fix(monitoring): cap Prometheus retention below the PVC size

retentionSize was 95GB against a 25Gi volume, so the limit never fired. The
volume filled, and Prometheus crashlooped with:

  write /prometheus/queries.active: no space left on device
  failed to initialize active query tracker

18GB keeps roughly 7GiB of headroom for the WAL and block overhead.

k8s/apps/sms/deployment-macos.yaml

@@ -1,120 +0,0 @@
-# macOS VM (Docker-OSX) hosting the BlueBubbles server.
-#
-# ── Why a VM and not a container ────────────────────────────────────────────
-# Containers share the host kernel. macOS binaries are Mach-O and need XNU plus
-# Cocoa/IOKit, which a Linux kernel cannot provide, so no macOS container exists
-# or can exist. Docker-OSX is QEMU running a macOS guest, packaged in a
-# container — a VM in a box, not a macOS container.
-#
-# ── Why this works on worker-2 ──────────────────────────────────────────────
-# Verified on the existing hardware: amd64, `vmx` (Intel VT-x) present, and
-# /dev/kvm exists on Talos nodes (KVM is compiled into Talos' kernel, not a
-# module). Bare metal, so no nested virtualisation needed.
-#
-# ── Read this before relying on it ──────────────────────────────────────────
-# 1. Setup is INTERACTIVE. First boot runs the macOS installer: connect over
-#    VNC (:5999), erase the disk in Disk Utility, install, create a user, sign
-#    into iMessage, THEN install BlueBubbles inside the guest. This manifest
-#    only provides the machine; it does not provision macOS.
-# 2. iMessage activation on non-Apple hardware is a coin flip. BlueBubbles'
-#    own guidance: "test sending an iMessage to yourself. If it does not
-#    succeed, it's likely best to restart from the beginning."
-# 3. Apple's macOS licence permits virtualisation only on Apple hardware. This
-#    is a Hackintosh. Use a throwaway Apple ID, not a primary one.
-# 4. BlueBubbles labels this path "not for beginners", "no guarantees or
-#    warranty".
-#
-# Private API (reactions, typing indicators, edit/unsend) needs SIP disabled
-# inside the guest and is NOT required for plain send/receive. Skip it.
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: macos-bluebubbles
-  labels:
-    app.kubernetes.io/name: macos-bluebubbles
-    app.kubernetes.io/part-of: sms
-spec:
-  # Scaled to 0 on 2026-10-24. The pod pinned itself to a node labelled
-  # workload=imessage, and no such node exists any more. The PVC macos-disk also
-  # uses StorageClass longhorn-imessage-local, which pins the same dead node and
-  # stayed unbound for 71 days. The macOS guest therefore cannot start. Raise
-  # this to 1 again only after a KVM-capable node carries that label and taint.
-  replicas: 0
-  # Recreate: the qcow2 disk is RWO and a second pod must never attach it
-  # concurrently — two QEMU processes on one image corrupts it.
-  strategy:
-    type: Recreate
-  selector:
-    matchLabels:
-      app.kubernetes.io/name: macos-bluebubbles
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: macos-bluebubbles
-        app.kubernetes.io/part-of: sms
-    spec:
-      # Dedicated node. The taint keeps everything else off worker-2; this
-      # toleration is what lets the VM on. Both halves are required.
-      nodeSelector:
-        workload: imessage
-      tolerations:
-        - key: workload
-          operator: Equal
-          value: imessage
-          effect: NoSchedule
-      containers:
-        - name: macos
-          image: sickcodes/docker-osx:latest@sha256:3a3c82c79bc4e73531f819ccdfa4053b3084efd7c1f645678dbf8b4b3a24369c
-          # QEMU needs /dev/kvm; Talos enforces `baseline` cluster-wide, so this
-          # only schedules because the sms namespace is labelled privileged.
-          securityContext:
-            privileged: true
-          env:
-            # Generates a unique serial / board-serial / UUID / MAC and persists
-            # them to bootdisk.qcow2. This synthetic identity is what iMessage
-            # activates against — it must stay stable across restarts, which is
-            # why the PVC matters.
-            - name: GENERATE_UNIQUE
-              value: "true"
-            # Identity is only plausible if it matches a real product line.
-            - name: DEVICE_MODEL
-              value: "iMacPro1,1"
-            - name: RAM
-              value: "12"
-            - name: CORES
-              value: "6"
-            - name: EXTRA
-              # Expose the BlueBubbles server port from the guest to the pod.
-              # Guest :1234 (BlueBubbles default) -> pod :1234.
-              value: "-device virtio-net-pci,netdev=net0 -netdev user,id=net0,hostfwd=tcp::1234-:1234"
-          ports:
-            - name: vnc
-              containerPort: 5999
-              protocol: TCP
-            - name: bluebubbles
-              containerPort: 1234
-              protocol: TCP
-          resources:
-            requests:
-              cpu: "6"
-              memory: 14Gi
-            limits:
-              cpu: "12"
-              memory: 20Gi
-          volumeMounts:
-            - name: macos-disk
-              mountPath: /home/arch/OSX-KVM/disk
-            - name: kvm
-              mountPath: /dev/kvm
-          # No readiness probe on purpose. The guest takes many minutes to boot,
-          # and until macOS + BlueBubbles are installed BY HAND there is nothing
-          # listening on 1234. A probe here would crash-loop the pod through the
-          # entire interactive install.
-      volumes:
-        - name: macos-disk
-          persistentVolumeClaim:
-            claimName: macos-disk
-        - name: kvm
-          hostPath:
-            path: /dev/kvm
-            type: CharDevice

k8s/apps/sms/kustomization.yaml

@@ -1,10 +0,0 @@
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-namespace: sms
-resources:
-  - namespace.yaml
-  - storageclass.yaml
-  - pvc-macos.yaml
-  - deployment-macos.yaml
-  - service.yaml
-  - networkpolicy.yaml

k8s/apps/sms/namespace.yaml

@@ -1,19 +0,0 @@
-# iMessage delivery for the cluster.
-#
-# BlueBubbles' server is a macOS Electron app paired with an Objective-C helper
-# that hooks Messages.app private APIs — it cannot be containerised on Linux,
-# because containers share the host kernel and macOS needs XNU + Cocoa. The only
-# way to run it on Talos is a full macOS VM under QEMU/KVM (Docker-OSX), which
-# needs a privileged pod with /dev/kvm.
-#
-# Hence privileged PodSecurity: the cluster default from the Talos controlplane
-# is `enforce: baseline`, which forbids privileged containers and host devices.
-# Scope is limited to this namespace.
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: sms
-  labels:
-    pod-security.kubernetes.io/enforce: privileged
-    pod-security.kubernetes.io/audit: privileged
-    pod-security.kubernetes.io/warn: privileged

k8s/apps/sms/networkpolicy.yaml

@@ -1,22 +0,0 @@
-# Default-deny. This namespace runs a privileged QEMU VM signed into an Apple
-# ID and exposes an unauthenticated VNC console; nothing should reach it except
-# opted-in clients.
-apiVersion: networking.k8s.io/v1
-kind: NetworkPolicy
-metadata:
-  name: sms-default-deny
-spec:
-  podSelector:
-    matchLabels:
-      app.kubernetes.io/part-of: sms
-  policyTypes:
-    - Ingress
-  ingress:
-    - from:
-        - namespaceSelector: {}
-          podSelector:
-            matchLabels:
-              sms-client: "true"
-      ports:
-        - protocol: TCP
-          port: 1234

k8s/apps/sms/pvc-macos.yaml

@@ -1,25 +0,0 @@
-# Persistent macOS disk image + generated hardware identity (bootdisk.qcow2).
-#
-# This volume is NOT disposable: it holds the VM's serial number, board serial,
-# UUID and MAC, which together form the identity iMessage was activated against.
-# Losing it means re-running activation, which is the least reliable step of the
-# whole setup.
-#
-# Docker-OSX documents 128GB minimum for the guest image; 200Gi leaves room for
-# the installer, the base system, and qcow2 growth.
-#
-# ⚠️ Single replica (see storageclass.yaml — capacity and IO both rule out 3).
-# Losing worker-2's disk therefore means losing the activated identity and
-# redoing iMessage activation. Once the guest is installed and activated, take
-# a Longhorn snapshot/backup of this volume; that is the only redundancy here.
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: macos-disk
-spec:
-  accessModes:
-    - ReadWriteOnce
-  storageClassName: longhorn-imessage-local
-  resources:
-    requests:
-      storage: 200Gi

k8s/apps/sms/service.yaml

@@ -1,31 +0,0 @@
-# VNC is how you drive the interactive macOS install. Deliberately ClusterIP —
-# it is an unauthenticated console onto a machine holding a live Apple ID
-# session. Reach it with `kubectl port-forward`, never an Ingress.
-apiVersion: v1
-kind: Service
-metadata:
-  name: macos-vnc
-spec:
-  type: ClusterIP
-  selector:
-    app.kubernetes.io/name: macos-bluebubbles
-  ports:
-    - name: vnc
-      port: 5999
-      targetPort: vnc
----
-# The BlueBubbles REST API, once installed inside the guest. This is the stable
-# name cluster services use, so callers never depend on the pod IP or on whether
-# the backend is this VM or a real Mac mini later.
-apiVersion: v1
-kind: Service
-metadata:
-  name: bluebubbles
-spec:
-  type: ClusterIP
-  selector:
-    app.kubernetes.io/name: macos-bluebubbles
-  ports:
-    - name: http
-      port: 1234
-      targetPort: bluebubbles

k8s/apps/sms/storageclass.yaml

@@ -1,32 +0,0 @@
-# Dedicated StorageClass for the macOS VM disk.
-#
-# The default `longhorn` class does not work here, for two independent reasons:
-#
-# 1. Replica count. Default is 3, and Longhorn schedules against
-#    storageMaximum - storageScheduled with over-provisioning at 100%. Free
-#    space is cp-1 146Gi / cp-2 8Gi / cp-3 146Gi / worker-1 292Gi, so a 200Gi
-#    volume has only one node that can hold even a single replica — a 3-replica
-#    volume fails outright with ReplicaSchedulingFailure.
-# 2. Binding mode. `Immediate` provisions the volume the moment the PVC is
-#    created, before any pod is scheduled. Combined with strict-local that
-#    pins the data to an arbitrary node, not the one the VM runs on.
-#
-# So: one replica, kept local to the VM, bound only once the pod has a node.
-apiVersion: storage.k8s.io/v1
-kind: StorageClass
-metadata:
-  name: longhorn-imessage-local
-provisioner: driver.longhorn.io
-allowVolumeExpansion: true
-reclaimPolicy: Delete
-# The pod is pinned to worker-2 by nodeSelector; wait for it to be scheduled so
-# the replica is placed on that node and not somewhere else.
-volumeBindingMode: WaitForFirstConsumer
-parameters:
-  # A qcow2 backing a live VM is latency-sensitive and rewritten constantly.
-  # Serving it over the network from another node's disk would be the single
-  # worst thing for guest responsiveness, so force it local.
-  numberOfReplicas: "1"
-  dataLocality: "strict-local"
-  staleReplicaTimeout: "30"
-  fsType: "ext4"

k8s/argocd/apps/60-applications.yaml

@@ -110,37 +110,6 @@ spec:
     syncOptions:
       - CreateNamespace=true
 ---
-# iMessage/SMS delivery. Raw manifests: a privileged macOS VM (Docker-OSX)
-# running the BlueBubbles server, plus its dedicated local StorageClass.
-#
-# Pinned to worker-2 via nodeSelector `workload: imessage` + a matching
-# toleration for that node's taint. Until worker-2 is provisioned this app
-# syncs everything except the pod, which stays Pending — that is expected.
-#
-# No CreateNamespace: namespace.yaml carries `pod-security: privileged`, which
-# the VM needs (/dev/kvm, privileged), and an ArgoCD-created namespace would
-# not have those labels.
-apiVersion: argoproj.io/v1alpha1
-kind: Application
-metadata:
-  name: sms
-  namespace: argocd
-  annotations:
-    argocd.argoproj.io/sync-wave: "8"
-spec:
-  project: homelab
-  source:
-    repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/homelab.git
-    targetRevision: main
-    path: k8s/apps/sms
-  destination:
-    server: https://kubernetes.default.svc
-    namespace: sms
-  syncPolicy:
-    automated:
-      prune: true
-      selfHeal: true
----
 # Document management. Raw manifests (no Helm): postgres is the dedicated
 # paperless-db CNPG cluster in k8s/infra/databases (wave 2), redis is
 # in-cluster only (no PVC), media lives on the cp-3 USB HDD (see

k8s/infra/monitoring/prometheus-values.yaml

@@ -55,7 +55,10 @@ alertmanager:
 prometheus:
   prometheusSpec:
     retention: 30d
-    retentionSize: "95GB"
+    # Must stay under the PVC size below (25Gi). At 95GB the limit never
+    # triggered, the volume filled, and Prometheus crashlooped with
+    # "no space left on device" writing /prometheus/queries.active.
+    retentionSize: "18GB"
 
     # scrapeTimeout MUST be <= scrapeInterval or the operator refuses to generate
     # the Prometheus config ("scrapeTimeout greater than scrapeInterval") and no