setup-runner-home` init
-container copies the baked toolcache from `/opt/runner-toolcache/Ruby` into
-`/home/runner/_tool/Ruby` before the runner container starts.
-
-```bash
-cd apps/github-runner
-podman build -t localhost/fc-github-runner:v20260520-ruby3.3.11 .
-podman run --rm localhost/fc-github-runner:v20260520-ruby3.3.11 ruby -v
-podman run --rm localhost/fc-github-runner:v20260520-ruby3.3.11 \
-  test -f /opt/runner-toolcache/Ruby/3.3/x64.complete
-podman save localhost/fc-github-runner:v20260520-ruby3.3.11 \
-  -o fc-github-runner-v20260520-ruby3.3.11.tar
-```
-
-Import the saved image on every schedulable RKE2 node before ArgoCD rolls the
-Deployments:
-
-```bash
-for node in rke2-server rke2-agent1 rke2-agent2; do
-  scp fc-github-runner-v20260520-ruby3.3.11.tar "$node:/tmp/"
-  ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images rm localhost/fc-github-runner:v20260520-ruby3.3.11 || true'
-  ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images import /tmp/fc-github-runner-v20260520-ruby3.3.11.tar'
-done
-```
 
 ## Post-Merge Proof
 
@@ -69,14 +40,6 @@ After the PR is merged and ArgoCD syncs, verify the runner fleet:
 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
@@ -88,7 +51,7 @@ for repo in FlowerCore.Common FlowerCore.Shared.Pos FlowerCore.Puppet FlowerCore
             FlowerCore.Distribution FlowerCore.Scoreboard FlowerCore.SegmentDisplay \
             FlowerCore.Signage.Contracts FlowerCore.SignalControl FlowerCore.Intranet.Web \
             FlowerCore.Provisioning FlowerCore.Redis FlowerCore.MessageBoard \
-            FlowerCore.MenuBoard; do
+            FlowerCore.MenuBoard FlowerCore.DeviceManagement FlowerCore.WorldBuilder; do
   echo "=== $repo ==="
   gh api "/repos/astoltz/$repo/actions/runners" \
     --jq '.runners[] | select(.labels[].name == "fc-build-linux") | {name,status,busy,labels:[.labels[].name]}'
@@ -105,15 +68,25 @@ gh run list --repo astoltz/FlowerCore.Shared.Pos \
 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.
 
+## Sprint 37 Cx-2 Gap Audit
+
+The 2026-05-18 GitHub workflow scan found these remaining repos with
+`runs-on: [self-hosted, linux, fc-build-linux]` but no K8s runner Deployment:
+`FlowerCore.AiStation.Linux`, `FlowerCore.PHP`, `FlowerCore.PiManager`,
+`FlowerCore.Shared.Barcodes`, `FlowerCore.Shared.Lookup`,
+`FlowerCore.Shared.Nodes`, `FlowerCore.Shared.PrintClient`,
+`FlowerCore.Shared.Relay`, `FlowerCore.Shared.ShowRunner`, and
+`FlowerCore.Shared.Storage`.
+
+Mixed/platform repos also have Linux workflow legs but need owner review before
+adding Linux runner Deployments: `FlowerCore.Library.Mac`,
+`FlowerCore.Signage.Agent.AppleTv`, and `FlowerCore.Signage.Player.Wpf`.
+
 ## 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.

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

@@ -1,19 +0,0 @@
-#!/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/monitoring/noc-monitoring.yaml

@@ -280,14 +280,13 @@ 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/health"]
+          - targets: ["http://10.0.57.16:5200/"]
             labels:
               instance: "print-web"
               service: "print-web"
@@ -730,7 +729,7 @@ data:
             expr: |
               kube_deployment_status_replicas_ready{
                 namespace="github-runner",
-                deployment=~"github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"
+                deployment=~"github-runner(|-.+)"
               } == 0
             for: 5m
             labels:
@@ -1274,55 +1273,24 @@ metadata:
 data:
   notify.py: |
     #!/usr/bin/env python3
-    """HTTP->IRC alert relay with thermal-printer DIGEST forwarding.
+    """HTTP->IRC alert relay with thermal printer forwarding for Grafana webhooks.
-
+    Listens on :9119, posts to #alerts on UnrealIRCd via raw IRC protocol.
-    Listens on :9119, posts to #alerts on UnrealIRCd, forwards to Print.Web
+    Alerts tagged alert_channel=thermal_print also POST to Print.Web /api/print/alert.
-    /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, os, socket, sys, threading, time
+    import json, socket, sys, 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
 
-    THERMAL_PRINT_ENABLED = os.environ.get("THERMAL_PRINT_ENABLED", "true").lower() == "true"
+    IRC_HOST = "unrealircd.irc.svc"  # short name: CoreDNS ndots:5 + iamworkin.lan template hijacks full .cluster.local (see memory)
-    BATCH_INTERVAL_MIN    = int(os.environ.get("BATCH_INTERVAL_MIN", "60"))
+    IRC_PORT = 6667
-    BATCH_MAX_PENDING     = int(os.environ.get("BATCH_MAX_PENDING", "50"))
+    IRC_NICK = "grafana-bot"
-
+    IRC_CHANNEL = "#alerts"
-    IRC_HOST      = os.environ.get("IRC_HOST", "unrealircd.irc.svc")
+    PRINT_WEB_URL = "http://10.0.57.16:5200/api/print/alert"
-    IRC_PORT      = int(os.environ.get("IRC_PORT", "6667"))
+    PRINT_ENABLED = True
-    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())
@@ -1355,137 +1323,52 @@ 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 post_thermal(payload, kind):
+    def send_thermal_print(alert):
-        if not THERMAL_PRINT_ENABLED:
+        if not PRINT_ENABLED: return
-            print(f"[irc-notify] thermal disabled; skip {kind} ({payload.get('title','?')[:40]})", file=sys.stderr)
+        labels = alert.get("labels", {})
-            return False
+        annotations = alert.get("annotations", {})
+        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)
-            if kind == "immediate": _stats["print_immediate"] += 1
+            print(f"[irc-notify] Thermal print sent: {resp.read().decode()}", file=sys.stderr)
-            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 {kind} failed: {e}", file=sys.stderr)
+            print(f"[irc-notify] Thermal print failed: {e}", file=sys.stderr)
-            return False
 
-    def fingerprint_of(alert):
+    def should_print(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 ""
+        if labels.get("alert_channel") == "thermal_print": return True
-        return f"{labels.get('alertname','?')}/{labels.get('namespace','')}/{target}"
+        if labels.get("severity", "").lower() in ("critical", "disaster"): return True
-
+        if alert.get("status", "").upper() == "RESOLVED": return False
-    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", []):
@@ -1500,56 +1383,22 @@ data:
                 msg = f"{icon}{sev_tag} {name}: {summary}"
                 if desc: msg += f"\n  {desc}"
                 send_irc(msg)
-                # Thermal routing — EVERYTHING (including criticals) goes into
+                if should_print(alert): send_thermal_print(alert)
-                # the hourly digest. Only the explicit `alert_channel=thermal_print_immediate`
+            self.send_response(200)
-                # label bypasses, and even that flushes-the-current-digest rather
+            self.send_header("Content-Type", "application/json")
-                # than printing a standalone job, so the same fingerprint can't
+            self.end_headers()
-                # 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_header("Content-Type", "application/json"); self.end_headers()
+            self.send_response(200)
-            with _buffer_lock:
+            self.send_header("Content-Type", "application/json")
-                alertnames = sorted({it["alert"].get("labels", {}).get("alertname", "?") for it in _buffer.values()})
+            self.end_headers()
-                depth = len(_buffer)
+            self.wfile.write(json.dumps({"service":"irc-notify","thermal_print":PRINT_ENABLED}).encode())
-            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-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)
+        print(f"IRC alert relay :9119 -> {IRC_HOST}:{IRC_PORT} {IRC_CHANNEL} (thermal: {PRINT_ENABLED})")
         server.serve_forever()
 
 # =============================================================================
@@ -3660,7 +3509,7 @@ 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}
+                model: {expr: 'kube_deployment_status_replicas_ready{namespace="github-runner",deployment=~"github-runner(|-.+)"} == 0', instant: true, refId: A}
               - refId: B
                 relativeTimeRange: {from: 300, to: 0}
                 datasourceUid: __expr__

apps/selenium/network-policy.yaml

@@ -24,16 +24,7 @@
 #     (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
+#     telephony / gitea / fc-system / fc-signage namespaces on 4444.
-#     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:
@@ -212,13 +203,6 @@ spec:
     ports:
     - port: 4444
       protocol: TCP
-  - from:
-    - namespaceSelector:
-        matchLabels:
-          kubernetes.io/metadata.name: github-runner
-    ports:
-    - port: 4444
-      protocol: TCP
   podSelector: {}
   policyTypes:
   - Ingress

apps/selenium/selenium-grid.yaml

@@ -1,412 +0,0 @@
-# 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
-        resources:
-          limits:
-            cpu: 500m
-            memory: 1Gi
-          requests:
-            cpu: 250m
-            memory: 512Mi
----
-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
-        resources:
-          limits:
-            cpu: '1'
-            memory: 1Gi
-          requests:
-            cpu: 500m
-            memory: 512Mi
-        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
-        resources:
-          limits:
-            cpu: '1'
-            memory: 1Gi
-          requests:
-            cpu: 500m
-            memory: 512Mi
-        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

tests/bluejay-infra-lint/FleetManifestLintTests.cs

@@ -67,6 +67,8 @@ public sealed class FleetManifestLintTests
         ["github-runner-chat"] = "https://github.com/astoltz/FlowerCore.Chat",
         ["github-runner-mysql"] = "https://github.com/astoltz/FlowerCore.MySQL",
         ["github-runner-kiosk-linux"] = "https://github.com/astoltz/FlowerCore.Kiosk.Linux",
+        ["github-runner-devicemgmt"] = "https://github.com/astoltz/FlowerCore.DeviceManagement",
+        ["github-runner-worldbuilder"] = "https://github.com/astoltz/FlowerCore.WorldBuilder",
     };
 
     private static readonly HashSet<string> ScaledLinuxRunnerDeployments = new(StringComparer.Ordinal)
@@ -80,6 +82,8 @@ public sealed class FleetManifestLintTests
         "github-runner-chat",
         "github-runner-mysql",
         "github-runner-kiosk-linux",
+        "github-runner-devicemgmt",
+        "github-runner-worldbuilder",
     };
 
     private static readonly IReadOnlyDictionary<string, string> WritableRunnerEnv = new Dictionary<string, string>(StringComparer.Ordinal)
@@ -234,7 +238,7 @@ public sealed class FleetManifestLintTests
         {
             deployments.Should().ContainKey(expectedRunner.Key);
 
-            var container = deployments[expectedRunner.Key].ContainerMappings().Should().ContainSingle().Subject;
+            var container = RunnerContainer(deployments[expectedRunner.Key]);
             EnvValue(container, "REPO_URL").Should().Be(expectedRunner.Value);
             EnvValue(container, "EPHEMERAL").Should().Be("true");
             EnvValue(container, "LABELS").Should().Be("self-hosted,linux,fc-build-linux");
@@ -250,7 +254,7 @@ public sealed class FleetManifestLintTests
     {
         foreach (var deployment in GitHubRunnerDeployments().Values)
         {
-            var container = deployment.ContainerMappings().Should().ContainSingle().Subject;
+            var container = RunnerContainer(deployment);
 
             foreach (var expectedEnv in WritableRunnerEnv)
             {
@@ -311,7 +315,7 @@ public sealed class FleetManifestLintTests
         monitoring.Should().Contain("MacMiniRunnerOffline");
         monitoring.Should().Contain("LinuxRunnerOffline");
         monitoring.Should().Contain("kube_deployment_status_replicas_ready");
-        monitoring.Should().Contain("github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))");
+        monitoring.Should().Contain("github-runner(|-.+)");
         monitoring.Should().Contain("folder: CI Alerts");
         monitoring.Should().Contain("uid: linux-runner-offline");
         monitoring.Should().Contain("alert_channel: irc");
@@ -641,6 +645,15 @@ public sealed class FleetManifestLintTests
         return EnvMapping(container, name) is { } env ? ManifestNodeExtensions.Scalar(env, "value") : null;
     }
 
+    private static YamlMappingNode RunnerContainer(ManifestDocument deployment)
+    {
+        return deployment.ContainerMappings()
+            .Where(container => string.Equals(ManifestNodeExtensions.Scalar(container, "name"), "runner", StringComparison.Ordinal))
+            .Should()
+            .ContainSingle($"{deployment.Name} must keep exactly one main runner container")
+            .Subject;
+    }
+
     private static string? EnvSecretName(YamlMappingNode container, string name)
     {
         return EnvMapping(container, name) is { } env