feat: add qt sdk remotedesktop warm pool

Removes the apps/brochure/ directory entirely from the bluejay-infra
ApplicationSet glob. ArgoCD will:

  1. See infra-brochure has no git source -> mark for delete
  2. Prune the brochure namespace + Deployment + Service + Certificate
     + Secret + IngressRoute (all generated from the now-gone
     apps/brochure/brochure.yaml)
  3. Remove the infra-brochure Application from argocd ns

Operator decision 2026-05-19 (follow-up to 09387f9 ARCHIVED banner
commit): "Yes, prune argo for brochure. Probably fully deleted there."

The brochure subdomain project was a planning-chain misinterpretation
of "make TtsReader + AI Station production-ready" — see
memory/project_brochure_split_misinterpretation_archived_2026_05_19.md
in FlowerCore.Notes for the full decision record.

Reusable artifacts that were the operator's archive concern stay alive
in their actual homes:

- FlowerCore.Intranet.Web PR #8 content-NuGet carve-out: still in
  Intranet's master, may transfer to TtsReader / AI Station prod work
- Sprint 32 Cl-5 substrate (public-twin design ideas): SUPERSEDED banner
  in-place in FlowerCore.Notes docs/standards/, history preserved
- magpie-doc-writer + wren-walkthrough skill output: unchanged in
  Intranet's flowercore-whats-new/walkthroughs/galleries directories

Companion Notes-side commit updates the "scaled to 0 + ARCHIVED banner"
language in mvp-readiness.html + fleet-roadmap-2026-05-19-sprint36-v2.md
+ memory record to reflect full deletion instead.

Wrong-codebase image localhost/fc-brochure-web:v20260524-sprint32 is
being removed from rke2-server / rke2-agent1 / rke2-agent2 in a
follow-up step (reclaims ~800MB per node).

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

.gitattributes

@@ -0,0 +1,2 @@
+*.yaml text eol=lf
+*.yml text eol=lf

README.md

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

apps/fc-chat/fc-chat.yaml

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

apps/fc-desktop/remotedesktop-pools.yaml

@@ -0,0 +1,30 @@
+# FlowerCore RemoteDesktop warm-pool posture.
+#
+# The RemoteDesktop Web and Operator Deployments remain owned by
+# FlowerCore.RemoteDesktop. bluejay-infra owns these GitOps pool intents so
+# rebuilds preserve the operational posture without baking it into service code.
+---
+apiVersion: flowercore.io/v1
+kind: RemoteDesktopPoolCrd
+metadata:
+  name: qt-sdk-pool
+  namespace: fc-desktop
+  labels:
+    app.kubernetes.io/name: remotedesktop-pool
+    app.kubernetes.io/component: warm-pool
+    app.kubernetes.io/part-of: flowercore-remotedesktop
+    flowercore.io/template: dev-workstation
+    flowercore.io/image: localhost-fc-desktop-qt-sdk
+  annotations:
+    flowercore.io/deficit-tolerance: "0"
+    flowercore.io/scale-mode: ManualScaleOnDemand
+    flowercore.io/image-ref: localhost/fc-desktop:qt-sdk
+    flowercore.io/image-pull-policy: Never
+spec:
+  templateSlug: dev-workstation
+  desiredSize: 0
+  enabled: false
+  userVolumeMode: LateAttach
+  deficitTolerance: 0
+  scaleMode: ManualScaleOnDemand
+  reconcileNow: false

apps/fc-devicemgmt/deployment-operator.yaml

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

apps/fc-devicemgmt/deployment-web.yaml

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

apps/fc-ttsreader/fc-ttsreader.yaml

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

apps/github-runner/README.md

@@ -0,0 +1,76 @@
+# GitHub Runner Fleet
+
+ArgoCD owns `apps/github-runner/github-runner.yaml`. Do not patch live runner
+Deployments with `kubectl`; update this manifest and let ArgoCD reconcile.
+
+## Runner Shape
+
+All repo-scoped Linux runners use:
+
+- `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
+
+`github-runner` for `FlowerCore.Common` is single-replica because it retains the
+original Longhorn ReadWriteOnce NuGet PVC. Every other repo-scoped runner uses
+two replicas with per-pod `emptyDir` caches. That is the safe backlog-drain
+strategy: no two pods share one RWO PVC.
+
+Sprint 32 final long-tail wave adds 16 two-replica Deployments:
+`FlowerCore.Knowledge`, `FlowerCore.LlmBridge`, `FlowerCore.Media`,
+`FlowerCore.Presentations`, `FlowerCore.RemoteDesktop`, `FlowerCore.DNS`,
+`FlowerCore.Distribution`, `FlowerCore.Scoreboard`,
+`FlowerCore.SegmentDisplay`, `FlowerCore.Signage.Contracts`,
+`FlowerCore.SignalControl`, `FlowerCore.Intranet.Web`,
+`FlowerCore.Provisioning`, `FlowerCore.Redis`, `FlowerCore.MessageBoard`, and
+`FlowerCore.MenuBoard`.
+
+## Post-Merge Proof
+
+After the PR is merged and ArgoCD syncs, verify the runner fleet:
+
+```bash
+kubectl -n github-runner get deploy,pods,pvc
+```
+
+Verify GitHub registration for the repo-scoped runners:
+
+```bash
+for repo in FlowerCore.Common FlowerCore.Shared.Pos FlowerCore.Puppet FlowerCore.Signage \
+            FlowerCore.DMS FlowerCore.Telephony FlowerCore.Print.Web FlowerCore.Chat \
+            FlowerCore.MySQL FlowerCore.Kiosk.Linux FlowerCore.Marquee FlowerCore.TtsReader \
+            FlowerCore.Knowledge FlowerCore.LlmBridge FlowerCore.Media \
+            FlowerCore.Presentations FlowerCore.RemoteDesktop FlowerCore.DNS \
+            FlowerCore.Distribution FlowerCore.Scoreboard FlowerCore.SegmentDisplay \
+            FlowerCore.Signage.Contracts FlowerCore.SignalControl FlowerCore.Intranet.Web \
+            FlowerCore.Provisioning FlowerCore.Redis FlowerCore.MessageBoard \
+            FlowerCore.MenuBoard; do
+  echo "=== $repo ==="
+  gh api "/repos/astoltz/$repo/actions/runners" \
+    --jq '.runners[] | select(.labels[].name == "fc-build-linux") | {name,status,busy,labels:[.labels[].name]}'
+done
+```
+
+Shared.Pos publish proof after the runner pod is online:
+
+```bash
+gh run list --repo astoltz/FlowerCore.Shared.Pos \
+  --workflow "Build, Test & Publish" --branch main --limit 5
+```
+
+If the latest run is still queued after runner registration, rerun the workflow
+from GitHub Actions and verify it lands on an `rke2-linux-*` runner.
+
+## Failure Notes
+
+- `actions/setup-dotnet` permission error at `/usr/share/dotnet`: check that
+  `DOTNET_INSTALL_DIR=/home/runner/.dotnet` and related cache env vars are
+  present on the runner pod.
+- `404` during runner registration: the fine-grained PAT is valid but missing
+  repository access for that repo. Add the repo to the PAT access list; the PAT
+  value does not change.
+- `Multi-Attach` volume error: only the Common runner uses a RWO PVC and it must
+  stay single-replica. New multi-replica runners use `emptyDir`.

apps/monitoring/noc-monitoring.yaml

@@ -723,6 +723,24 @@ data:
               summary: "Mac mini GitHub runner offline ({{ $labels.runner }})"
               description: "A macmini-* GitHub Actions runner has not reported online for more than 10 minutes. Puppet manages its LaunchDaemon under /Library/LaunchDaemons/io.flowercore.github-runner-<slug>.plist; runners survive reboot and do not require a GUI session."
 
+      - name: linux-runners
+        rules:
+          - alert: LinuxRunnerOffline
+            expr: |
+              kube_deployment_status_replicas_ready{
+                namespace="github-runner",
+                deployment=~"github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"
+              } == 0
+            for: 5m
+            labels:
+              severity: warning
+              alert_channel: irc
+              service: github-runner
+              team: ci
+            annotations:
+              summary: "Linux CI runner offline: {{ $labels.deployment }}"
+              description: "Deployment {{ $labels.deployment }} in namespace github-runner has 0 ready replicas for more than 5 minutes. CI jobs targeting this repo will queue until the runner pod restarts and re-registers with GitHub. Check pods with: kubectl -n github-runner get pods -l app.kubernetes.io/name={{ $labels.deployment }}. Check logs with: kubectl -n github-runner logs -l app.kubernetes.io/name={{ $labels.deployment }} --tail=50. Common causes: PAT missing repo access, runner CrashLoopBackOff, or node/resource pressure."
+
       - name: remote-desktop
         rules:
           - alert: RemoteDesktopWebDown
@@ -948,6 +966,52 @@ data:
             annotations:
               summary: "Disk usage high on {{ $labels.instance }} ({{ $value | printf \"%.1f\" }}%)"
 
+      # Puppet agent + service alerts.
+      # Mirror of FlowerCore.Notes/scripts/monitoring/alerts.yml `puppet` group
+      # so a future migration to in-cluster Prometheus inherits the ruleset.
+      # Source-of-truth for the live Podman Prometheus on noc1 is the Notes file.
+      # See feedback_monitoring_k8s_target_vs_live_podman.
+      - name: puppet
+        rules:
+          - alert: PuppetAgentReportStale
+            expr: puppet_last_run_age_seconds > 7200
+            for: 30m
+            labels:
+              severity: warning
+              alert_channel: irc
+            annotations:
+              summary: "Puppet agent {{ $labels.instance }} hasn't reported in over 2h"
+              description: "Last run age: {{ $value | humanizeDuration }}. The puppet agent on {{ $labels.instance }} may be stopped, the node may be powered off, or noc1 may be unreachable from this node."
+              runbook: "1. SSH to node (via noc1 jumpbox if needed) 2. sudo systemctl status puppet 3. sudo puppet agent -t --noop to force a run 4. Check r10k: ssh fcadmin@10.0.56.10 'sudo podman logs openvoxserver --tail 50' 5. Verify noc1 reachability: ping puppet.iamworkin.lan"
+
+          - alert: PuppetAgentReportCritical
+            expr: puppet_last_run_age_seconds > 86400
+            for: 1h
+            labels:
+              severity: critical
+              alert_channel: irc
+            annotations:
+              summary: "Puppet agent {{ $labels.instance }} silent for over 24h — node is unmanaged"
+              description: "Last run age: {{ $value | humanizeDuration }}. Node {{ $labels.instance }} has not submitted a Puppet report in over 24 hours. Config drift is accumulating — investigate immediately. If intentional (maintenance), add to the exclusion filter or silence in Grafana."
+              runbook: "URGENT: 1. Check node power state 2. SSH via noc1 jumpbox: ssh fcadmin@10.0.56.10 then ssh <node> 3. sudo systemctl status puppet 4. sudo systemctl start puppet + sudo puppet agent -t 5. Check for network partitions (VLAN connectivity to 10.0.56.10) 6. If node was recently reimaged: sudo puppet agent -t to re-register with new SSL cert"
+
+          # Sprint 33 Cx-7 Phase B (2026-05-25 postmortem follow-up):
+          # Detects puppet.service in failed state — distinct from PuppetAgentReportStale
+          # which catches "agent hasn't run." This catches "systemd gave up restarting it"
+          # (CA-verify loop or other fatal exit). Requires node-exporter systemd collector
+          # enabled with --collector.systemd. If `node_systemd_unit_state` has no series
+          # for a node, the collector is disabled there — flag in postmortem follow-up.
+          - alert: PuppetServiceFailed
+            expr: node_systemd_unit_state{name="puppet.service",state="failed"} == 1
+            for: 5m
+            labels:
+              severity: warning
+              alert_channel: irc
+            annotations:
+              summary: "Puppet service failed on {{ $labels.instance }}"
+              description: "puppet.service on {{ $labels.instance }} has been in failed state for 5+ minutes. systemd has stopped auto-restarting (CA-verify-loop or other exit). Manual `systemctl status puppet` confirms. Run `sudo systemctl start puppet` to recover; investigate journal for root cause."
+              runbook_url: "https://github.com/astoltz/FlowerCore.Notes/blob/master/memory/feedback_puppet_service_dead_after_ca_loop_alert_misreads.md"
+
       # K8s pod-state alerts. Require kube-state-metrics scrape (added
       # 2026-04-26 — see scrape_configs above). Would have surfaced the
       # agent-zero ollama-proxy 172x crash-loop instead of letting it
@@ -1209,24 +1273,55 @@ metadata:
 data:
   notify.py: |
     #!/usr/bin/env python3
-    """HTTP->IRC alert relay with thermal printer forwarding for Grafana webhooks.
+    """HTTP->IRC alert relay with thermal-printer DIGEST forwarding.
-    Listens on :9119, posts to #alerts on UnrealIRCd via raw IRC protocol.
+
-    Alerts tagged alert_channel=thermal_print also POST to Print.Web /api/print/alert.
+    Listens on :9119, posts to #alerts on UnrealIRCd, forwards to Print.Web
+    /api/print/alert. Thermal printing is BATCHED into hourly digests by
+    default so the printer no longer spam-fires per Grafana webhook.
+
+    Routing (per Grafana webhook alert):
+      - IRC: always per-event (operator likes the stream)
+      - Thermal printer:
+          * severity in {critical,disaster,page} OR
+            label alert_channel=thermal_print_immediate -> print NOW
+          * label alert_channel=thermal_print -> enqueue into hourly digest
+          * everything else -> IRC only
+      - RESOLVED webhooks remove the alert from the digest buffer
+
+    Env vars (defaults preserve old behavior on first deploy):
+      THERMAL_PRINT_ENABLED  default "true"   - master kill switch
+      BATCH_INTERVAL_MIN     default "60"     - minutes between digest prints
+      BATCH_MAX_PENDING      default "50"     - force-flush threshold
+
+    HTTP surface:
+      POST /         - Grafana webhook entry
+      POST /flush    - manual digest flush (idempotent)
+      GET  /         - status + config + buffer depth + stats
     """
-    import json, socket, sys, time
+    import json, os, socket, sys, threading, time
+    from collections import defaultdict
+    from datetime import datetime, timezone
     from http.server import HTTPServer, BaseHTTPRequestHandler
     from urllib.request import Request, urlopen
-    from urllib.error import URLError
 
-    IRC_HOST = "unrealircd.irc.svc"  # short name: CoreDNS ndots:5 + iamworkin.lan template hijacks full .cluster.local (see memory)
+    THERMAL_PRINT_ENABLED = os.environ.get("THERMAL_PRINT_ENABLED", "true").lower() == "true"
-    IRC_PORT = 6667
+    BATCH_INTERVAL_MIN    = int(os.environ.get("BATCH_INTERVAL_MIN", "60"))
-    IRC_NICK = "grafana-bot"
+    BATCH_MAX_PENDING     = int(os.environ.get("BATCH_MAX_PENDING", "50"))
-    IRC_CHANNEL = "#alerts"
+
-    PRINT_WEB_URL = "http://10.0.57.16:5200/api/print/alert"
+    IRC_HOST      = os.environ.get("IRC_HOST", "unrealircd.irc.svc")
-    PRINT_ENABLED = True
+    IRC_PORT      = int(os.environ.get("IRC_PORT", "6667"))
+    IRC_NICK      = os.environ.get("IRC_NICK", "grafana-bot")
+    IRC_CHANNEL   = os.environ.get("IRC_CHANNEL", "#alerts")
+    PRINT_WEB_URL = os.environ.get("PRINT_WEB_URL", "http://10.0.57.16:5200/api/print/alert")
+
+    _buffer_lock = threading.Lock()
+    _buffer = {}   # fingerprint -> {"alert": dict, "first_seen": float, "last_seen": float}
+    _last_flush_time = time.time()
+    _stats = {"webhooks_received": 0, "irc_sent": 0, "print_immediate": 0,
+              "digest_flushed": 0, "buffer_dedup": 0, "buffer_added": 0,
+              "buffer_resolved": 0, "started_at": time.time()}
 
     def send_irc(message):
-        """Connect, handle PING, join, send, quit."""
         try:
             sock = socket.create_connection((IRC_HOST, IRC_PORT), timeout=15)
             sock.sendall(f"NICK {IRC_NICK}\r\n".encode())
@@ -1259,52 +1354,137 @@ data:
             time.sleep(0.5)
             sock.sendall(b"QUIT :alert delivered\r\n")
             sock.close()
+            _stats["irc_sent"] += 1
             return True
         except Exception as e:
             print(f"[irc-notify] IRC send failed: {e}", file=sys.stderr)
             return False
 
-    def send_thermal_print(alert):
+    def post_thermal(payload, kind):
-        if not PRINT_ENABLED: return
+        if not THERMAL_PRINT_ENABLED:
-        labels = alert.get("labels", {})
+            print(f"[irc-notify] thermal disabled; skip {kind} ({payload.get('title','?')[:40]})", file=sys.stderr)
-        annotations = alert.get("annotations", {})
+            return False
-        status = alert.get("status", "firing").upper()
-        summary = annotations.get("summary", "")
-        description = annotations.get("description", "")
-        runbook = annotations.get("runbook", "")
-        # Build a useful message: summary + description + runbook steps
-        parts = []
-        if summary: parts.append(summary)
-        if description and description != summary: parts.append(description)
-        if runbook: parts.append("STEPS: " + runbook)
-        message = " | ".join(parts) if parts else labels.get("alertname", "Unknown alert")
-        payload = {
-            "title": labels.get("alertname", "Unknown"),
-            "severity": labels.get("severity", "warning").capitalize(),
-            "host": labels.get("instance", labels.get("host", "unknown")),
-            "message": message,
-            "eventId": alert.get("fingerprint", ""),
-            "source": "Grafana",
-            "status": "RESOLVED" if status == "RESOLVED" else "PROBLEM",
-            "acknowledged": False
-        }
         try:
             req = Request(PRINT_WEB_URL, data=json.dumps(payload).encode("utf-8"),
                           headers={"Content-Type": "application/json"}, method="POST")
             resp = urlopen(req, timeout=10)
-            print(f"[irc-notify] Thermal print sent: {resp.read().decode()}", file=sys.stderr)
+            if kind == "immediate": _stats["print_immediate"] += 1
+            print(f"[irc-notify] thermal {kind} sent: {payload.get('title','?')[:50]}", file=sys.stderr)
+            return True
         except Exception as e:
-            print(f"[irc-notify] Thermal print failed: {e}", file=sys.stderr)
+            print(f"[irc-notify] thermal {kind} failed: {e}", file=sys.stderr)
+            return False
 
-    def should_print(alert):
+    def fingerprint_of(alert):
+        fp = alert.get("fingerprint", "")
+        if fp: return fp
         labels = alert.get("labels", {})
-        if labels.get("alert_channel") == "thermal_print": return True
+        target = labels.get("pod") or labels.get("instance") or labels.get("deployment") or labels.get("statefulset") or labels.get("namespace") or ""
-        if labels.get("severity", "").lower() in ("critical", "disaster"): return True
+        return f"{labels.get('alertname','?')}/{labels.get('namespace','')}/{target}"
-        if alert.get("status", "").upper() == "RESOLVED": return False
+
-        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", []):
@@ -1319,22 +1499,56 @@ data:
                 msg = f"{icon}{sev_tag} {name}: {summary}"
                 if desc: msg += f"\n  {desc}"
                 send_irc(msg)
-                if should_print(alert): send_thermal_print(alert)
+                # Thermal routing — EVERYTHING (including criticals) goes into
-            self.send_response(200)
+                # the hourly digest. Only the explicit `alert_channel=thermal_print_immediate`
-            self.send_header("Content-Type", "application/json")
+                # label bypasses, and even that flushes-the-current-digest rather
-            self.end_headers()
+                # than printing a standalone job, so the same fingerprint can't
+                # spam the printer per webhook cycle.
+                if status == "RESOLVED":
+                    add_to_digest(alert)  # removes from buffer
+                    continue
+                if is_immediate_label(alert):
+                    # Explicit opt-in for "paper this NOW" — first arrival of a
+                    # new fingerprint triggers an immediate digest flush; repeat
+                    # webhooks for the same fingerprint dedupe in the buffer
+                    # until the next interval or until the alert resolves.
+                    new_in_buffer = add_to_digest(alert)
+                    if new_in_buffer:
+                        global _last_flush_time
+                        flush_digest()
+                        _last_flush_time = time.time()
+                elif is_critical(alert) or is_batched_label(alert):
+                    add_to_digest(alert)
+                # else: IRC-only (warnings without thermal_print label)
+            self.send_response(200); self.send_header("Content-Type", "application/json"); self.end_headers()
             self.wfile.write(b'{"status":"ok"}')
+
         def do_GET(self):
-            self.send_response(200)
+            self.send_response(200); self.send_header("Content-Type", "application/json"); self.end_headers()
-            self.send_header("Content-Type", "application/json")
+            with _buffer_lock:
-            self.end_headers()
+                alertnames = sorted({it["alert"].get("labels", {}).get("alertname", "?") for it in _buffer.values()})
-            self.wfile.write(json.dumps({"service":"irc-notify","thermal_print":PRINT_ENABLED}).encode())
+                depth = len(_buffer)
+            info = {
+                "service": "irc-notify",
+                "config": {"thermal_print_enabled": THERMAL_PRINT_ENABLED,
+                           "batch_interval_min": BATCH_INTERVAL_MIN,
+                           "batch_max_pending": BATCH_MAX_PENDING,
+                           "irc_target": f"{IRC_HOST}:{IRC_PORT} {IRC_CHANNEL}",
+                           "print_web_url": PRINT_WEB_URL},
+                "buffer": {"depth": depth, "alertnames": alertnames,
+                           "seconds_since_last_flush": int(time.time() - _last_flush_time),
+                           "seconds_until_next_flush": max(0, int(BATCH_INTERVAL_MIN*60 - (time.time() - _last_flush_time)))},
+                "stats": _stats,
+            }
+            self.wfile.write(json.dumps(info, indent=2).encode())
+
         def log_message(self, format, *args):
             print(f"[irc-notify] {args[0]}", file=sys.stderr)
 
     if __name__ == "__main__":
+        threading.Thread(target=digest_loop, daemon=True).start()
         server = HTTPServer(("0.0.0.0", 9119), Handler)
-        print(f"IRC alert relay :9119 -> {IRC_HOST}:{IRC_PORT} {IRC_CHANNEL} (thermal: {PRINT_ENABLED})")
+        print(f"[irc-notify] :9119 -> IRC {IRC_HOST}:{IRC_PORT} {IRC_CHANNEL} | thermal={'ON' if THERMAL_PRINT_ENABLED else 'OFF'} | digest={BATCH_INTERVAL_MIN}m max={BATCH_MAX_PENDING}", file=sys.stderr)
         server.serve_forever()
 
 # =============================================================================
@@ -3421,6 +3635,39 @@ data:
                 relativeTimeRange: {from: 120, to: 0}
                 datasourceUid: __expr__
                 model: {type: threshold, expression: B, conditions: [{evaluator: {params: [600], type: gt}}], refId: C}
+      - orgId: 1
+        name: CI Runners
+        folder: CI Alerts
+        interval: 1m
+        rules:
+          - uid: linux-runner-offline
+            title: LinuxRunnerOffline
+            condition: C
+            for: 5m
+            noDataState: OK
+            execErrState: Error
+            annotations:
+              summary: "Linux CI runner offline: {{ $labels.deployment }}"
+              description: "A github-runner namespace Deployment has 0 ready replicas for more than 5 minutes. CI jobs targeting that repo will queue until the runner pod restarts and re-registers."
+              runbook: "1. kubectl -n github-runner get pods -l app.kubernetes.io/name={{ $labels.deployment }} 2. kubectl -n github-runner logs -l app.kubernetes.io/name={{ $labels.deployment }} --tail=50 3. Verify PAT repo access if registration returns 404 4. Verify no RWO PVC is shared by scaled runners"
+            labels:
+              severity: warning
+              service: github-runner
+              alert_channel: irc
+              team: ci
+            data:
+              - refId: A
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: prometheus
+                model: {expr: 'kube_deployment_status_replicas_ready{namespace="github-runner",deployment=~"github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"} == 0', instant: true, refId: A}
+              - refId: B
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: __expr__
+                model: {type: reduce, expression: A, reducer: last, refId: B}
+              - refId: C
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: __expr__
+                model: {type: threshold, expression: B, conditions: [{evaluator: {params: [0], type: gt}}], refId: C}
       - orgId: 1
         name: Infrastructure
         folder: AI Stack Alerts

apps/worldbuilder/README.md

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

apps/worldbuilder/worldbuilder.yaml

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

docs/runbooks/openvoxserver-quadlet-durability.md

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

scripts/monitoring/openvox-recreate-smoke.sh

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

tests/bluejay-infra-lint/FleetManifestLintTests.cs

@@ -13,6 +13,7 @@ public sealed class FleetManifestLintTests
 
     private static readonly HashSet<string> PublicReadOnlyHosts = new(StringComparer.Ordinal)
     {
+        "brochure.flowercore.io",
         "dist.flowercore.io",
         "dns.iamworkin.lan",
     };
@@ -54,6 +55,43 @@ public sealed class FleetManifestLintTests
         "ttsreader-piper",
     };
 
+    private static readonly IReadOnlyDictionary<string, string> LinuxRunnerRepos = new Dictionary<string, string>(StringComparer.Ordinal)
+    {
+        ["github-runner"] = "https://github.com/astoltz/FlowerCore.Common",
+        ["github-runner-sharedpos"] = "https://github.com/astoltz/FlowerCore.Shared.Pos",
+        ["github-runner-puppet"] = "https://github.com/astoltz/FlowerCore.Puppet",
+        ["github-runner-signage"] = "https://github.com/astoltz/FlowerCore.Signage",
+        ["github-runner-dms"] = "https://github.com/astoltz/FlowerCore.DMS",
+        ["github-runner-telephony"] = "https://github.com/astoltz/FlowerCore.Telephony",
+        ["github-runner-print-web"] = "https://github.com/astoltz/FlowerCore.Print.Web",
+        ["github-runner-chat"] = "https://github.com/astoltz/FlowerCore.Chat",
+        ["github-runner-mysql"] = "https://github.com/astoltz/FlowerCore.MySQL",
+        ["github-runner-kiosk-linux"] = "https://github.com/astoltz/FlowerCore.Kiosk.Linux",
+    };
+
+    private static readonly HashSet<string> ScaledLinuxRunnerDeployments = new(StringComparer.Ordinal)
+    {
+        "github-runner-sharedpos",
+        "github-runner-puppet",
+        "github-runner-signage",
+        "github-runner-dms",
+        "github-runner-telephony",
+        "github-runner-print-web",
+        "github-runner-chat",
+        "github-runner-mysql",
+        "github-runner-kiosk-linux",
+    };
+
+    private static readonly IReadOnlyDictionary<string, string> WritableRunnerEnv = new Dictionary<string, string>(StringComparer.Ordinal)
+    {
+        ["HOME"] = "/home/runner",
+        ["DOTNET_INSTALL_DIR"] = "/home/runner/.dotnet",
+        ["DOTNET_CLI_HOME"] = "/home/runner",
+        ["NUGET_PACKAGES"] = "/home/runner/.nuget/packages",
+        ["XDG_CACHE_HOME"] = "/home/runner/.cache",
+        ["RUNNER_TOOL_CACHE"] = "/home/runner/_tool",
+    };
+
     [Fact]
     public void IngressRoutes_MustKeepServiceReferencesInTheSameNamespace()
     {
@@ -187,6 +225,98 @@ public sealed class FleetManifestLintTests
         violations.Should().BeEmpty();
     }
 
+    [Fact]
+    public void GitHubRunnerFleet_MustRegisterRequiredReposAsRepoScopedDeployments()
+    {
+        var deployments = GitHubRunnerDeployments();
+
+        foreach (var expectedRunner in LinuxRunnerRepos)
+        {
+            deployments.Should().ContainKey(expectedRunner.Key);
+
+            var container = deployments[expectedRunner.Key].ContainerMappings().Should().ContainSingle().Subject;
+            EnvValue(container, "REPO_URL").Should().Be(expectedRunner.Value);
+            EnvValue(container, "EPHEMERAL").Should().Be("true");
+            EnvValue(container, "LABELS").Should().Be("self-hosted,linux,fc-build-linux");
+            EnvValue(container, "RUN_AS_ROOT").Should().Be("false");
+            EnvValue(container, "ACCESS_TOKEN").Should().BeNull("ACCESS_TOKEN must come from github-runner-token Secret, not a literal");
+            EnvSecretName(container, "ACCESS_TOKEN").Should().Be("github-runner-token");
+            EnvSecretKey(container, "ACCESS_TOKEN").Should().Be("credential");
+        }
+    }
+
+    [Fact]
+    public void GitHubRunnerFleet_MustSetWritableNonRootDotnetAndCachePaths()
+    {
+        foreach (var deployment in GitHubRunnerDeployments().Values)
+        {
+            var container = deployment.ContainerMappings().Should().ContainSingle().Subject;
+
+            foreach (var expectedEnv in WritableRunnerEnv)
+            {
+                EnvValue(container, expectedEnv.Key).Should().Be(expectedEnv.Value, $"{deployment.Name} must keep .NET paths writable for uid 1001");
+            }
+
+            var mounts = ManifestNodeExtensions.MappingSequence(container, "volumeMounts")
+                .ToDictionary(
+                    mount => ManifestNodeExtensions.Scalar(mount, "name") ?? string.Empty,
+                    mount => ManifestNodeExtensions.Scalar(mount, "mountPath") ?? string.Empty,
+                    StringComparer.Ordinal);
+
+            mounts.Should().Contain("runner-home", "/home/runner");
+            mounts.Should().Contain("nuget-cache", "/home/runner/.nuget/packages");
+            mounts.Should().Contain("tmp", "/tmp");
+        }
+    }
+
+    [Fact]
+    public void GitHubRunnerFleet_MustAvoidRwoMultiAttachForScaledDeployments()
+    {
+        var deployments = GitHubRunnerDeployments();
+
+        foreach (var deploymentName in ScaledLinuxRunnerDeployments)
+        {
+            var deployment = deployments[deploymentName];
+            ReplicaCount(deployment).Should().Be(2);
+
+            var volumes = deployment.MappingSequence("spec", "template", "spec", "volumes");
+            var claimNames = volumes
+                .Select(volume => ManifestNodeExtensions.Scalar(volume, "persistentVolumeClaim", "claimName"))
+                .Where(value => !string.IsNullOrWhiteSpace(value))
+                .ToList();
+
+            claimNames.Should().BeEmpty($"{deploymentName} is scaled and must not share a RWO PVC");
+            volumes.Should().Contain(volume =>
+                string.Equals(ManifestNodeExtensions.Scalar(volume, "name"), "nuget-cache", StringComparison.Ordinal)
+                && ManifestNodeExtensions.Mapping(volume, "emptyDir") != null);
+        }
+
+        var common = deployments["github-runner"];
+        ReplicaCount(common).Should().Be(1);
+        common.MappingSequence("spec", "template", "spec", "volumes")
+            .Select(volume => ManifestNodeExtensions.Scalar(volume, "persistentVolumeClaim", "claimName"))
+            .Where(value => !string.IsNullOrWhiteSpace(value))
+            .Should()
+            .ContainSingle()
+            .Which
+            .Should()
+            .Be("github-runner-nuget-cache");
+    }
+
+    [Fact]
+    public void Monitoring_MustAlertWhenLinuxRunnerDeploymentIsUnavailable()
+    {
+        var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
+
+        monitoring.Should().Contain("MacMiniRunnerOffline");
+        monitoring.Should().Contain("LinuxRunnerOffline");
+        monitoring.Should().Contain("kube_deployment_status_replicas_ready");
+        monitoring.Should().Contain("github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))");
+        monitoring.Should().Contain("folder: CI Alerts");
+        monitoring.Should().Contain("uid: linux-runner-offline");
+        monitoring.Should().Contain("alert_channel: irc");
+    }
+
     [Fact]
     public void StatefulSets_WithVolumeClaimTemplates_MustDeclareFilesystemDefaults()
     {
@@ -493,6 +623,44 @@ public sealed class FleetManifestLintTests
         };
     }
 
+    private static IReadOnlyDictionary<string, ManifestDocument> GitHubRunnerDeployments()
+    {
+        return Inventory.Documents
+            .Where(document => document.Kind == "Deployment")
+            .Where(document => document.Namespace == "github-runner")
+            .ToDictionary(document => document.Name, StringComparer.Ordinal);
+    }
+
+    private static int ReplicaCount(ManifestDocument document)
+    {
+        return int.TryParse(document.Scalar("spec", "replicas"), out var replicas) ? replicas : 1;
+    }
+
+    private static string? EnvValue(YamlMappingNode container, string name)
+    {
+        return EnvMapping(container, name) is { } env ? ManifestNodeExtensions.Scalar(env, "value") : null;
+    }
+
+    private static string? EnvSecretName(YamlMappingNode container, string name)
+    {
+        return EnvMapping(container, name) is { } env
+            ? ManifestNodeExtensions.Scalar(env, "valueFrom", "secretKeyRef", "name")
+            : null;
+    }
+
+    private static string? EnvSecretKey(YamlMappingNode container, string name)
+    {
+        return EnvMapping(container, name) is { } env
+            ? ManifestNodeExtensions.Scalar(env, "valueFrom", "secretKeyRef", "key")
+            : null;
+    }
+
+    private static YamlMappingNode? EnvMapping(YamlMappingNode container, string name)
+    {
+        return ManifestNodeExtensions.MappingSequence(container, "env")
+            .SingleOrDefault(env => string.Equals(ManifestNodeExtensions.Scalar(env, "name"), name, StringComparison.Ordinal));
+    }
+
     private static IReadOnlyList<ManifestDocument> FcDeviceManagementDocuments()
     {
         return Inventory.Documents

tests/bluejay-infra-lint/OpenVoxServerDurabilityTests.cs

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

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

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