docs(fc-build-windows): capture runner operator gate

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/fc-build-windows/README.md

@@ -0,0 +1,263 @@
+# fc-build-windows runner gate
+
+Status: OPEN-WITH-OPERATOR-ACTION as of 2026-05-20.
+
+This directory is intentionally not a live runner deployment. It records the
+exact gate for bringing up the Windows self-hosted runner fleet without faking
+capacity in GitHub or Kubernetes.
+
+## Lane evidence
+
+- `D:\git\FlowerCore\FlowerCore.Notes\docs\dashboards\decisions-waiting.html`
+  lines 15078-15085: Q-MR-82 says the Updater Windows Sandbox E2E run is
+  queued and `bluejay-ws-sandbox-1` is offline.
+- `D:\git\FlowerCore\FlowerCore.Notes\memory\project_morning_routine_8_2026_05_20.md`:
+  Morning Routine #8 carries Q-MR-82 as the fleet-wide Windows runner gap.
+- `D:\git\FlowerCore\FlowerCore.Notes\docs\standards\sprint-37-codex-dispatch-log-2026-05-19.md`
+  lines 76, 84-85, and 97: keep BLUEJAY-WS out of runner plans, merge Linux
+  runner expansion separately, and keep true Windows-only workflows parked on
+  the Windows runner host substrate path.
+- `D:\git\FlowerCore\FlowerCore.Notes\docs\ai-agents\codex-prompts\2026-05-20-xxxxl-sprint-42-orchestrator-briefs.md`
+  lane Cx-5: land a deployment only if a Windows runner image/substrate is
+  ready; otherwise commit an operator-action gate.
+- `D:\git\FlowerCore\FlowerCore.Notes\memory\feedback_bluejay_ws_never_a_github_runner.md`:
+  BLUEJAY-WS is operator-only territory; Windows runners belong on a dedicated
+  KubeVirt Windows VM such as `ci1` or a sibling VM.
+
+## Live probe summary
+
+Commands run on 2026-05-20 from `D:\git\FlowerCore\bluejay-infra`:
+
+```powershell
+$env:KUBECONFIG="$env:USERPROFILE\.kube\rke2.yaml"
+kubectl get nodes -o jsonpath='{range .items[*]}{.metadata.name}{"`t"}{.metadata.labels.kubernetes\.io/os}{"`n"}{end}'
+```
+
+Result: `rke2-agent1`, `rke2-agent2`, and `rke2-server` all report
+`kubernetes.io/os=linux`. There is no Windows Kubernetes node, so Windows
+containers on RKE2 cannot satisfy `fc-build-windows`.
+
+```powershell
+kubectl -n kubevirt-vms get vm,vmi,pods -o wide
+```
+
+Result: KubeVirt is healthy and `ci1` is `Running` / `Ready=True` on
+`rke2-agent1` with VMI IP `10.42.103.35`.
+
+```powershell
+virtctl --kubeconfig $env:USERPROFILE\.kube\rke2.yaml port-forward vm/ci1.kubevirt-vms 15985:5985
+```
+
+Result during port tests: `dial tcp 10.42.103.35:5985: connect: no route to
+host`. The same result was seen for RDP 3389 and SSH 22. The VM exists, but it
+is not remotely reachable for runner bootstrap from this lane.
+
+```powershell
+gh api /repos/astoltz/FlowerCore.Updater/actions/runners `
+  --jq '.runners[]? | {name,status,busy,labels:[.labels[].name]}'
+gh run list --repo astoltz/FlowerCore.Updater `
+  --workflow "Updater Windows Sandbox E2E" --limit 5
+```
+
+Result: GitHub has one Updater runner, `bluejay-ws-sandbox-1`, with
+`status=offline`; run `26150689447` is still `queued`.
+
+## Feasibility classification
+
+### Option A: Windows containers on RKE2
+
+Not feasible without operator-physical infrastructure work. Kubernetes Windows
+containers require a Windows node. The current cluster has Linux-only RKE2
+nodes.
+
+### Option B: KubeVirt Windows VM
+
+Partially present, not deployable from this lane.
+
+`apps/kubevirt-vms/ci1.yaml` already defines a Windows Server 2025 KubeVirt VM
+using `localhost/fc-win-server-2025:v1`, and the live VM is running. However:
+
+- the guest is not reachable over RDP, WinRM, or SSH through `virtctl
+  port-forward`;
+- the current root disk is a `containerDisk`, so runner installation inside the
+  running guest is not a durable fleet state unless the first-boot automation
+  re-registers on every boot or the VM is moved to a persistent PVC-backed
+  disk;
+- FC.Updater `Updater Windows Sandbox E2E` uses
+  `[self-hosted, windows, windows-sandbox]`, while `fc-build-windows` build jobs
+  use `[self-hosted, windows, fc-build-windows]`. Do not advertise
+  `windows-sandbox` until Windows Sandbox has been proven in the guest.
+
+### Option C: bluejay-ws-sandbox-1
+
+Operator-only emergency fallback. GitHub shows it registered but offline. The
+current memory says BLUEJAY-WS must not be a fleet runner host, so this lane
+does not start or re-register it. If the operator deliberately overrides the
+policy to drain an emergency queue, start the existing visible runner console
+from the BLUEJAY-WS desktop and treat that as temporary break-glass, not the
+permanent Q-MR-82 closure.
+
+## Operator action plan
+
+### 1. Pick the Windows host class
+
+Use `ci1` or a sibling Windows Server 2025 VM for WPF build/test jobs that need
+`fc-build-windows`.
+
+Use a Windows 11 Pro/Enterprise KubeVirt VM for Updater or WorldBuilder
+Windows Sandbox gates, unless Windows Sandbox support is explicitly proven on
+the selected guest. The workflow labels must match the real capability:
+
+- WPF build runner: `self-hosted,windows,fc-build-windows,ci1`
+- Sandbox runner: `self-hosted,windows,windows-sandbox,ci-sandbox1`
+
+### 2. Make the VM reachable and durable
+
+From BLUEJAY-WS:
+
+```powershell
+$env:KUBECONFIG="$env:USERPROFILE\.kube\rke2.yaml"
+kubectl -n kubevirt-vms get vm,vmi,pods -o wide
+virtctl --kubeconfig $env:KUBECONFIG vnc ci1 -n kubevirt-vms
+virtctl --kubeconfig $env:KUBECONFIG port-forward vm/ci1.kubevirt-vms 13389:3389
+virtctl --kubeconfig $env:KUBECONFIG port-forward vm/ci1.kubevirt-vms 15985:5985
+```
+
+Before runner registration, fix the current port-forward failure. The expected
+state is that RDP or WinRM accepts a connection through the control plane.
+
+For durability, either:
+
+- move the runner VM to a persistent PVC-backed root disk; or
+- keep `containerDisk` and bake first-boot runner registration into the sysprep
+  flow using a non-expiring credential lookup path.
+
+Do not install a runner by hand into a transient VM and call Q-MR-82 closed.
+
+### 3. Install runner prerequisites inside the VM
+
+Run in an elevated PowerShell session in the Windows runner guest:
+
+```powershell
+winget install Microsoft.DotNet.SDK.10 --silent
+winget install Microsoft.DotNet.DesktopRuntime.8 --silent
+winget install Microsoft.PowerShell --silent
+winget install Git.Git --silent
+winget install Microsoft.VisualStudio.2022.BuildTools --silent
+winget install Google.Chrome --silent
+```
+
+For a Sandbox-capable runner only:
+
+```powershell
+Enable-WindowsOptionalFeature -Online -FeatureName Containers-DisposableClientVM -All
+Restart-Computer -Force
+```
+
+After reboot:
+
+```powershell
+Get-CimInstance -ClassName Win32_OptionalFeature -Filter "Name='Containers-DisposableClientVM'"
+Test-Path C:\Windows\System32\WindowsSandbox.exe
+```
+
+### 4. Register repo-scoped GitHub runners
+
+The `astoltz` account uses repo-scoped runners. Generate a fresh one-hour
+registration token per repo immediately before `config.cmd`.
+
+From a trusted operator shell with `gh` authenticated:
+
+```powershell
+$repos = @(
+  "FlowerCore.Updater",
+  "FlowerCore.WorldBuilder",
+  "FlowerCore.DeviceManagement"
+)
+
+foreach ($repo in $repos) {
+  $token = gh api -X POST "/repos/astoltz/$repo/actions/runners/registration-token" --jq .token
+  $repoSlug = $repo.ToLowerInvariant().Replace("flowercore.", "").Replace(".", "-")
+  $runnerDir = "C:\fc-ghr\$repoSlug-fc-build-windows"
+
+  New-Item -ItemType Directory -Force -Path $runnerDir | Out-Null
+  Set-Location $runnerDir
+
+  if (-not (Test-Path ".\config.cmd")) {
+    Invoke-WebRequest `
+      -Uri "https://github.com/actions/runner/releases/download/v2.323.0/actions-runner-win-x64-2.323.0.zip" `
+      -OutFile "actions-runner.zip"
+    Add-Type -AssemblyName System.IO.Compression.FileSystem
+    [System.IO.Compression.ZipFile]::ExtractToDirectory((Resolve-Path actions-runner.zip), $runnerDir)
+  }
+
+  .\config.cmd `
+    --url "https://github.com/astoltz/$repo" `
+    --token $token `
+    --name "ci1-$repoSlug-fc-build-windows" `
+    --labels "self-hosted,windows,fc-build-windows,ci1" `
+    --work "_work" `
+    --unattended `
+    --replace
+
+  .\svc.ps1 install
+  .\svc.ps1 start
+}
+```
+
+For Updater Sandbox E2E, register only after the guest proves Sandbox support,
+and use `windows-sandbox` labels:
+
+```powershell
+$token = gh api -X POST "/repos/astoltz/FlowerCore.Updater/actions/runners/registration-token" --jq .token
+.\config.cmd `
+  --url "https://github.com/astoltz/FlowerCore.Updater" `
+  --token $token `
+  --name "ci-sandbox1-updater" `
+  --labels "self-hosted,windows,windows-sandbox,ci-sandbox1" `
+  --work "_work" `
+  --unattended `
+  --replace
+```
+
+Keep registration tokens out of Git and logs. The durable credential source for
+automation should be the existing 1Password item named `GitHub PAT (Runner
+Registration)`, used only to mint short-lived repo registration tokens.
+
+### 5. Verify GitHub and workflow pickup
+
+```powershell
+gh api /repos/astoltz/FlowerCore.Updater/actions/runners `
+  --jq '.runners[] | select(.labels[].name == "windows-sandbox") | {name,status,busy,labels:[.labels[].name]}'
+
+gh api /repos/astoltz/FlowerCore.DeviceManagement/actions/runners `
+  --jq '.runners[] | select(.labels[].name == "fc-build-windows") | {name,status,busy,labels:[.labels[].name]}'
+
+gh run list --repo astoltz/FlowerCore.Updater `
+  --workflow "Updater Windows Sandbox E2E" --limit 3
+```
+
+Q-MR-82 can be marked resolved only after the Updater run moves from `queued` to
+`in_progress` or `completed` on an online runner, or after the affected WPF
+build repos show online `fc-build-windows` repo-scoped runners and their queued
+jobs start.
+
+## Break-glass BLUEJAY-WS command
+
+Only if the operator explicitly overrides the "BLUEJAY-WS is not a runner"
+policy to drain a queue:
+
+```powershell
+Set-Location C:\fc-ghr\updater-sandbox
+.\run.cmd
+```
+
+If a Windows service exists:
+
+```powershell
+Get-Service 'actions.runner.*'
+Start-Service 'actions.runner.*'
+```
+
+This does not close Q-MR-82 permanently. It is a temporary queue drain until a
+dedicated VM runner is online.

apps/fc-build-windows/kustomization.yaml

@@ -0,0 +1,4 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - operator-gate-configmap.yaml

apps/fc-build-windows/operator-gate-configmap.yaml

@@ -0,0 +1,61 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: fc-build-windows-operator-gate
+  namespace: kubevirt-vms
+  labels:
+    app.kubernetes.io/name: fc-build-windows
+    app.kubernetes.io/component: operator-gate
+    app.kubernetes.io/part-of: github-runner
+    flowercore.io/q-card: Q-MR-82
+  annotations:
+    flowercore.io/outcome: OPEN-WITH-OPERATOR-ACTION
+    flowercore.io/live-runner: "false"
+data:
+  outcome: OPEN-WITH-OPERATOR-ACTION
+  gate.md: |
+    Do not treat this ConfigMap as runner capacity.
+
+    Current probe, 2026-05-20:
+    - RKE2 nodes are linux-only; Windows containers require a Windows node.
+    - KubeVirt `ci1` is Running/Ready, but RDP 3389, WinRM 5985, and SSH 22
+      through `virtctl port-forward` return `connect: no route to host`.
+    - GitHub Updater runner list has only `bluejay-ws-sandbox-1`, status
+      offline. Updater Windows Sandbox E2E run 26150689447 remains queued.
+
+    Required operator action:
+    1. Make a dedicated Windows VM reachable and durable.
+    2. Install .NET 10 SDK, .NET 8 Desktop Runtime, Git, VS Build Tools, and
+       PowerShell 7.
+    3. Register repo-scoped runners with short-lived GitHub registration tokens.
+    4. Add `fc-build-windows` labels only to WPF build-capable guests.
+    5. Add `windows-sandbox` labels only after Sandbox support is proven.
+  registration-token-pattern.ps1: |
+    $repo = "FlowerCore.Updater"
+    $token = gh api -X POST "/repos/astoltz/$repo/actions/runners/registration-token" --jq .token
+    $runnerDir = "C:\fc-ghr\updater-fc-build-windows"
+
+    New-Item -ItemType Directory -Force -Path $runnerDir | Out-Null
+    Set-Location $runnerDir
+
+    # Install the Actions runner package here if config.cmd is absent.
+    .\config.cmd `
+      --url "https://github.com/astoltz/$repo" `
+      --token $token `
+      --name "ci1-updater-fc-build-windows" `
+      --labels "self-hosted,windows,fc-build-windows,ci1" `
+      --work "_work" `
+      --unattended `
+      --replace
+
+    .\svc.ps1 install
+    .\svc.ps1 start
+  verification.ps1: |
+    gh api /repos/astoltz/FlowerCore.Updater/actions/runners `
+      --jq '.runners[] | {name,status,busy,labels:[.labels[].name]}'
+
+    gh run list --repo astoltz/FlowerCore.Updater `
+      --workflow "Updater Windows Sandbox E2E" --limit 3
+
+    $env:KUBECONFIG="$env:USERPROFILE\.kube\rke2.yaml"
+    kubectl -n kubevirt-vms get vm,vmi,pods -o wide

apps/github-runner/.gitattributes

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

apps/github-runner/Dockerfile

@@ -1,54 +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:${PATH}"
-
-USER root
-
-# Bake the IAmWorkin step-ca root CA into the system trust store. Without
-# this, .NET HttpClient calls from CI tests against *.iamworkin.lan
-# (e.g. https://selenium.iamworkin.lan/session) fail with `PartialChain`
-# because the runner image's default Ubuntu trust bundle doesn't include
-# our internal Root CA. update-ca-certificates regenerates
-# /etc/ssl/certs/ca-certificates.crt, which OpenSSL + .NET on Linux read
-# automatically — no SSL_CERT_FILE env var needed.
-COPY step-ca-root.crt /usr/local/share/ca-certificates/iamworkin-step-ca-root.crt
-
-RUN apt-get update \
-    && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
-        autoconf \
-        bison \
-        build-essential \
-        ca-certificates \
-        curl \
-        libdb-dev \
-        libffi-dev \
-        libgdbm-dev \
-        libgmp-dev \
-        libncurses-dev \
-        libreadline-dev \
-        libssl-dev \
-        libyaml-dev \
-        patch \
-        pkg-config \
-        uuid-dev \
-        zlib1g-dev \
-    && update-ca-certificates \
-    && curl -fsSL "https://github.com/rbenv/ruby-build/archive/refs/tags/${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

@@ -7,17 +7,12 @@ Deployments with `kubectl`; update this manifest and let ArgoCD reconcile.
 
 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
@@ -33,46 +28,6 @@ Sprint 32 final long-tail wave adds 16 two-replica Deployments:
 `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:
@@ -81,14 +36,6 @@ 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
@@ -122,10 +69,6 @@ from GitHub Actions and verify it lands on an `rke2-linux-*` runner.
 - `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/github-runner/step-ca-root.crt

@@ -1,12 +0,0 @@
------BEGIN CERTIFICATE-----
-MIIBxDCCAWqgAwIBAgIRAPY357G6ow6zMAL5+4bS2kkwCgYIKoZIzj0EAwIwQDEa
-MBgGA1UEChMRSUFtV29ya2luIEFDTUUgQ0ExIjAgBgNVBAMTGUlBbVdvcmtpbiBB
-Q01FIENBIFJvb3QgQ0EwHhcNMjYwMzA4MTgwNzExWhcNMzYwMzA1MTgwNzExWjBA
-MRowGAYDVQQKExFJQW1Xb3JraW4gQUNNRSBDQTEiMCAGA1UEAxMZSUFtV29ya2lu
-IEFDTUUgQ0EgUm9vdCBDQTBZMBMGByqGSM49AgEGCCqGSM49AwEHA0IABJ2n04X1
-JZo5Zdq/i1Idv8+fqwZyAzBh7whbqj0SWsJL8UWRabCMqYCs7+dXO0xRSzqkwFDL
-x+vooOai8RgRNhajRTBDMA4GA1UdDwEB/wQEAwIBBjASBgNVHRMBAf8ECDAGAQH/
-AgEBMB0GA1UdDgQWBBRnuPPQR6iM/H6vOluiU3Sygayz8jAKBggqhkjOPQQDAgNI
-ADBFAiEArQK9dYPGmAZsdYnjziuFVVE5NKZUcceYvGfGC+tLXUsCIAudF2zJrCRq
-3mK50ZZET/fwTkJwiEF4824mjP8p1CKM
------END CERTIFICATE-----

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"

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

@@ -1,427 +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
-        # 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

tests/bluejay-infra-lint/FleetManifestLintTests.cs

@@ -67,7 +67,6 @@ 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-updater"] = "https://github.com/astoltz/FlowerCore.Updater",
     };
 
     private static readonly HashSet<string> ScaledLinuxRunnerDeployments = new(StringComparer.Ordinal)
@@ -81,7 +80,6 @@ public sealed class FleetManifestLintTests
         "github-runner-chat",
         "github-runner-mysql",
         "github-runner-kiosk-linux",
-        "github-runner-updater",
     };
 
     private static readonly IReadOnlyDictionary<string, string> WritableRunnerEnv = new Dictionary<string, string>(StringComparer.Ordinal)
@@ -236,7 +234,7 @@ public sealed class FleetManifestLintTests
         {
             deployments.Should().ContainKey(expectedRunner.Key);
 
-            var container = deployments[expectedRunner.Key].MainContainerMappings().Should().ContainSingle().Subject;
+            var container = deployments[expectedRunner.Key].ContainerMappings().Should().ContainSingle().Subject;
             EnvValue(container, "REPO_URL").Should().Be(expectedRunner.Value);
             EnvValue(container, "EPHEMERAL").Should().Be("true");
             EnvValue(container, "LABELS").Should().Be("self-hosted,linux,fc-build-linux");
@@ -252,7 +250,7 @@ public sealed class FleetManifestLintTests
     {
         foreach (var deployment in GitHubRunnerDeployments().Values)
         {
-            var container = deployment.MainContainerMappings().Should().ContainSingle().Subject;
+            var container = deployment.ContainerMappings().Should().ContainSingle().Subject;
 
             foreach (var expectedEnv in WritableRunnerEnv)
             {
@@ -279,10 +277,7 @@ public sealed class FleetManifestLintTests
         foreach (var deploymentName in ScaledLinuxRunnerDeployments)
         {
             var deployment = deployments[deploymentName];
-            // Scaled runners must have >= 2 replicas (avoid single-pod bottleneck).
+            ReplicaCount(deployment).Should().Be(2);
-            // Individual deployments may be tuned upward per CI activity — see
-            // "runners: right-size replica counts per 14d CI activity (#24)".
-            ReplicaCount(deployment).Should().BeGreaterOrEqualTo(2, $"{deploymentName} is in the scaled set and must run with at least 2 replicas");
 
             var volumes = deployment.MappingSequence("spec", "template", "spec", "volumes");
             var claimNames = volumes
@@ -308,108 +303,6 @@ public sealed class FleetManifestLintTests
             .Be("github-runner-nuget-cache");
     }
 
-    [Fact]
-    public void Runners_MustNotPinToOperatorWorkstationHosts()
-    {
-        // CRITICAL SAFETY (operator directive 2026-05-26): BLUEJAY-WS is the
-        // operator's primary workstation — host of the 1Password Connect
-        // bearer token, fcadmin SSH keys to noc1, signing CA private keys,
-        // and source for every FC repo. A self-hosted GitHub Actions runner
-        // there would execute arbitrary PR code with that local access.
-        // Build-side analog of the Sprint 9 NEW safe-account exclusion gate
-        // (Puppet GPO/AppLocker/WDAC/audit-forwarder modules refuse to apply
-        // on BLUEJAY-WS). This lint asserts no GitHub-runner Deployment in
-        // apps/github-runner/ pins to a forbidden operator-workstation host
-        // via nodeName, nodeSelector, nodeAffinity, or tolerations.
-        // Existing legacy `bluejay-ws-sandbox-1` GitHub-registered runner is
-        // out of scope here (it's a runtime registration, not a K8s
-        // Deployment) — see CLAUDE.md "Common Mistakes" entry and
-        // feedback_bluejay_ws_never_public_runner.md.
-        var forbiddenHostPatterns = new[]
-        {
-            "bluejay-ws",
-            "BLUEJAY-WS",
-            "bluejay-ws.iamworkin.lan",
-            "iamworkin-ws",
-        };
-
-        bool ContainsForbidden(string? value) =>
-            !string.IsNullOrWhiteSpace(value)
-            && forbiddenHostPatterns.Any(pattern => value!.Contains(pattern, StringComparison.OrdinalIgnoreCase));
-
-        var violations = GitHubRunnerDeployments().Values.SelectMany(deployment =>
-        {
-            var local = new List<string>();
-            var podSpec = ManifestNodeExtensions.Mapping(deployment.Root, "spec", "template", "spec");
-            if (podSpec is null)
-            {
-                return local;
-            }
-
-            // nodeName: pins the pod to a specific node by name.
-            var nodeName = ManifestNodeExtensions.Scalar(podSpec, "nodeName");
-            if (ContainsForbidden(nodeName))
-            {
-                local.Add($"{deployment.Name} sets nodeName='{nodeName}' which targets a forbidden operator-workstation host.");
-            }
-
-            // nodeSelector: dict of label → value pinning the pod to nodes
-            // carrying matching labels. Examples that would trip this:
-            //   kubernetes.io/hostname: bluejay-ws
-            //   flowercore.io/host: bluejay-ws.iamworkin.lan
-            var nodeSelector = ManifestNodeExtensions.Mapping(podSpec, "nodeSelector");
-            if (nodeSelector is not null)
-            {
-                foreach (var entry in nodeSelector.Children)
-                {
-                    var key = entry.Key is YamlScalarNode keyScalar ? keyScalar.Value : null;
-                    var value = entry.Value is YamlScalarNode valueScalar ? valueScalar.Value : null;
-                    if (ContainsForbidden(value))
-                    {
-                        local.Add($"{deployment.Name} has nodeSelector entry '{key}: {value}' which targets a forbidden operator-workstation host.");
-                    }
-                }
-            }
-
-            // nodeAffinity: matchExpressions over node labels.
-            foreach (var term in ManifestNodeExtensions.MappingSequence(podSpec, "affinity", "nodeAffinity", "requiredDuringSchedulingIgnoredDuringExecution", "nodeSelectorTerms"))
-            {
-                foreach (var expr in ManifestNodeExtensions.MappingSequence(term, "matchExpressions"))
-                {
-                    var key = ManifestNodeExtensions.Scalar(expr, "key");
-                    foreach (var valueNode in ManifestNodeExtensions.ScalarSequence(expr, "values"))
-                    {
-                        if (ContainsForbidden(valueNode))
-                        {
-                            local.Add($"{deployment.Name} has nodeAffinity matchExpression '{key}' value '{valueNode}' which targets a forbidden operator-workstation host.");
-                        }
-                    }
-                }
-            }
-
-            // tolerations: scheduling onto a tainted operator-workstation
-            // node would let the runner run there. Forbid any toleration
-            // value that names the workstation.
-            foreach (var toleration in ManifestNodeExtensions.MappingSequence(podSpec, "tolerations"))
-            {
-                var key = ManifestNodeExtensions.Scalar(toleration, "key");
-                var value = ManifestNodeExtensions.Scalar(toleration, "value");
-                if (ContainsForbidden(key))
-                {
-                    local.Add($"{deployment.Name} has toleration key '{key}' which targets a forbidden operator-workstation host.");
-                }
-                if (ContainsForbidden(value))
-                {
-                    local.Add($"{deployment.Name} has toleration value '{value}' which targets a forbidden operator-workstation host.");
-                }
-            }
-
-            return local;
-        }).ToList();
-
-        violations.Should().BeEmpty("BLUEJAY-WS / iamworkin-ws must never host a fleet GitHub Actions runner; see CLAUDE.md 'Registering BLUEJAY-WS as a fleet GitHub Actions runner' and feedback_bluejay_ws_never_public_runner.md");
-    }
-
     [Fact]
     public void Monitoring_MustAlertWhenLinuxRunnerDeploymentIsUnavailable()
     {
@@ -997,22 +890,6 @@ internal sealed record ManifestDocument(
             .ToList();
     }
 
-    // MainContainerMappings excludes initContainers. Use this when asserting
-    // properties of the primary container (env, image, volumeMounts) where an
-    // initContainer would be a false-positive match — e.g. the GitHub runner
-    // image's `setup-runner-home` initContainer should not count toward the
-    // single-container assertions on the runner deployments.
-    public IReadOnlyList<YamlMappingNode> MainContainerMappings()
-    {
-        var podSpec = PodSpec();
-        if (podSpec is null)
-        {
-            return Array.Empty<YamlMappingNode>();
-        }
-
-        return ManifestNodeExtensions.MappingSequence(podSpec, "containers").ToList();
-    }
-
     public IReadOnlyList<ContainerSpec> ContainerSpecs()
     {
         return ContainerMappings()