runners: right-size replica counts per 14d CI activity (#24)

Drop 2 → 1 for 10 deploys based on trailing-14d run counts:
  - LlmBridge, Media, Knowledge, Intranet.Web, DNS  (0 runs each)
  - Presentations (6), Redis (3), Provisioning (3),
    MessageBoard (3), MenuBoard (3)

Bump 2 → 3 for Print.Web: 12 runs in trailing 5d, and the
help-screenshots AAT job holds a runner 30+ min, creating
head-of-line blocking for parallel PRs.

Net change: -9 replicas (≈ -9 GiB committed memory).
Aligns with Sprint 33 morning-routine capacity audit.

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

apps/authentik/authentik.yaml

@@ -0,0 +1,448 @@
+# Authentik OIDC backend
+# ArgoCD-managed. BlueJay Lab.
+#
+# Stack:
+#   - PostgreSQL 16 StatefulSet (single replica, Longhorn RWO 5Gi)
+#   - Redis 7 Deployment (no persistence — session/cache only)
+#   - Authentik server + worker Deployments (image ghcr.io/goauthentik/server:2024.12.3)
+#   - Media PVC shared between server + worker (Longhorn RWO 2Gi)
+#   - Certificate via step-ca-acme ClusterIssuer
+#   - Traefik IngressRoute at id.iamworkin.lan
+#
+# Secrets come from 1Password item "authentik-credentials" (IAmWorkin vault, id y6i74ch22q5wvm7znquq4nhhcu)
+# via the OnePasswordItem CRD, materialized into k8s Secret authentik/authentik-credentials.
+#
+# Why the discovery URL is /application/o/pimanager/ : Authentik issues per-application OIDC providers.
+# The pimanager OIDC application/provider is created after the cluster pods are healthy (manual or
+# via API once the bootstrap token is available — see Notes substrate).
+
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: authentik
+  labels:
+    app.kubernetes.io/part-of: bluejay-infra
+
+---
+# 1Password operator pulls the authentik-credentials item into a k8s Secret of the same name.
+# Field labels in 1P become Secret keys: AUTHENTIK_SECRET_KEY, POSTGRES_PASSWORD, REDIS_PASSWORD,
+# BOOTSTRAP_ADMIN_PASSWORD, BOOTSTRAP_ADMIN_TOKEN, BOOTSTRAP_ADMIN_EMAIL.
+apiVersion: onepassword.com/v1
+kind: OnePasswordItem
+metadata:
+  name: authentik-credentials
+  namespace: authentik
+spec:
+  itemPath: "vaults/IAmWorkin/items/authentik-credentials"
+
+---
+# Shared media volume for server + worker pods.
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: authentik-media
+  namespace: authentik
+spec:
+  storageClassName: longhorn
+  accessModes: [ReadWriteOnce]
+  resources:
+    requests:
+      storage: 2Gi
+
+---
+# PostgreSQL 16 StatefulSet — Authentik's primary store.
+apiVersion: apps/v1
+kind: StatefulSet
+metadata:
+  name: authentik-postgres
+  namespace: authentik
+  labels:
+    app: authentik-postgres
+    argocd.argoproj.io/instance: infra-authentik
+spec:
+  persistentVolumeClaimRetentionPolicy:
+    whenDeleted: Retain
+    whenScaled: Retain
+  podManagementPolicy: OrderedReady
+  serviceName: authentik-postgres
+  replicas: 1
+  revisionHistoryLimit: 10
+  selector:
+    matchLabels:
+      app: authentik-postgres
+  template:
+    metadata:
+      labels:
+        app: authentik-postgres
+    spec:
+      containers:
+        - name: postgres
+          image: postgres:16-alpine
+          ports:
+            - containerPort: 5432
+              name: postgres
+          env:
+            - name: POSTGRES_USER
+              value: authentik
+            - name: POSTGRES_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: POSTGRES_PASSWORD
+            - name: POSTGRES_DB
+              value: authentik
+            - name: POSTGRES_INITDB_ARGS
+              value: "--encoding=UTF-8 --lc-collate=C --lc-ctype=C"
+            - name: PGDATA
+              value: /var/lib/postgresql/data/pgdata
+          readinessProbe:
+            exec:
+              command: ["pg_isready", "-U", "authentik"]
+            initialDelaySeconds: 5
+            periodSeconds: 5
+          livenessProbe:
+            exec:
+              command: ["pg_isready", "-U", "authentik"]
+            initialDelaySeconds: 30
+            periodSeconds: 30
+          resources:
+            requests: { cpu: 100m, memory: 256Mi }
+            limits: { cpu: 1000m, memory: 1Gi }
+          volumeMounts:
+            - name: pgdata
+              mountPath: /var/lib/postgresql/data
+  volumeClaimTemplates:
+    - metadata:
+        name: pgdata
+      spec:
+        storageClassName: longhorn
+        accessModes: [ReadWriteOnce]
+        volumeMode: Filesystem
+        resources:
+          requests:
+            storage: 5Gi
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: authentik-postgres
+  namespace: authentik
+spec:
+  clusterIP: None
+  selector:
+    app: authentik-postgres
+  ports:
+    - name: postgres
+      port: 5432
+      targetPort: 5432
+
+---
+# Redis 7 — session storage + Celery broker. No persistence needed (cache).
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: authentik-redis
+  namespace: authentik
+  labels:
+    app: authentik-redis
+    argocd.argoproj.io/instance: infra-authentik
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: authentik-redis
+  template:
+    metadata:
+      labels:
+        app: authentik-redis
+    spec:
+      containers:
+        - name: redis
+          image: redis:7-alpine
+          args:
+            - "--save"
+            - ""
+            - "--appendonly"
+            - "no"
+            - "--requirepass"
+            - "$(REDIS_PASSWORD)"
+          env:
+            - name: REDIS_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: REDIS_PASSWORD
+          ports:
+            - containerPort: 6379
+              name: redis
+          readinessProbe:
+            tcpSocket: { port: 6379 }
+            initialDelaySeconds: 5
+            periodSeconds: 5
+          livenessProbe:
+            tcpSocket: { port: 6379 }
+            initialDelaySeconds: 30
+            periodSeconds: 30
+          resources:
+            requests: { cpu: 50m, memory: 64Mi }
+            limits: { cpu: 500m, memory: 256Mi }
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: authentik-redis
+  namespace: authentik
+spec:
+  selector:
+    app: authentik-redis
+  ports:
+    - name: redis
+      port: 6379
+      targetPort: 6379
+
+---
+# Authentik server Deployment — HTTP frontend on :9000.
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: authentik-server
+  namespace: authentik
+  labels:
+    app: authentik-server
+    argocd.argoproj.io/instance: infra-authentik
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate  # shares /media RWO PVC with worker
+  selector:
+    matchLabels:
+      app: authentik-server
+  template:
+    metadata:
+      labels:
+        app: authentik-server
+    spec:
+      securityContext:
+        # Authentik image runs as uid 1000 "authentik" but the Longhorn PVC mounts
+        # root:root by default. fsGroup recursively chgrp + chmod g+rwx so the
+        # non-root container can mkdir /media/public during the tenant_files migration.
+        fsGroup: 1000
+      containers:
+        - name: server
+          image: ghcr.io/goauthentik/server:2024.12.3
+          args: ["server"]
+          ports:
+            - containerPort: 9000
+              name: http
+            - containerPort: 9443
+              name: https
+          env:
+            - name: AUTHENTIK_SECRET_KEY
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: AUTHENTIK_SECRET_KEY
+            - name: AUTHENTIK_REDIS__HOST
+              value: authentik-redis
+            - name: AUTHENTIK_REDIS__PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: REDIS_PASSWORD
+            - name: AUTHENTIK_POSTGRESQL__HOST
+              value: authentik-postgres
+            - name: AUTHENTIK_POSTGRESQL__NAME
+              value: authentik
+            - name: AUTHENTIK_POSTGRESQL__USER
+              value: authentik
+            - name: AUTHENTIK_POSTGRESQL__PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: POSTGRES_PASSWORD
+            - name: AUTHENTIK_BOOTSTRAP_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: BOOTSTRAP_ADMIN_PASSWORD
+            - name: AUTHENTIK_BOOTSTRAP_TOKEN
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: BOOTSTRAP_ADMIN_TOKEN
+            - name: AUTHENTIK_BOOTSTRAP_EMAIL
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: BOOTSTRAP_ADMIN_EMAIL
+            - name: AUTHENTIK_DISABLE_UPDATE_CHECK
+              value: "true"
+            - name: AUTHENTIK_ERROR_REPORTING__ENABLED
+              value: "false"
+            - name: AUTHENTIK_LOG_LEVEL
+              value: info
+          # First-boot Authentik can take 3+ min on the migration phase
+          # (waiting on DB lock while worker also runs migrations). Initial
+          # delays are generous so kubelet doesn't kill the pod mid-migration;
+          # periodSeconds keeps post-startup probing responsive.
+          readinessProbe:
+            httpGet:
+              path: /-/health/ready/
+              port: 9000
+            initialDelaySeconds: 60
+            periodSeconds: 10
+            timeoutSeconds: 5
+            failureThreshold: 12
+          livenessProbe:
+            httpGet:
+              path: /-/health/live/
+              port: 9000
+            initialDelaySeconds: 300
+            periodSeconds: 30
+            timeoutSeconds: 10
+            failureThreshold: 3
+          startupProbe:
+            httpGet:
+              path: /-/health/live/
+              port: 9000
+            initialDelaySeconds: 30
+            periodSeconds: 15
+            timeoutSeconds: 10
+            failureThreshold: 40  # 30s + 40*15s = 10.5 min budget
+          resources:
+            requests: { cpu: 150m, memory: 512Mi }
+            limits: { cpu: 1500m, memory: 1Gi }
+          volumeMounts:
+            - name: media
+              mountPath: /media
+      volumes:
+        - name: media
+          persistentVolumeClaim:
+            claimName: authentik-media
+
+---
+# Authentik worker Deployment — runs Celery background tasks.
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: authentik-worker
+  namespace: authentik
+  labels:
+    app: authentik-worker
+    argocd.argoproj.io/instance: infra-authentik
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate  # shares /media RWO PVC with server
+  selector:
+    matchLabels:
+      app: authentik-worker
+  template:
+    metadata:
+      labels:
+        app: authentik-worker
+    spec:
+      securityContext:
+        # Same as server pod — non-root uid 1000 needs PVC group write.
+        fsGroup: 1000
+      containers:
+        - name: worker
+          image: ghcr.io/goauthentik/server:2024.12.3
+          args: ["worker"]
+          env:
+            - name: AUTHENTIK_SECRET_KEY
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: AUTHENTIK_SECRET_KEY
+            - name: AUTHENTIK_REDIS__HOST
+              value: authentik-redis
+            - name: AUTHENTIK_REDIS__PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: REDIS_PASSWORD
+            - name: AUTHENTIK_POSTGRESQL__HOST
+              value: authentik-postgres
+            - name: AUTHENTIK_POSTGRESQL__NAME
+              value: authentik
+            - name: AUTHENTIK_POSTGRESQL__USER
+              value: authentik
+            - name: AUTHENTIK_POSTGRESQL__PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: authentik-credentials
+                  key: POSTGRES_PASSWORD
+            - name: AUTHENTIK_DISABLE_UPDATE_CHECK
+              value: "true"
+            - name: AUTHENTIK_ERROR_REPORTING__ENABLED
+              value: "false"
+            - name: AUTHENTIK_LOG_LEVEL
+              value: info
+          resources:
+            requests: { cpu: 100m, memory: 256Mi }
+            limits: { cpu: 1000m, memory: 768Mi }
+          volumeMounts:
+            - name: media
+              mountPath: /media
+      volumes:
+        - name: media
+          persistentVolumeClaim:
+            claimName: authentik-media
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: authentik-server
+  namespace: authentik
+spec:
+  selector:
+    app: authentik-server
+  ports:
+    - name: http
+      port: 9000
+      targetPort: 9000
+    - name: https
+      port: 9443
+      targetPort: 9443
+
+---
+# step-ca leaf certificate for id.iamworkin.lan.
+# step-ca container resolver uses pfSense Unbound, so the public A record for id.iamworkin.lan
+# MUST exist before this Certificate is applied (cert-manager HTTP-01 will silently 2h-backoff
+# otherwise). Added 2026-05-25 via scripts/pfsense-add-id-host.py.
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: authentik-tls
+  namespace: authentik
+spec:
+  secretName: authentik-tls
+  dnsNames:
+    - id.iamworkin.lan
+  issuerRef:
+    name: step-ca-acme
+    kind: ClusterIssuer
+
+---
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: authentik
+  namespace: authentik
+spec:
+  entryPoints: [websecure]
+  routes:
+    - match: Host(`id.iamworkin.lan`)
+      kind: Rule
+      services:
+        - name: authentik-server
+          port: 9000
+  tls:
+    secretName: authentik-tls

apps/fc-devicemgmt/argocd-application.yaml

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

apps/github-runner/.gitattributes

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

apps/github-runner/Dockerfile

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

apps/github-runner/README.md

@@ -7,12 +7,17 @@ Deployments with `kubectl`; update this manifest and let ArgoCD reconcile.
 
 All repo-scoped Linux runners use:
 
+- `localhost/fc-github-runner:v20260520-ruby3.3.11`, derived from
+  `myoung34/github-runner:latest`
 - `ACCESS_TOKEN` from the `github-runner-token` Secret
 - `RUN_AS_ROOT=false`
 - `EPHEMERAL=true`
 - `LABELS=self-hosted,linux,fc-build-linux`
 - writable non-root paths under `/home/runner` for .NET, NuGet, XDG cache, and
   Actions tool cache
+- Ruby 3.3.11 seeded into `/home/runner/_tool/Ruby/3.3/x64` from the baked
+  `/opt/runner-toolcache` copy so `ruby/setup-ruby@v1` can discover it on
+  self-hosted `ubuntu-20.04-x64` runners
 
 `github-runner` for `FlowerCore.Common` is single-replica because it retains the
 original Longhorn ReadWriteOnce NuGet PVC. Every other repo-scoped runner uses
@@ -28,6 +33,34 @@ 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.
+
+```bash
+cd apps/github-runner
+podman build -t localhost/fc-github-runner:v20260520-ruby3.3.11 .
+podman run --rm localhost/fc-github-runner:v20260520-ruby3.3.11 ruby -v
+podman run --rm localhost/fc-github-runner:v20260520-ruby3.3.11 \
+  test -f /opt/runner-toolcache/Ruby/3.3/x64.complete
+podman save localhost/fc-github-runner:v20260520-ruby3.3.11 \
+  -o fc-github-runner-v20260520-ruby3.3.11.tar
+```
+
+Import the saved image on every schedulable RKE2 node before ArgoCD rolls the
+Deployments:
+
+```bash
+for node in rke2-server rke2-agent1 rke2-agent2; do
+  scp fc-github-runner-v20260520-ruby3.3.11.tar "$node:/tmp/"
+  ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images rm localhost/fc-github-runner:v20260520-ruby3.3.11 || true'
+  ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images import /tmp/fc-github-runner-v20260520-ruby3.3.11.tar'
+done
+```
+
 ## Post-Merge Proof
 
 After the PR is merged and ArgoCD syncs, verify the runner fleet:
@@ -36,6 +69,14 @@ 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
@@ -69,6 +110,10 @@ 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

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+RUBY_VERSION="${RUBY_VERSION:-3.3.11}"
+RUBY_MINOR="${RUBY_MINOR:-3.3}"
+TOOLCACHE_ROOT="${TOOLCACHE_ROOT:-/opt/runner-toolcache}"
+RUNNER_UID="${RUNNER_UID:-1001}"
+RUNNER_GID="${RUNNER_GID:-1001}"
+RUBY_PREFIX="${TOOLCACHE_ROOT}/Ruby/${RUBY_VERSION}/x64"
+
+mkdir -p "${TOOLCACHE_ROOT}/Ruby"
+RUBY_CONFIGURE_OPTS="${RUBY_CONFIGURE_OPTS:---disable-install-doc --disable-yjit}" ruby-build "${RUBY_VERSION}" "${RUBY_PREFIX}"
+
+touch "${TOOLCACHE_ROOT}/Ruby/${RUBY_VERSION}/x64.complete"
+ln -sfn "${RUBY_VERSION}" "${TOOLCACHE_ROOT}/Ruby/${RUBY_MINOR}"
+
+"${RUBY_PREFIX}/bin/ruby" -v
+chown -R "${RUNNER_UID}:${RUNNER_GID}" "${TOOLCACHE_ROOT}"
+chmod -R a+rX "${TOOLCACHE_ROOT}"

apps/monitoring/noc-monitoring.yaml

@@ -280,13 +280,14 @@ data:
               printer_model: "NuPrint 210"
 
       # Print.Web health (Blazor app on edge2:5200)
+      # Target `/health` (anonymous) — root path requires API key auth and returns 401.
       - job_name: "probe-printweb"
         metrics_path: /probe
         params:
           module: [http_2xx]
         scrape_interval: 30s
         static_configs:
-          - targets: ["http://10.0.57.16:5200/"]
+          - targets: ["http://10.0.57.16:5200/health"]
             labels:
               instance: "print-web"
               service: "print-web"
@@ -656,15 +657,14 @@ data:
               summary: "Print queue backlog on edge2 ({{ $value }} active jobs)"
               description: "CUPS has {{ $value }} active jobs queued. Possible printer jam, USB disconnect, or paper out."
 
-          # Printer hardware and paper-roll lifecycle alerts.
+          # Paper roll lifecycle alerts (XL Track I, 2026-04-26).
-          # print_printer_online: 1 when the transport is reachable/selected.
+          # Source-of-truth gauge: print_paper_remaining_percent (Print.Web OTEL,
-          # print_printer_state enum: 0 unknown, 1 online, 2 offline,
+          # hydrated on startup from the active PaperRoll row).
-          # 3 paper_depleted, 4 jam, 5 head_error, 6 cover_open.
+          # alert_channel=thermal_print routes through irc-notify -> Print.Web
-          # Offline/jam/cover alerts stay IRC-only. Paper depleted and head
+          # /api/print/alert so the printer announces its own paper-out warning
-          # error may route to the thermal digest only when the printer is
+          # on its remaining paper. Self-referential humor + operator nudge.
-          # online enough to make that useful.
           - alert: PrintPaperRollLow
-            expr: (print_paper_remaining_percent{job="printweb-otel"} < 10 and print_paper_remaining_percent{job="printweb-otel"} > 5) and print_printer_online{job="printweb-otel"} == 1
+            expr: print_paper_remaining_percent{job="printweb-otel"} < 10 and print_paper_remaining_percent{job="printweb-otel"} > 5
             for: 5m
             labels:
               severity: warning
@@ -673,59 +673,15 @@ data:
               summary: "Print roll low on edge2 ({{ $value | printf \"%.1f\" }}% remaining)"
               description: "NuPrint 210 paper roll has {{ $value | printf \"%.1f\" }}% remaining. Operator should load a fresh roll soon. Run /api/paper/status for the precise mm + estimated jobs left."
 
-          - alert: PrinterOfflineWarning
-            expr: print_printer_state{job="printweb-otel"} == 2
-            for: 2m
-            labels:
-              severity: warning
-              service: print-web
-              alert_channel: irc
-            annotations:
-              summary: "Print.Web printer offline on edge2"
-              description: "Print.Web reports the NuPrint 210 transport is offline or unreachable. IRC-only by design: do not thermal-print an alert when the thermal printer itself is offline."
-
           - alert: PrintPaperRollCritical
-            expr: print_printer_state{job="printweb-otel"} == 3 and print_printer_online{job="printweb-otel"} == 1
+            expr: print_paper_remaining_percent{job="printweb-otel"} <= 5
             for: 2m
             labels:
               severity: critical
               alert_channel: thermal_print
             annotations:
-              summary: "Print paper depleted on edge2"
+              summary: "Print roll critical on edge2 ({{ $value | printf \"%.1f\" }}% remaining)"
-              description: "NuPrint 210 reports paper depleted while the printer is still online. Load a new roll, drain the hardware buffer if needed, then replay DeadLetter jobs from /print-log."
+              description: "NuPrint 210 paper roll at {{ $value | printf \"%.1f\" }}% — load a new roll NOW. The 50ft roll has a ~12% red-stripe zone; once paper passes that, the printer can run dry mid-job."
-
-          - alert: PrinterJamWarning
-            expr: print_printer_state{job="printweb-otel"} == 4
-            for: 2m
-            labels:
-              severity: warning
-              service: print-web
-              alert_channel: irc
-            annotations:
-              summary: "Print.Web printer jam on edge2"
-              description: "Print.Web reports a paper/cutter jam state. IRC-only: clear the jam, drain the hardware buffer if bytes were queued, then retry affected jobs."
-
-          - alert: PrinterHeadErrorCritical
-            expr: print_printer_state{job="printweb-otel"} == 5
-            for: 2m
-            labels:
-              severity: critical
-              service: print-web
-              alert_channel: thermal_print
-            annotations:
-              summary: "Print.Web printer head error on edge2"
-              description: "Print.Web reports a thermal head or unrecoverable printer error. Critical routing may enter the thermal digest per existing policy; IRC remains the primary triage stream."
-
-          - alert: PrinterCoverOpenWarning
-            expr: print_printer_state{job="printweb-otel"} == 6
-            for: 2m
-            labels:
-              severity: warning
-              service: print-web
-              alert_channel: irc
-            annotations:
-              summary: "Print.Web printer cover open on edge2"
-              description: "Print.Web reports the printer cover/lid is open. IRC-only: close the cover and verify /api/print/status before retrying jobs."
 
           - alert: PrintJobDeadLetter
             expr: increase(print_jobs_dead_letter_total[15m]) > 0
@@ -3680,146 +3636,6 @@ data:
                 relativeTimeRange: {from: 120, to: 0}
                 datasourceUid: __expr__
                 model: {type: threshold, expression: B, conditions: [{evaluator: {params: [600], type: gt}}], refId: C}
-      - orgId: 1
-        name: Print Services
-        folder: Print Alerts
-        interval: 1m
-        rules:
-          - uid: printer-offline-warning
-            title: PrinterOfflineWarning
-            condition: C
-            for: 2m
-            noDataState: OK
-            execErrState: OK
-            annotations:
-              summary: "Print.Web printer offline on edge2"
-              description: "Print.Web reports the NuPrint 210 transport is offline or unreachable. IRC-only by design: do not thermal-print an alert when the thermal printer itself is offline."
-              runbook: "1. Check edge2 power/network 2. Check USB/CUPS queue 3. Open https://print.iamworkin.lan/admin 4. Do not force thermal routing for offline alerts."
-            labels:
-              severity: warning
-              service: print-web
-              alert_channel: irc
-            data:
-              - refId: A
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: prometheus
-                model: {expr: 'print_printer_state{job="printweb-otel"} == 2', instant: true, refId: A}
-              - refId: B
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: __expr__
-                model: {type: reduce, expression: A, reducer: last, refId: B}
-              - refId: C
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: __expr__
-                model: {type: threshold, expression: B, conditions: [{evaluator: {params: [0], type: gt}}], refId: C}
-          - uid: print-paper-roll-critical
-            title: PrintPaperRollCritical
-            condition: C
-            for: 2m
-            noDataState: OK
-            execErrState: OK
-            annotations:
-              summary: "Print paper depleted on edge2"
-              description: "NuPrint 210 reports paper depleted while the printer is still online. Load a new roll, drain the hardware buffer if needed, then replay DeadLetter jobs from /print-log."
-              runbook: "1. Load a fresh roll 2. Drain the hardware buffer if paper-out happened mid-job 3. Open https://print.iamworkin.lan/print-log 4. Retry DeadLetter jobs after the state clears."
-            labels:
-              severity: critical
-              service: print-web
-              alert_channel: thermal_print
-            data:
-              - refId: A
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: prometheus
-                model: {expr: 'print_printer_state{job="printweb-otel"} == 3 and print_printer_online{job="printweb-otel"} == 1', instant: true, refId: A}
-              - refId: B
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: __expr__
-                model: {type: reduce, expression: A, reducer: last, refId: B}
-              - refId: C
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: __expr__
-                model: {type: threshold, expression: B, conditions: [{evaluator: {params: [0], type: gt}}], refId: C}
-          - uid: printer-jam-warning
-            title: PrinterJamWarning
-            condition: C
-            for: 2m
-            noDataState: OK
-            execErrState: OK
-            annotations:
-              summary: "Print.Web printer jam on edge2"
-              description: "Print.Web reports a paper/cutter jam state. IRC-only: clear the jam, drain the hardware buffer if bytes were queued, then retry affected jobs."
-              runbook: "1. Clear paper/cutter path 2. Drain hardware buffer if CUPS queued bytes 3. Verify /api/print/status 4. Retry affected jobs."
-            labels:
-              severity: warning
-              service: print-web
-              alert_channel: irc
-            data:
-              - refId: A
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: prometheus
-                model: {expr: 'print_printer_state{job="printweb-otel"} == 4', instant: true, refId: A}
-              - refId: B
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: __expr__
-                model: {type: reduce, expression: A, reducer: last, refId: B}
-              - refId: C
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: __expr__
-                model: {type: threshold, expression: B, conditions: [{evaluator: {params: [0], type: gt}}], refId: C}
-          - uid: printer-head-error-critical
-            title: PrinterHeadErrorCritical
-            condition: C
-            for: 2m
-            noDataState: OK
-            execErrState: OK
-            annotations:
-              summary: "Print.Web printer head error on edge2"
-              description: "Print.Web reports a thermal head or unrecoverable printer error. Critical routing may enter the thermal digest per existing policy; IRC remains the primary triage stream."
-              runbook: "1. Let the printer cool if overheated 2. Power-cycle only after checking queued jobs 3. Verify /api/print/status 4. Retry jobs after the state clears."
-            labels:
-              severity: critical
-              service: print-web
-              alert_channel: thermal_print
-            data:
-              - refId: A
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: prometheus
-                model: {expr: 'print_printer_state{job="printweb-otel"} == 5', instant: true, refId: A}
-              - refId: B
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: __expr__
-                model: {type: reduce, expression: A, reducer: last, refId: B}
-              - refId: C
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: __expr__
-                model: {type: threshold, expression: B, conditions: [{evaluator: {params: [0], type: gt}}], refId: C}
-          - uid: printer-cover-open-warning
-            title: PrinterCoverOpenWarning
-            condition: C
-            for: 2m
-            noDataState: OK
-            execErrState: OK
-            annotations:
-              summary: "Print.Web printer cover open on edge2"
-              description: "Print.Web reports the printer cover/lid is open. IRC-only: close the cover and verify /api/print/status before retrying jobs."
-              runbook: "1. Close the printer cover 2. Verify /api/print/status returns online 3. Retry affected jobs only after the state clears."
-            labels:
-              severity: warning
-              service: print-web
-              alert_channel: irc
-            data:
-              - refId: A
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: prometheus
-                model: {expr: 'print_printer_state{job="printweb-otel"} == 6', instant: true, refId: A}
-              - refId: B
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: __expr__
-                model: {type: reduce, expression: A, reducer: last, refId: B}
-              - refId: C
-                relativeTimeRange: {from: 120, to: 0}
-                datasourceUid: __expr__
-                model: {type: threshold, expression: B, conditions: [{evaluator: {params: [0], type: gt}}], refId: C}
       - orgId: 1
         name: CI Runners
         folder: CI Alerts

tests/bluejay-infra-lint/FleetManifestLintTests.cs

@@ -304,7 +304,7 @@ public sealed class FleetManifestLintTests
     }
 
     [Fact]
-    public void Monitoring_MustIncludeRequiredAlertRoutingGuards()
+    public void Monitoring_MustAlertWhenLinuxRunnerDeploymentIsUnavailable()
     {
         var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
 
@@ -315,15 +315,6 @@ public sealed class FleetManifestLintTests
         monitoring.Should().Contain("folder: CI Alerts");
         monitoring.Should().Contain("uid: linux-runner-offline");
         monitoring.Should().Contain("alert_channel: irc");
-
-        monitoring.Should().Contain("PrinterOfflineWarning");
-        monitoring.Should().Contain("expr: print_printer_state{job=\"printweb-otel\"} == 2");
-        monitoring.Should().Contain("IRC-only by design: do not thermal-print an alert when the thermal printer itself is offline.");
-        monitoring.Should().Contain("PrintPaperRollCritical");
-        monitoring.Should().Contain("expr: print_printer_state{job=\"printweb-otel\"} == 3 and print_printer_online{job=\"printweb-otel\"} == 1");
-        monitoring.Should().Contain("PrinterJamWarning");
-        monitoring.Should().Contain("PrinterHeadErrorCritical");
-        monitoring.Should().Contain("PrinterCoverOpenWarning");
     }
 
     [Fact]