monitoring: disable wait on node-exporter

Reviewed-on: #2

.gitignore

@@ -0,0 +1 @@
+AGENTS.md

clusters/atlas/applications/kustomization.yaml

@@ -0,0 +1,12 @@
+# clusters/atlas/applications/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - ../../services/crypto
+  - ../../services/gitea
+  - ../../services/jellyfin
+  - ../../services/jitsi
+  - ../../services/monitoring
+  - ../../services/pegasus
+  - ../../services/vault
+  - ../../services/zot

clusters/atlas/flux-system/applications/crypto/kustomization.yaml

@@ -1,4 +1,4 @@
-# infrastructure/flux-system/kustomization-crypto.yaml
+# clusters/atlas/flux-system/applications/crypto/kustomization.yaml
 apiVersion: kustomize.toolkit.fluxcd.io/v1
 kind: Kustomization
 metadata:

clusters/atlas/flux-system/applications/gitea/kustomization.yaml

@@ -1,4 +1,4 @@
-# infrastructure/flux-system/kustomization-gitea.yaml
+# clusters/atlas/flux-system/applications/gitea/kustomization.yaml
 apiVersion: kustomize.toolkit.fluxcd.io/v1beta2
 kind: Kustomization
 metadata:

clusters/atlas/flux-system/applications/jellyfin/kustomization.yaml

@@ -1,4 +1,4 @@
-# infrastructure/flux-system/kustomization-jellyfin.yaml
+# clusters/atlas/flux-system/applications/jellyfin/kustomization.yaml
 apiVersion: kustomize.toolkit.fluxcd.io/v1
 kind: Kustomization
 metadata:

clusters/atlas/flux-system/applications/jitsi/kustomization.yaml

@@ -0,0 +1,19 @@
+# clusters/atlas/flux-system/applications/jitsi/kustomization.yaml
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: jitsi
+  namespace: flux-system
+spec:
+  interval: 10m
+  path: ./services/jitsi
+  targetNamespace: jitsi
+  prune: true
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+    namespace: flux-system
+  dependsOn:
+    - name: core
+  wait: true
+  timeout: 5m

clusters/atlas/flux-system/applications/kustomization.yaml

@@ -0,0 +1,15 @@
+# clusters/atlas/flux-system/applications/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - zot/kustomization.yaml
+  - gitea/kustomization.yaml
+  - vault/kustomization.yaml
+  - jitsi/kustomization.yaml
+  - crypto/kustomization.yaml
+  - monerod/kustomization.yaml
+  - pegasus/kustomization.yaml
+  - pegasus/image-automation.yaml
+  - jellyfin/kustomization.yaml
+  - xmr-miner/kustomization.yaml
+  - sui-metrics/kustomization.yaml

clusters/atlas/flux-system/applications/monerod/kustomization.yaml

@@ -1,4 +1,4 @@
-# infrastructure/flux-system/kustomization-monerod.yaml
+# clusters/atlas/flux-system/applications/monerod/kustomization.yaml
 apiVersion: kustomize.toolkit.fluxcd.io/v1
 kind: Kustomization
 metadata:

clusters/atlas/flux-system/applications/pegasus/image-automation.yaml

@@ -0,0 +1,20 @@
+# clusters/atlas/flux-system/applications/pegasus/image-automation.yaml
+apiVersion: image.toolkit.fluxcd.io/v1beta1
+kind: ImageUpdateAutomation
+metadata:
+  name: pegasus
+  namespace: flux-system
+spec:
+  interval: 1m0s
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+  git:
+    commit:
+      author:
+        email: ops@bstein.dev
+        name: flux-bot
+      messageTemplate: "chore(pegasus): update image to {{range .Updated.Images}}{{.}}{{end}}"
+  update:
+    strategy: Setters
+    path: ./services/pegasus

clusters/atlas/flux-system/applications/pegasus/kustomization.yaml

@@ -0,0 +1,19 @@
+# clusters/atlas/flux-system/applications/pegasus/kustomization.yaml
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: pegasus
+  namespace: flux-system
+spec:
+  interval: 10m
+  path: ./services/pegasus
+  targetNamespace: jellyfin
+  prune: true
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+    namespace: flux-system
+  dependsOn:
+    - name: core
+  wait: true
+  timeout: 5m

clusters/atlas/flux-system/applications/sui-metrics/kustomization.yaml

@@ -0,0 +1,19 @@
+# clusters/atlas/flux-system/applications/sui-metrics/kustomization.yaml
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: sui-metrics
+  namespace: flux-system
+spec:
+  interval: 10m
+  path: ./services/sui-metrics/overlays/atlas
+  prune: true
+  dependsOn:
+    - name: monitoring
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+    namespace: flux-system
+  wait: true
+  timeout: 5m
+  targetNamespace: sui-metrics

clusters/atlas/flux-system/applications/vault/kustomization.yaml

@@ -1,4 +1,4 @@
-# infrastructure/flux-system/kustomization-vault.yaml
+# clusters/atlas/flux-system/applications/vault/kustomization.yaml
 apiVersion: kustomize.toolkit.fluxcd.io/v1
 kind: Kustomization
 metadata:

clusters/atlas/flux-system/applications/xmr-miner/kustomization.yaml

@@ -1,4 +1,4 @@
-# infrastructure/flux-system/kustomization-core.yaml
+# clusters/atlas/flux-system/applications/xmr-miner/kustomization.yaml
 apiVersion: kustomize.toolkit.fluxcd.io/v1
 kind: Kustomization
 metadata:

clusters/atlas/flux-system/applications/zot/kustomization.yaml

@@ -1,4 +1,4 @@
-# infrastructure/flux-system/kustomization-zot.yaml
+# clusters/atlas/flux-system/applications/zot/kustomization.yaml
 apiVersion: kustomize.toolkit.fluxcd.io/v1
 kind: Kustomization
 metadata:

clusters/atlas/flux-system/gotk-components.yaml

@@ -1,6 +1,6 @@
 ---
 # This manifest was generated by flux. DO NOT EDIT.
-# Flux Version: v2.5.1
+# Flux Version: v2.5.1f reconzaq1=  zaq1= aq1=  1=  w2cile kustomization flux-system --namespace flux-system --with-source
 # Components: source-controller,kustomize-controller,helm-controller,notification-controller
 apiVersion: v1
 kind: Namespace

clusters/atlas/flux-system/gotk-sync.yaml

@@ -8,7 +8,7 @@ metadata:
 spec:
   interval: 1m0s
   ref:
-    branch: main
+    branch: restructure/hybrid-clusters
   secretRef:
     name: flux-system-gitea
   url: ssh://git@scm.bstein.dev:2242/bstein/titan-iac.git
@@ -20,7 +20,7 @@ metadata:
   namespace: flux-system
 spec:
   interval: 10m0s
-  path: ./
+  path: ./clusters/atlas/flux-system
   prune: true
   sourceRef:
     kind: GitRepository

clusters/atlas/flux-system/kustomization.yaml

@@ -0,0 +1,8 @@
+# clusters/atlas/flux-system/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - gotk-components.yaml
+  - gotk-sync.yaml
+  - platform
+  - applications

clusters/atlas/flux-system/platform/core/kustomization.yaml

@@ -0,0 +1,15 @@
+# clusters/atlas/flux-system/platform/core/kustomization.yaml
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: core
+  namespace: flux-system
+spec:
+  interval: 10m
+  path: ./infrastructure/core
+  prune: true
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+    namespace: flux-system
+  wait: false

clusters/atlas/flux-system/platform/helm/kustomization.yaml

@@ -1,4 +1,4 @@
-# infrastructure/flux-system/kustomization-helm.yaml
+# clusters/atlas/flux-system/platform/helm/kustomization.yaml
 apiVersion: kustomize.toolkit.fluxcd.io/v1
 kind: Kustomization
 metadata:

clusters/atlas/flux-system/platform/kustomization.yaml

@@ -0,0 +1,9 @@
+# clusters/atlas/flux-system/platform/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - core/kustomization.yaml
+  - helm/kustomization.yaml
+  - traefik/kustomization.yaml
+  - monitoring/kustomization.yaml
+  - longhorn-ui/kustomization.yaml

clusters/atlas/flux-system/platform/longhorn-ui/kustomization.yaml

@@ -1,3 +1,4 @@
+# clusters/atlas/flux-system/platform/longhorn-ui/kustomization.yaml
 apiVersion: kustomize.toolkit.fluxcd.io/v1
 kind: Kustomization
 metadata:

clusters/atlas/flux-system/platform/monitoring/kustomization.yaml

@@ -0,0 +1,14 @@
+# clusters/atlas/flux-system/platform/monitoring/kustomization.yaml
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: monitoring
+  namespace: flux-system
+spec:
+  interval: 10m
+  path: ./services/monitoring
+  prune: true
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+  wait: true

clusters/atlas/flux-system/platform/traefik/kustomization.yaml

@@ -0,0 +1,18 @@
+# clusters/atlas/flux-system/platform/traefik/kustomization.yaml
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: traefik
+  namespace: flux-system
+spec:
+  interval: 10m
+  path: ./infrastructure/traefik
+  targetNamespace: traefik
+  prune: true
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+    namespace: flux-system
+  dependsOn:
+    - name: core
+  wait: true

clusters/atlas/platform/kustomization.yaml

@@ -0,0 +1,7 @@
+# clusters/atlas/platform/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - ../../../infrastructure/modules/base
+  - ../../../infrastructure/modules/profiles/atlas-ha
+  - ../../../infrastructure/sources/cert-manager/letsencrypt.yaml

clusters/oceanus/README.md

@@ -0,0 +1,5 @@
+# Oceanus Cluster Scaffold
+
+This directory prepares the Flux and Kustomize layout for a future Oceanus-managed cluster.
+Populate `flux-system/` with `gotk-components.yaml` and related manifests after running `flux bootstrap`.
+Define node-specific resources under `infrastructure/modules/profiles/oceanus-validator/` and reference workloads in `applications/` as they come online.

clusters/oceanus/applications/kustomization.yaml

@@ -0,0 +1,4 @@
+# clusters/oceanus/applications/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources: []

clusters/oceanus/flux-system/kustomization.yaml

@@ -0,0 +1,9 @@
+# clusters/oceanus/flux-system/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  # Populate when oceanus cluster is bootstrapped with Flux.
+  # - gotk-components.yaml
+  # - gotk-sync.yaml
+  - ../platform
+  - ../applications

clusters/oceanus/platform/kustomization.yaml

@@ -0,0 +1,6 @@
+# clusters/oceanus/platform/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - ../../infrastructure/modules/base
+  - ../../infrastructure/modules/profiles/oceanus-validator

docs/topology.md

@@ -0,0 +1,16 @@
+# Titan Homelab Topology
+
+| Hostname   | Role / Function                | Managed By          | Notes |
+|------------|--------------------------------|---------------------|-------|
+| titan-0a   | Kubernetes control-plane       | Flux (atlas cluster)| HA leader, tainted for control only |
+| titan-0b   | Kubernetes control-plane       | Flux (atlas cluster)| Standby control node |
+| titan-0c   | Kubernetes control-plane       | Flux (atlas cluster)| Standby control node |
+| titan-04-19| Raspberry Pi workers           | Flux (atlas cluster)| Workload nodes, labelled per hardware |
+| titan-22   | GPU mini-PC (Jellyfin)         | Flux + Ansible      | NVIDIA runtime managed via `modules/profiles/atlas-ha` |
+| titan-24   | Tethys hybrid node             | Flux + Ansible      | Runs SUI metrics via K8s, validator via Ansible |
+| titan-db   | HA control plane database      | Ansible             | PostgreSQL / etcd backing services |
+| titan-jh   | Jumphost & bastion             | Ansible             | Entry point / future KVM services |
+| oceanus    | Dedicated SUI validator host   | Ansible / Flux prep | Baremetal validator workloads, exposes metrics to atlas; Kustomize scaffold under `clusters/oceanus/` |
+| styx       | Air-gapped workstation         | Manual / Scripts    | Remains isolated, scripts tracked in `hosts/styx` |
+
+Use the `clusters/` directory for cluster-scoped state and the `hosts/` directory for baremetal orchestration.

hosts/group_vars/all.yaml

@@ -0,0 +1,2 @@
+# hosts/group_vars/all.yaml
+validator_version: latest

hosts/host_vars/titan-24.yaml

@@ -0,0 +1,2 @@
+# hosts/host_vars/titan-24.yaml
+validator_compose_path: /opt/sui-validator

hosts/inventory/lab.yaml

@@ -0,0 +1,28 @@
+# hosts/inventory/lab.yaml
+# Replace ansible_host and ansible_user values with real connectivity details.
+all:
+  children:
+    atlas:
+      hosts:
+        titan-24:
+          ansible_host: REPLACE_ME
+          ansible_user: ubuntu
+          roleset: tethys_hybrid
+        titan-22:
+          ansible_host: REPLACE_ME
+          ansible_user: debian
+          roleset: minipc_gpu
+    baremetal:
+      hosts:
+        titan-db:
+          ansible_host: REPLACE_ME
+          ansible_user: postgres
+          roleset: database
+        titan-jh:
+          ansible_host: REPLACE_ME
+          ansible_user: jump
+          roleset: jumphost
+        oceanus:
+          ansible_host: REPLACE_ME
+          ansible_user: validator
+          roleset: validator

hosts/playbooks/site.yaml

@@ -0,0 +1,29 @@
+# hosts/playbooks/site.yaml
+---
+- name: Configure titan-db
+  hosts: titan-db
+  gather_facts: true
+  roles:
+    - common
+    - titan_db
+
+- name: Configure titan-jh
+  hosts: titan-jh
+  gather_facts: true
+  roles:
+    - common
+    - titan_jh
+
+- name: Configure oceanus validator host
+  hosts: oceanus
+  gather_facts: true
+  roles:
+    - common
+    - oceanus_base
+
+- name: Prepare hybrid tethys node
+  hosts: titan-24
+  gather_facts: true
+  roles:
+    - common
+    - tethys_canary

hosts/roles/common/tasks/main.yaml

@@ -0,0 +1,9 @@
+# hosts/roles/common/tasks/main.yaml
+---
+- name: Ensure base packages present
+  ansible.builtin.package:
+    name:
+      - curl
+      - vim
+    state: present
+  tags: ['common', 'packages']

hosts/roles/oceanus_base/tasks/main.yaml

@@ -0,0 +1,6 @@
+# hosts/roles/oceanus_base/tasks/main.yaml
+---
+- name: Placeholder for oceanus base configuration
+  ansible.builtin.debug:
+    msg: "Install validator prerequisites and monitoring exporters here."
+  tags: ['oceanus']

hosts/roles/tethys_canary/tasks/main.yaml

@@ -0,0 +1,6 @@
+# hosts/roles/tethys_canary/tasks/main.yaml
+---
+- name: Placeholder for SUI validator container runtime setup
+  ansible.builtin.debug:
+    msg: "Configure container runtime and validator compose stack here."
+  tags: ['tethys', 'validator']

hosts/roles/titan_db/tasks/main.yaml

@@ -0,0 +1,6 @@
+# hosts/roles/titan_db/tasks/main.yaml
+---
+- name: Placeholder for titan-db provisioning
+  ansible.builtin.debug:
+    msg: "Install database packages, configure backups, and manage users here."
+  tags: ['titan_db']

hosts/roles/titan_jh/tasks/main.yaml

@@ -0,0 +1,6 @@
+# hosts/roles/titan_jh/tasks/main.yaml
+---
+- name: Placeholder for jumphost hardening
+  ansible.builtin.debug:
+    msg: "Harden SSH, manage bastion tooling, and configure audit logging here."
+  tags: ['jumphost']

hosts/styx/README.md

@@ -0,0 +1,2 @@
+# hosts/styx/README.md
+Styx is air-gapped; provisioning scripts live under `scripts/`.

infrastructure/core/gpu/profiles/jetson-only/kustomization.yaml

@@ -1,5 +0,0 @@
-# infrastructure/core/gpu/daemonsets/profiles/jetson-only/kustomization.yaml
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-resources:
-  - ../../device-plugin-jetson

infrastructure/core/gpu/profiles/minipc-and-jetson/kustomization.yaml

@@ -1,6 +0,0 @@
-# infrastructure/core/gpu/daemonsets/profiles/minipc-and-jetson/kustomization.yaml
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-resources:
-  - ../../device-plugin-minipc
-  - ../../device-plugin-jetson

infrastructure/core/gpu/profiles/minipc-only/kustomization.yaml

@@ -1,5 +0,0 @@
-# infrastructure/core/gpu/daemonsets/profiles/minipc-only/kustomization.yaml
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-resources:
-  - ../../device-plugin-minipc

infrastructure/core/kustomization.yaml

@@ -2,7 +2,6 @@
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:
-  - base
+  - ../modules/base
-  # - gpu/profiles/jetson-only 
+  - ../modules/profiles/atlas-ha
-  # - gpu/profiles/minipc-and-jetson
+  - ../sources/cert-manager/letsencrypt.yaml
-  - gpu/profiles/minipc-only 

infrastructure/flux-system/kustomization-core.yaml

@@ -1,22 +0,0 @@
-# infrastructure/flux-system/kustomization-core.yaml
-apiVersion: kustomize.toolkit.fluxcd.io/v1
-kind: Kustomization
-metadata:
-  name: core
-  namespace: flux-system
-spec:
-  interval: 10m
-  path: ./infrastructure/core
-  prune: true
-  sourceRef:
-    kind: GitRepository
-    name: flux-system
-    namespace: flux-system
-  wait: true
-
-  # Only wait for the NVIDIA device-plugin DaemonSet on titan-22
-  healthChecks:
-    - apiVersion: apps/v1
-      kind: DaemonSet
-      name: nvidia-device-plugin-minipc
-      namespace: kube-system

infrastructure/flux-system/kustomization.yaml

@@ -2,15 +2,4 @@
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:
-- gotk-components.yaml
+  - ../clusters/atlas/flux-system
-- gotk-sync.yaml
-- kustomization-zot.yaml
-- kustomization-core.yaml
-- kustomization-helm.yaml
-- kustomization-gitea.yaml
-- kustomization-vault.yaml
-- kustomization-crypto.yaml
-- kustomization-monerod.yaml
-- kustomization-jellyfin.yaml
-- kustomization-xmr-miner.yaml
-- kustomization-longhorn-ui.yaml

infrastructure/modules/base/kustomization.yaml

@@ -1,4 +1,4 @@
-# infrastructure/core/base/kustomization.yaml
+# infrastructure/modules/base/kustomization.yaml
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:

infrastructure/modules/base/priorityclass/kustomization.yaml

@@ -1,4 +1,4 @@
-# infrastructure/core/base/priorityclass/kustomization.yaml
+# infrastructure/modules/base/priorityclass/kustomization.yaml
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:

infrastructure/modules/base/priorityclass/scavenger.yaml

@@ -1,4 +1,4 @@
-# infrastructure/core/base/priorityclass/scavenger.yaml
+# infrastructure/modules/base/priorityclass/scavenger.yaml
 apiVersion: scheduling.k8s.io/v1
 kind: PriorityClass
 metadata:

infrastructure/modules/base/runtimeclass/kustomization.yaml

@@ -1,4 +1,4 @@
-# infrastructure/core/base/storageclass/kustomization.yaml
+# infrastructure/modules/base/runtimeclass/kustomization.yaml
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:

infrastructure/modules/base/runtimeclass/runtimeclass.yaml

@@ -1,4 +1,4 @@
-# services/jellyfin/runtimeclass.yaml
+# infrastructure/modules/base/runtimeclass/runtimeclass.yaml
 apiVersion: node.k8s.io/v1
 kind: RuntimeClass
 metadata:

infrastructure/modules/base/storageclass/asteria.yaml

@@ -1,4 +1,4 @@
-# infrastructure/core/base/storageclass/asteria.yaml
+# infrastructure/modules/base/storageclass/asteria.yaml
 apiVersion: storage.k8s.io/v1
 kind: StorageClass
 metadata:
@@ -8,6 +8,9 @@ parameters:
   fromBackup: ""
   numberOfReplicas: "2"
   staleReplicaTimeout: "30"
+  fsType: "ext4"
+  replicaAutoBalance: "least-effort"
+  dataLocality: "disabled"
 provisioner: driver.longhorn.io
 reclaimPolicy: Retain
 allowVolumeExpansion: true

infrastructure/modules/base/storageclass/astreae.yaml

@@ -1,4 +1,4 @@
-# infrastructure/core/base/storageclass/astreae.yaml
+# infrastructure/modules/base/storageclass/astreae.yaml
 apiVersion: storage.k8s.io/v1
 kind: StorageClass
 metadata:

infrastructure/modules/base/storageclass/kustomization.yaml

@@ -1,4 +1,4 @@
-# infrastructure/core/base/storageclass/kustomization.yaml
+# infrastructure/modules/base/storageclass/kustomization.yaml
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:

infrastructure/modules/profiles/atlas-ha/kustomization.yaml

@@ -0,0 +1,7 @@
+# infrastructure/modules/profiles/atlas-ha/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - ../components/device-plugin-jetson
+  - ../components/device-plugin-minipc
+  - ../components/device-plugin-tethys

infrastructure/modules/profiles/components/device-plugin-jetson/daemonset.yaml

@@ -1,4 +1,4 @@
-# infrastructure/core/gpu/daemonsets/device-plugin-jetson/daemonset.yaml
+# infrastructure/modules/profiles/components/device-plugin-jetson/daemonset.yaml
 apiVersion: apps/v1
 kind: DaemonSet
 metadata:

infrastructure/modules/profiles/components/device-plugin-jetson/kustomization.yaml

@@ -1,4 +1,4 @@
-# infrastructure/core/gpu/daemonsets/device-plugin-jetson/kustomization.yaml
+# infrastructure/modules/profiles/components/device-plugin-jetson/kustomization.yaml
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources: 

infrastructure/modules/profiles/components/device-plugin-minipc/daemonset.yaml

@@ -1,4 +1,4 @@
-# infrastructure/core/gpu/daemonsets/device-plugin-minipc/daemonset.yaml
+# infrastructure/modules/profiles/components/device-plugin-minipc/daemonset.yaml
 apiVersion: apps/v1
 kind: DaemonSet
 metadata:
@@ -24,7 +24,6 @@ spec:
       tolerations:
         - operator: Exists
       priorityClassName: system-node-critical
-      runtimeClassName: nvidia
       containers:
         - name: nvidia-device-plugin-ctr
           image: nvcr.io/nvidia/k8s-device-plugin:v0.16.2

infrastructure/modules/profiles/components/device-plugin-minipc/kustomization.yaml

@@ -1,4 +1,4 @@
-# infrastructure/core/gpu/daemonsets/device-plugin-minipc/kustomization.yaml
+# infrastructure/modules/profiles/components/device-plugin-minipc/kustomization.yaml
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources: 

infrastructure/modules/profiles/components/device-plugin-tethys/daemonset.yaml

@@ -0,0 +1,49 @@
+# infrastructure/modules/profiles/components/device-plugin-tethys/daemonset.yaml
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: nvidia-device-plugin-tethys
+  namespace: kube-system
+  labels:
+    app.kubernetes.io/name: nvidia-device-plugin
+    app.kubernetes.io/instance: titan24
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: nvidia-device-plugin
+      app.kubernetes.io/instance: titan24
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: nvidia-device-plugin
+        app.kubernetes.io/instance: titan24
+    spec:
+      nodeSelector:
+        kubernetes.io/hostname: titan-24
+        kubernetes.io/arch: amd64
+      tolerations:
+        - operator: Exists
+      priorityClassName: system-node-critical
+      runtimeClassName: nvidia
+      containers:
+        - name: nvidia-device-plugin-ctr
+          image: nvcr.io/nvidia/k8s-device-plugin:v0.16.2
+          imagePullPolicy: IfNotPresent
+          args:
+            - "--fail-on-init-error=false"
+            - "--device-list-strategy=envvar"
+            - "--mig-strategy=none"
+          securityContext:
+            privileged: true
+          env:
+            - name: NVIDIA_VISIBLE_DEVICES
+              value: "all"
+            - name: NVIDIA_DRIVER_CAPABILITIES
+              value: "compute,video,utility"
+          volumeMounts:
+            - name: device-plugin
+              mountPath: /var/lib/kubelet/device-plugins
+      volumes:
+        - name: device-plugin
+          hostPath:
+            path: /var/lib/kubelet/device-plugins

infrastructure/modules/profiles/components/device-plugin-tethys/kustomization.yaml

@@ -0,0 +1,5 @@
+# infrastructure/modules/profiles/components/device-plugin-tethys/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - daemonset.yaml

infrastructure/modules/profiles/oceanus-validator/kustomization.yaml

@@ -0,0 +1,4 @@
+# infrastructure/modules/profiles/oceanus-validator/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources: []

infrastructure/modules/profiles/tethys-hybrid/kustomization.yaml

@@ -0,0 +1,5 @@
+# infrastructure/modules/profiles/tethys-hybrid/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - ../components/device-plugin-tethys

infrastructure/sources/cert-manager/letsencrypt.yaml

@@ -4,7 +4,7 @@ metadata:
   name: letsencrypt
 spec:
   acme:
-    email: you@bstein.dev
+    email: brad.stein@gmail.com
     server: https://acme-v02.api.letsencrypt.org/directory
     privateKeySecretRef:
       name: letsencrypt-account-key

infrastructure/sources/helm/grafana.yaml

@@ -1,3 +1,4 @@
+# infrastructure/sources/helm/grafana.yaml
 apiVersion: source.toolkit.fluxcd.io/v1
 kind: HelmRepository
 metadata:

infrastructure/sources/helm/hashicorp.yaml

@@ -1,3 +1,4 @@
+# infrastructure/sources/helm/hashicorp.yaml
 apiVersion: source.toolkit.fluxcd.io/v1
 kind: HelmRepository
 metadata:

infrastructure/sources/helm/jetstack.yaml

@@ -1,3 +1,4 @@
+# infrastructure/sources/helm/jetstack.yaml
 apiVersion: source.toolkit.fluxcd.io/v1
 kind: HelmRepository
 metadata:

infrastructure/sources/helm/prometheus.yaml

@@ -1,3 +1,4 @@
+# infrastructure/sources/helm/prometheus.yaml
 apiVersion: source.toolkit.fluxcd.io/v1
 kind: HelmRepository
 metadata:

infrastructure/sources/helm/victoria-metrics.yaml

@@ -0,0 +1,9 @@
+# infrastructure/sources/helm/victoria-metrics.yaml
+apiVersion: source.toolkit.fluxcd.io/v1
+kind: HelmRepository
+metadata:
+  name: victoria-metrics
+  namespace: flux-system
+spec:
+  interval: 1h
+  url: https://victoriametrics.github.io/helm-charts/

infrastructure/traefik/deployment.yaml

@@ -35,6 +35,12 @@ items:
           - --entrypoints.web.address=:80
           - --entrypoints.websecure.address=:443
           - --api.dashboard=true
+          - --metrics.prometheus=true
+          - --metrics.prometheus.addEntryPointsLabels=true
+          - --metrics.prometheus.addRoutersLabels=true
+          - --metrics.prometheus.addServicesLabels=true
+          - --entrypoints.metrics.address=:9100
+          - --metrics.prometheus.entryPoint=metrics
           image: traefik:v3.3.3
           imagePullPolicy: IfNotPresent
           name: traefik
@@ -48,6 +54,9 @@ items:
           - containerPort: 8080
             name: admin
             protocol: TCP
+          - containerPort: 9100
+            name: metrics
+            protocol: TCP
           terminationMessagePath: /dev/termination-log
           terminationMessagePolicy: File
         dnsPolicy: ClusterFirst

infrastructure/traefik/kustomization.yaml

@@ -9,3 +9,4 @@ resources:
   - serviceaccount.yaml
   - clusterrole.yaml
   - clusterrolebinding.yaml
+  - service.yaml

infrastructure/traefik/service.yaml

@@ -0,0 +1,20 @@
+# infrastructure/traefik/service.yaml
+apiVersion: v1
+kind: Service
+metadata:
+  name: traefik-metrics
+  namespace: traefik
+  labels:
+    app: traefik
+  annotations:
+    prometheus.io/scrape: "true"
+    prometheus.io/port: "9100"
+    prometheus.io/path: "/metrics"
+spec:
+  type: ClusterIP
+  selector:
+    app: traefik
+  ports:
+    - name: metrics
+      port: 9100
+      targetPort: metrics

scripts/longhorn_volume_usage.fish

@@ -1,3 +1,5 @@
+#!/usr/bin/env fish
+
 function pvc-usage --description "Show Longhorn PVC usage (human-readable) mapped to namespace/name"
   begin
     kubectl -n longhorn-system get volumes.longhorn.io -o json \

scripts/styx_kioskification.sh

@@ -0,0 +1,218 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# 0) Create dedicated user if it doesn't exist
+if ! id -u styx >/dev/null 2>&1; then
+  sudo useradd -m -s /bin/bash styx
+  echo "Created user 'styx'"
+fi
+
+# 1) App directory
+sudo mkdir -p /opt/styx-kiosk/keys
+sudo chown -R styx:styx /opt/styx-kiosk
+
+# 2) Drop the kiosk app (written below) into place
+sudo tee /opt/styx-kiosk/kiosk.py >/dev/null <<'PY'
+#!/usr/bin/env python3
+import base64, json, os, subprocess, threading, tempfile
+from datetime import datetime
+import tkinter as tk
+from tkinter import ttk, messagebox
+
+APP_TITLE = "STYX Airgap Signer"
+CAMERA_DEV = os.environ.get("ZBAR_DEV", "/dev/video0")
+KEY_PATH   = os.environ.get("STYX_KEY", "/vault/keys/signer_ed25519.pem")  # in the LUKS vault
+ALGO       = os.environ.get("STYX_ALGO", "ed25519")  # or 'secp256r1'
+QR_TMP     = "/tmp/styx_signed.png"
+
+def zbar_scan_oneshot():
+    # --raw -> data only; --nodisplay -> no preview window; --oneshot -> exit after first code
+    # (zbarcam supports --oneshot; prints one code and exits). :contentReference[oaicite:2]{index=2}
+    cmd = ["zbarcam", "--raw", "--nodisplay", "--oneshot", CAMERA_DEV]
+    try:
+        out = subprocess.check_output(cmd, text=True, timeout=30)
+        out = out.strip()
+        return out if out else None
+    except Exception as e:
+        return None
+
+def openssl_pub_der_b64(key_path):
+    der = subprocess.check_output(["openssl","pkey","-in",key_path,"-pubout","-outform","DER"])
+    return base64.b64encode(der).decode()
+
+def sign_bytes(msg: bytes, key_path: str, algo: str) -> bytes:
+    with tempfile.NamedTemporaryFile(delete=False) as f:
+        f.write(msg)
+        msg_path = f.name
+    try:
+        if algo.lower() == "ed25519":
+            # Ed25519 expects raw message; OpenSSL handles hashing internally.
+            sig = subprocess.check_output(
+                ["openssl","pkeyutl","-sign","-inkey",key_path,"-rawin","-in",msg_path]
+            )
+            return sig
+        elif algo.lower() in ("secp256r1","prime256v1","p256"):
+            # ECDSA over P-256; hash with SHA-256; OpenSSL returns DER-encoded (r,s)
+            sig = subprocess.check_output(
+                ["openssl","dgst","-sha256","-sign",key_path,msg_path]
+            )
+            return sig
+        else:
+            raise RuntimeError(f"Unsupported algo: {algo}")
+    finally:
+        try: os.unlink(msg_path)
+        except: pass
+
+def make_signed_envelope(scanned_text: str, key_path: str, algo: str) -> dict:
+    # Accept either raw string or JSON with 'tx_bytes' (base64) or 'message'
+    try:
+        obj = json.loads(scanned_text)
+        if "tx_bytes" in obj:
+            msg = base64.b64decode(obj["tx_bytes"])
+        elif "message" in obj:
+            msg = obj["message"].encode()
+        else:
+            # If it's JSON but doesn't carry known fields, sign canonical JSON bytes
+            msg = json.dumps(obj, sort_keys=True, separators=(",",":")).encode()
+        request_id = obj.get("request_id")
+    except Exception:
+        # Non-JSON → treat the scanned text as the message to sign
+        msg = scanned_text.encode()
+        request_id = None
+
+    sig = sign_bytes(msg, key_path, algo)
+    env = {
+        "algo": algo.lower(),
+        "signature_b64": base64.b64encode(sig).decode(),
+        "pubkey_spki_der_b64": openssl_pub_der_b64(key_path),
+        "payload_sha256_b64": base64.b64encode(subprocess.check_output(["openssl","dgst","-sha256","-binary"], input=msg)).decode(),
+        "quote_raw": scanned_text,
+        "request_id": request_id,
+        "device": os.uname().nodename,
+        "ts_utc": datetime.utcnow().isoformat(timespec="seconds") + "Z",
+    }
+    return env
+
+def qrencode_to_file(text: str, path: str):
+    # Use qrencode CLI to render a PNG we can display.
+    subprocess.run(["qrencode","-l","M","-s","16","-t","PNG","-o",path], input=text.encode(), check=True)
+
+class App(tk.Tk):
+    def __init__(self):
+        super().__init__()
+        self.title(APP_TITLE)
+        self.attributes("-fullscreen", True)
+        self.configure(background="black")
+        self.bind("<Escape>", lambda e: self.quit())  # for maintenance only
+
+        s = ttk.Style(self)
+        s.configure("Big.TButton", font=("DejaVu Sans", 48), padding=24)
+        s.configure("Big.TLabel",  font=("DejaVu Sans", 32), foreground="white", background="black")
+
+        self.container = tk.Frame(self, bg="black")
+        self.container.pack(expand=True, fill="both")
+
+        self.status = ttk.Label(self.container, text="Ready", style="Big.TLabel")
+        self.status.pack(pady=20)
+
+        self.scan_btn = ttk.Button(self.container, text="SCAN", style="Big.TButton", command=self.start_scan)
+        self.scan_btn.pack(pady=20)
+
+        self.image_label = tk.Label(self.container, bg="black")
+        self.image_label.pack(pady=10)
+
+        self.new_btn = ttk.Button(self.container, text="NEW SCAN", style="Big.TButton", command=self.reset)
+        self.new_btn.pack_forget()
+
+        self.note = ttk.Label(self.container, text="", style="Big.TLabel")
+        self.note.pack(pady=10)
+
+        if not os.path.exists(KEY_PATH):
+            self.status.config(text=f"Key not found at {KEY_PATH}\nInsert/unlock vault to proceed.")
+
+    def reset(self):
+        self.image_label.configure(image="")
+        self.image_label.image = None
+        self.new_btn.pack_forget()
+        self.note.config(text="")
+        self.status.config(text="Ready")
+        self.scan_btn.config(state="normal")
+
+    def start_scan(self):
+        if not os.path.exists(KEY_PATH):
+            messagebox.showerror("Key missing", f"Signing key not found at:\n{KEY_PATH}\nUnlock your vault.")
+            return
+        self.status.config(text="Scanning…")
+        self.scan_btn.config(state="disabled")
+        threading.Thread(target=self._do_scan_and_sign, daemon=True).start()
+
+    def _do_scan_and_sign(self):
+        scanned = zbar_scan_oneshot()
+        if not scanned:
+            self.after(0, self._scan_failed)
+            return
+        try:
+            envelope = make_signed_envelope(scanned, KEY_PATH, ALGO)
+            payload = json.dumps(envelope, separators=(",",":"))
+            qrencode_to_file(payload, QR_TMP)
+            self.after(0, self._show_qr, envelope)
+        except Exception as e:
+            self.after(0, lambda: self._error(str(e)))
+
+    def _scan_failed(self):
+        self.status.config(text="No QR detected. Try again.")
+        self.scan_btn.config(state="normal")
+
+    def _show_qr(self, envelope):
+        # Display the PNG produced by qrencode
+        try:
+            img = tk.PhotoImage(file=QR_TMP)
+            self.image_label.configure(image=img)
+            self.image_label.image = img
+        except Exception as e:
+            self.status.config(text=f"QR render failed: {e}")
+            self.scan_btn.config(state="normal")
+            return
+        self.status.config(text="Signed. Show this QR to your online box.")
+        self.note.config(text=f"Algo: {envelope['algo']}   Host: {envelope['device']}")
+        self.new_btn.pack(pady=20)
+
+if __name__ == "__main__":
+    App().mainloop()
+PY
+sudo chmod +x /opt/styx-kiosk/kiosk.py
+sudo chown -R styx:styx /opt/styx-kiosk
+
+# 3) Minimal X session: openbox + kiosk; no mouse pointer
+sudo -u styx tee /home/styx/.xinitrc >/dev/null <<'XRC'
+xset -dpms
+xset s off
+xset s noblank
+# If 'unclutter' is installed, uncomment the next line to hide cursor:
+# unclutter -idle 0 -root &
+openbox-session &
+/opt/styx-kiosk/kiosk.py
+XRC
+sudo chown styx:styx /home/styx/.xinitrc
+sudo chmod 0755 /home/styx/.xinitrc
+
+# 4) Autologin the 'styx' user on tty1, auto-start X
+sudo mkdir -p /etc/systemd/system/getty@tty1.service.d
+sudo tee /etc/systemd/system/getty@tty1.service.d/override.conf >/dev/null <<'OVR'
+[Service]
+ExecStart=
+ExecStart=-/sbin/agetty --autologin styx --noclear %I $TERM
+Type=idle
+OVR
+
+sudo -u styx tee -a /home/styx/.bash_profile >/dev/null <<'BRC'
+# Start X on the first tty automatically, headless
+if [ -z "$DISPLAY" ] && [ "$(tty)" = "/dev/tty1" ]; then
+  exec startx -- -nocursor
+fi
+BRC
+
+sudo systemctl daemon-reload
+sudo systemctl enable getty@tty1.service
+
+echo "Done. Reboot to try the kiosk."

scripts/styx_prep.sh

@@ -0,0 +1,195 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# === CONFIG ===
+STYX_USER="styx"
+STYX_PASS="TempPass#123"       # change at first login
+STYX_HOSTNAME="styx"
+SSH_PUBKEY=""                  # e.g., 'ssh-ed25519 AAAA... your@host' (optional)
+
+# === helpers ===
+require_root() {
+  if [[ $EUID -ne 0 ]]; then exec sudo -E "$0" "$@"; fi
+}
+
+ensure_binfmt_arm64() {
+  # If binfmt for arm64 isn't registered, register it via Docker (idempotent).
+  if [[ ! -e /proc/sys/fs/binfmt_misc/qemu-aarch64 ]]; then
+    command -v docker >/dev/null || { echo "Docker required to register binfmt (sudo pacman -S docker)"; exit 1; }
+    sudo systemctl enable --now docker >/dev/null 2>&1 || true
+    sudo docker run --rm --privileged tonistiigi/binfmt --install arm64
+  fi
+}
+
+find_parts() {
+  BOOT=$(lsblk -o LABEL,PATH -nr | awk '$1=="system-boot"{print $2}' | head -n1)
+  ROOT=$(lsblk -o LABEL,PATH -nr | awk '$1=="writable"{print $2}' | head -n1)
+  if [[ -z "${BOOT:-}" || -z "${ROOT:-}" ]]; then
+    echo "Could not find 'system-boot'/'writable' on any device."
+    lsblk -o NAME,SIZE,FSTYPE,LABEL,PATH -nr
+    exit 1
+  fi
+}
+
+mount_parts() {
+  mkdir -p /mnt/pi-boot /mnt/pi-root
+  mount "$ROOT" /mnt/pi-root
+  mount "$BOOT" /mnt/pi-boot
+
+  # Bind only what we need (avoid /run to prevent postinst fights)
+  for d in dev dev/pts proc sys; do mount --bind "/$d" "/mnt/pi-root/$d"; done
+
+  # Ubuntu images use a resolv.conf symlink—replace with a real file
+  if [[ -L /mnt/pi-root/etc/resolv.conf || ! -e /mnt/pi-root/etc/resolv.conf ]]; then
+    rm -f /mnt/pi-root/etc/resolv.conf
+    cat /etc/resolv.conf > /mnt/pi-root/etc/resolv.conf
+  fi
+}
+
+prep_chroot() {
+  # Block service starts inside chroot (no systemd there)
+  cat >/mnt/pi-root/usr/sbin/policy-rc.d <<'EOF'
+#!/bin/sh
+exit 101
+EOF
+  chmod +x /mnt/pi-root/usr/sbin/policy-rc.d
+
+  # All the work happens inside the ARM64 rootfs
+  CHCMD=$(cat <<'EOS'
+set -euo pipefail
+export DEBIAN_FRONTEND=noninteractive TZ=Etc/UTC
+# Ensure sbin is in PATH so user/group tools work
+export PATH="/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
+
+apt-get update
+apt-get -y full-upgrade
+
+# Remove snaps and keep them gone (Ubuntu for Pi ships with snaps)
+apt-get -y purge snapd || true
+rm -rf /snap /var/snap /var/lib/snapd /home/*/snap || true
+mkdir -p /etc/apt/preferences.d
+printf 'Package: snapd\nPin: release *\nPin-Priority: -10\n' > /etc/apt/preferences.d/nosnap.pref
+
+# Ensure user/group tools exist
+apt-get install -y passwd adduser || true
+getent group i2c >/dev/null || /usr/sbin/groupadd i2c
+
+# Base packages
+BASE_PKGS="openssh-server git i2c-tools python3-smbus python3-pil zbar-tools qrencode lm-sensors"
+apt-get install -y $BASE_PKGS
+
+# ------- OLED (Luma) -------
+# Prefer distro package; fall back to pip if not present in this release
+if ! dpkg -s python3-luma.oled >/dev/null 2>&1; then
+  apt-get update
+  if ! apt-get install -y python3-luma.oled; then
+    apt-get install -y python3-pip
+    pip3 install --no-input --break-system-packages luma.oled
+  fi
+fi
+
+# ------- Camera apps -------
+# Ubuntu renamed libcamera-apps -> rpicam-apps for Raspberry Pi.
+# Try in order; tolerate absence (the box might be display-only).
+apt-get update
+if ! apt-get install -y rpicam-apps; then
+  apt-get install -y libcamera-apps || apt-get install -y libcamera-tools || true
+fi
+
+# Enable SSH on boot (no systemctl in chroot)
+mkdir -p /etc/systemd/system/multi-user.target.wants
+ln -sf /lib/systemd/system/ssh.service /etc/systemd/system/multi-user.target.wants/ssh.service
+
+# Create user and set password
+if ! id -u STYX_USER >/dev/null 2>&1; then
+  /usr/sbin/useradd -m -s /bin/bash -G sudo,video,i2c STYX_USER
+fi
+echo 'STYX_USER:STYX_PASS' | /usr/sbin/chpasswd
+
+# Optional: preload SSH key
+if [ -n 'SSH_PUBKEY' ] && echo 'SSH_PUBKEY' | grep -q 'ssh-'; then
+  install -d -m700 /home/STYX_USER/.ssh
+  echo 'SSH_PUBKEY' >> /home/STYX_USER/.ssh/authorized_keys
+  chmod 600 /home/STYX_USER/.ssh/authorized_keys
+  chown -R STYX_USER:STYX_USER /home/STYX_USER/.ssh
+fi
+
+# Freenove code
+git clone https://github.com/Freenove/Freenove_Computer_Case_Kit_for_Raspberry_Pi.git /opt/freenove || true
+
+# Hostname
+echo 'STYX_HOSTNAME' > /etc/hostname
+if grep -q '^127\.0\.1\.1' /etc/hosts; then
+  sed -i 's/^127\.0\.1\.1.*/127.0.1.1\tSTYX_HOSTNAME/' /etc/hosts
+else
+  echo -e '127.0.1.1\tSTYX_HOSTNAME' >> /etc/hosts
+fi
+
+apt-get clean
+EOS
+)
+  # Inject config values safely
+  CHCMD="${CHCMD//STYX_USER/${STYX_USER}}"
+  CHCMD="${CHCMD//STYX_PASS/${STYX_PASS}}"
+  CHCMD="${CHCMD//STYX_HOSTNAME/${STYX_HOSTNAME}}"
+  CHCMD="${CHCMD//SSH_PUBKEY/${SSH_PUBKEY}}"
+
+  chroot /mnt/pi-root /bin/bash -lc "$CHCMD"
+}
+
+install_service_host() {
+  # Systemd unit for the Freenove example app
+  mkdir -p /mnt/pi-root/etc/systemd/system/multi-user.target.wants
+  cat >/mnt/pi-root/etc/systemd/system/freenove-case.service <<'SERVICE'
+[Unit]
+Description=Freenove Case OLED/Fans/LEDs
+After=multi-user.target
+
+[Service]
+Type=simple
+ExecStart=/usr/bin/python3 /opt/freenove/Code/application.py
+Restart=on-failure
+
+[Install]
+WantedBy=multi-user.target
+SERVICE
+  ln -sf /etc/systemd/system/freenove-case.service \
+        /mnt/pi-root/etc/systemd/system/multi-user.target.wants/freenove-case.service || true
+}
+
+boot_tweaks() {
+  # Enable I2C and set DSI panel on the BOOT partition
+  grep -q 'dtparam=i2c_arm=on' /mnt/pi-boot/config.txt || echo 'dtparam=i2c_arm=on' >> /mnt/pi-boot/config.txt
+  # Append kernel cmdline only once
+  if ! grep -q 'DSI-1:800x480@60D' /mnt/pi-boot/cmdline.txt 2>/dev/null; then
+    sed -i '1 s#$# video=DSI-1:800x480@60D video=HDMI-A-1:off video=HDMI-A-2:off#' /mnt/pi-boot/cmdline.txt || true
+  fi
+}
+
+cleanup() {
+  rm -f /mnt/pi-root/usr/sbin/policy-rc.d || true
+  for d in dev/pts dev proc sys; do umount -lf "/mnt/pi-root/$d" 2>/dev/null || true; done
+  umount -lf /mnt/pi-boot 2>/dev/null || true
+  umount -lf /mnt/pi-root 2>/dev/null || true
+  sync || true
+}
+
+main() {
+  require_root
+  ensure_binfmt_arm64
+  find_parts
+  trap 'echo "ERROR at line $LINENO" >&2; cleanup' ERR INT
+  mount_parts
+  prep_chroot
+  install_service_host
+  boot_tweaks
+  cleanup
+  echo "✅ Done. Move the NVMe to the Pi and boot."
+  echo "   Login: user '${STYX_USER}'  pass '${STYX_PASS}'  (change with 'passwd')."
+  echo "   Quick checks on the Pi:"
+  echo "     sudo i2cdetect -y 1"
+  echo "     rpicam-still -n -o test.jpg   # (if rpicam-apps installed)"
+  echo "     libcamera-still -n -o test.jpg # (if legacy libcamera-apps installed)"
+  echo "     systemctl status freenove-case"
+}
+main "$@"

services/jellyfin/deployment.yaml

@@ -23,6 +23,11 @@ spec:
     spec:
       nodeSelector:
         jellyfin: "true"
+      securityContext:
+        runAsUser: 1000 
+        fsGroup: 65532
+        fsGroupChangePolicy: OnRootMismatch
+        runAsGroup: 65532
       runtimeClassName: nvidia
       containers:
         - name: jellyfin
@@ -36,6 +41,12 @@ spec:
               value: "compute,video,utility"
             - name: JELLYFIN_PublishedServerUrl
               value: "https://stream.bstein.dev"
+            - name: PUID
+              value: "1000"
+            - name: PGID
+              value: "65532"
+            - name: UMASK
+              value: "002"
           resources:
             limits:
               nvidia.com/gpu: 1
@@ -64,4 +75,4 @@ spec:
             claimName: jellyfin-cache-astreae
         - name: media
           persistentVolumeClaim:
-            claimName: jellyfin-media-asteria
+            claimName: jellyfin-media-asteria-new

services/jellyfin/pvc.yaml

@@ -36,5 +36,19 @@ spec:
   accessModes: ["ReadWriteMany"]
   resources:
     requests:
-      storage: 2Ti
+      storage: 4Ti
+  storageClassName: asteria
+
+---
+
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: jellyfin-media-asteria-new
+  namespace: jellyfin
+spec:
+  accessModes: ["ReadWriteMany"]
+  resources:
+    requests:
+      storage: 4Ti
   storageClassName: asteria

services/jitsi/deployment.yaml

@@ -0,0 +1,171 @@
+# services/jitsi/deployment.yaml
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: jitsi-prosody
+  namespace: jitsi
+spec:
+  replicas: 0
+  selector:
+    matchLabels: { app: jitsi-prosody }
+  template:
+    metadata:
+      labels: { app: jitsi-prosody }
+    spec:
+      nodeSelector:
+        kubernetes.io/hostname: titan-22
+        kubernetes.io/arch: amd64
+      containers:
+        - name: prosody
+          image: jitsi/prosody:stable
+          ports:
+            - { name: c2s, containerPort: 5222, protocol: TCP }
+            - { name: http, containerPort: 5280, protocol: TCP }
+            - { name: comp, containerPort: 5347, protocol: TCP }
+          env:
+            - { name: XMPP_DOMAIN, value: "meet.jitsi" }
+            - { name: XMPP_AUTH_DOMAIN, value: "auth.meet.jitsi" }
+            - { name: XMPP_MUC_DOMAIN, value: "muc.meet.jitsi" }
+            - { name: XMPP_INTERNAL_MUC_DOMAIN, value: "internal-muc.meet.jitsi" }
+            - { name: ENABLE_AUTH, value: "0" }     # open instance, no auth (fastest path)
+            - { name: ENABLE_GUESTS, value: "1" }
+            - { name: JICOFO_AUTH_USER, value: "focus" }
+            - { name: JVB_AUTH_USER, value: "jvb" }
+            - name: JICOFO_AUTH_PASSWORD
+              valueFrom: { secretKeyRef: { name: jitsi-internal-secrets, key: JICOFO_AUTH_PASSWORD } }
+            - name: JICOFO_COMPONENT_SECRET
+              valueFrom: { secretKeyRef: { name: jitsi-internal-secrets, key: JICOFO_COMPONENT_SECRET } }
+            - name: JVB_AUTH_PASSWORD
+              valueFrom: { secretKeyRef: { name: jitsi-internal-secrets, key: JVB_AUTH_PASSWORD } }
+          volumeMounts:
+            - { name: cfg, mountPath: /config }
+      volumes:
+        - name: cfg
+          persistentVolumeClaim: { claimName: jitsi-prosody-config }
+
+---
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: jitsi-jicofo
+  namespace: jitsi
+spec:
+  replicas: 0
+  selector:
+    matchLabels: { app: jitsi-jicofo }
+  template:
+    metadata:
+      labels: { app: jitsi-jicofo }
+    spec:
+      nodeSelector:
+        kubernetes.io/hostname: titan-22
+        kubernetes.io/arch: amd64
+      containers:
+        - name: jicofo
+          image: jitsi/jicofo:stable
+          env:
+            - { name: XMPP_DOMAIN, value: "meet.jitsi" }
+            - { name: XMPP_AUTH_DOMAIN, value: "auth.meet.jitsi" }
+            - { name: XMPP_MUC_DOMAIN, value: "muc.meet.jitsi" }
+            - { name: XMPP_INTERNAL_MUC_DOMAIN, value: "internal-muc.meet.jitsi" }
+            - { name: XMPP_SERVER, value: "jitsi-prosody.jitsi.svc.cluster.local" }
+            - { name: JICOFO_AUTH_USER, value: "focus" }
+            - name: JICOFO_AUTH_PASSWORD
+              valueFrom: { secretKeyRef: { name: jitsi-internal-secrets, key: JICOFO_AUTH_PASSWORD } }
+            - name: JICOFO_COMPONENT_SECRET
+              valueFrom: { secretKeyRef: { name: jitsi-internal-secrets, key: JICOFO_COMPONENT_SECRET } }
+            - { name: JVB_BREWERY_MUC, value: "jvbbrewery" }
+          volumeMounts:
+            - { name: cfg, mountPath: /config }
+      volumes:
+        - name: cfg
+          persistentVolumeClaim: { claimName: jitsi-jicofo-config }
+
+---
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: jitsi-jvb
+  namespace: jitsi
+spec:
+  replicas: 0
+  selector:
+    matchLabels: { app: jitsi-jvb }
+  template:
+    metadata:
+      labels: { app: jitsi-jvb }
+    spec:
+      nodeSelector:
+        kubernetes.io/hostname: titan-22
+        kubernetes.io/arch: amd64
+      containers:
+        - name: jvb
+          image: jitsi/jvb:stable
+          ports:
+            - { name: colibri-ws, containerPort: 9090, protocol: TCP }   # WebSocket control channel
+            - { name: rtp-udp, containerPort: 10000, hostPort: 10000, protocol: UDP }  # media
+            - { name: rtp-tcp,   containerPort: 4443,  hostPort: 4443,  protocol: TCP }
+          env:
+            - { name: XMPP_DOMAIN, value: "meet.jitsi" }
+            - { name: XMPP_AUTH_DOMAIN, value: "auth.meet.jitsi" }
+            - { name: XMPP_MUC_DOMAIN, value: "muc.meet.jitsi" }
+            - { name: XMPP_INTERNAL_MUC_DOMAIN, value: "internal-muc.meet.jitsi" }
+            - { name: XMPP_SERVER, value: "jitsi-prosody.jitsi.svc.cluster.local" }
+            - { name: JVB_AUTH_USER, value: "jvb" }
+            - name: JVB_AUTH_PASSWORD
+              valueFrom: { secretKeyRef: { name: jitsi-internal-secrets, key: JVB_AUTH_PASSWORD } }
+            - { name: JVB_BREWERY_MUC, value: "jvbbrewery" }
+            - { name: JVB_PORT, value: "10000" }             # matches hostPort above
+            - { name: ENABLE_COLIBRI_WEBSOCKET, value: "1" } # enables /colibri-ws
+            # - { name: JVB_STUN_SERVERS, value: "stun.l.google.com:19302,stun1.l.google.com:19302,meet-jit-si-turnrelay.jitsi.net:443" }
+            - { name: JVB_ENABLE_APIS, value: "rest,colibri" }
+            - { name: JVB_WS_DOMAIN, value: "meet.bstein.dev:443" }
+            - { name: JVB_WS_TLS,    value: "true" }
+            - { name: JVB_ADVERTISE_IPS, value: "38.28.125.112" }
+            - { name: JVB_TCP_HARVESTER_DISABLED, value: "false" }
+            - { name: JVB_TCP_PORT, value: "4443" }
+          volumeMounts:
+            - { name: cfg, mountPath: /config }
+      volumes:
+        - name: cfg
+          persistentVolumeClaim: { claimName: jitsi-jvb-config }
+
+---
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: jitsi-web
+  namespace: jitsi
+spec:
+  replicas: 0
+  selector:
+    matchLabels: { app: jitsi-web }
+  template:
+    metadata:
+      labels: { app: jitsi-web }
+    spec:
+      nodeSelector:
+        kubernetes.io/hostname: titan-22
+        kubernetes.io/arch: amd64
+      containers:
+        - name: web
+          image: jitsi/web:stable
+          ports:
+            - { name: http, containerPort: 80, protocol: TCP }
+          env:
+            - { name: PUBLIC_URL, value: "https://meet.bstein.dev" }
+            - { name: XMPP_DOMAIN, value: "meet.jitsi" }
+            - { name: XMPP_AUTH_DOMAIN, value: "auth.meet.jitsi" }
+            - { name: XMPP_MUC_DOMAIN, value: "muc.meet.jitsi" }
+            - { name: XMPP_INTERNAL_MUC_DOMAIN, value: "internal-muc.meet.jitsi" }
+            - { name: XMPP_BOSH_URL_BASE, value: "https://meet.bstein.dev" }
+            - { name: ENABLE_XMPP_WEBSOCKET, value: "1" }
+            - { name: ENABLE_COLIBRI_WEBSOCKET, value: "1" }
+          volumeMounts:
+            - { name: cfg, mountPath: /config }
+      volumes:
+        - name: cfg
+          persistentVolumeClaim: { claimName: jitsi-web-config }

services/jitsi/ingress.yaml

@@ -0,0 +1,41 @@
+# services/jitsi/ingress.yaml
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: jitsi
+  namespace: jitsi
+  annotations:
+    cert-manager.io/cluster-issuer: "letsencrypt-prod"
+spec:
+  ingressClassName: traefik
+  tls:
+    - hosts: [ "meet.bstein.dev" ]
+      secretName: jitsi-meet-tls
+  rules:
+    - host: meet.bstein.dev
+      http:
+        paths:
+          - path: /colibri-ws
+            pathType: Prefix
+            backend:
+              service:
+                name: jitsi-jvb
+                port: { number: 9090 }
+          - path: /xmpp-websocket
+            pathType: Prefix
+            backend:
+              service:
+                name: jitsi-prosody
+                port: { number: 5280 }
+          - path: /http-bind
+            pathType: Prefix
+            backend:
+              service:
+                name: jitsi-prosody
+                port: { number: 5280 }
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: jitsi-web
+                port: { number: 80 }

services/jitsi/kustomization.yaml

@@ -0,0 +1,10 @@
+# services/jitsi/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - namespace.yaml
+  - deployment.yaml
+  - service.yaml
+  - pvc.yaml
+  - ingress.yaml
+  - secret.yaml

services/jitsi/namespace.yaml

@@ -0,0 +1,5 @@
+# services/jitsi/namespace.yaml
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: jitsi

services/jitsi/pvc.yaml

@@ -0,0 +1,42 @@
+# services/jitsi/pvc.yaml
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: jitsi-web-config
+  namespace: jitsi
+spec:
+  accessModes: ["ReadWriteOnce"]
+  resources: { requests: { storage: 10Gi } }
+
+---
+
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: jitsi-prosody-config
+  namespace: jitsi
+spec:
+  accessModes: ["ReadWriteOnce"]
+  resources: { requests: { storage: 10Gi } }
+
+---
+
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: jitsi-jicofo-config
+  namespace: jitsi
+spec:
+  accessModes: ["ReadWriteOnce"]
+  resources: { requests: { storage: 10Gi } }
+
+---
+
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: jitsi-jvb-config
+  namespace: jitsi
+spec:
+  accessModes: ["ReadWriteOnce"]
+  resources: { requests: { storage: 10Gi } }

services/jitsi/secret.yaml

@@ -0,0 +1,11 @@
+# services/jitsi/secret.yaml
+apiVersion: v1
+kind: Secret
+metadata:
+  name: jitsi-internal-secrets
+  namespace: jitsi
+type: Opaque
+data:
+  JICOFO_COMPONENT_SECRET: bEg5Y09hZFJBem5PUFliQlp4RHkwRTRP
+  JICOFO_AUTH_PASSWORD: VVkyUmczaVRDWUZ0MzdQdmN3UDN1SFc5
+  JVB_AUTH_PASSWORD: d0M5aWJ4dWlPTnhFak9lRHJqSHdYa0g5

services/jitsi/service.yaml

@@ -0,0 +1,36 @@
+# services/jitsi/service.yaml
+apiVersion: v1
+kind: Service
+metadata:
+  name: jitsi-prosody
+  namespace: jitsi
+spec:
+  selector: { app: jitsi-prosody }
+  ports:
+    - { name: c2s, port: 5222, targetPort: 5222, protocol: TCP }
+    - { name: http, port: 5280, targetPort: 5280, protocol: TCP }
+    - { name: comp, port: 5347, targetPort: 5347, protocol: TCP }
+
+---
+
+apiVersion: v1
+kind: Service
+metadata:
+  name: jitsi-jvb
+  namespace: jitsi
+spec:
+  selector: { app: jitsi-jvb }
+  ports:
+    - { name: colibri-ws, port: 9090, targetPort: 9090, protocol: TCP }
+
+---
+
+apiVersion: v1
+kind: Service
+metadata:
+  name: jitsi-web
+  namespace: jitsi
+spec:
+  selector: { app: jitsi-web }
+  ports:
+    - { name: http, port: 80, targetPort: 80, protocol: TCP }

services/monitoring/helmrelease.yaml

@@ -0,0 +1,212 @@
+# services/monitoring/kube-state-metrics-helmrelease.yaml
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: kube-state-metrics
+  namespace: monitoring
+spec:
+  interval: 15m
+  chart:
+    spec:
+      chart: kube-state-metrics
+      version: "~6.0.0"
+      sourceRef:
+        kind: HelmRepository
+        name: prometheus
+        namespace: flux-system
+  values:
+    prometheusScrape: false
+
+---
+
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: node-exporter
+  namespace: monitoring
+spec:
+  interval: 15m
+  install:
+    disableWait: true
+  chart:
+    spec:
+      chart: prometheus-node-exporter
+      version: "~4.0.0"
+      sourceRef:
+        kind: HelmRepository
+        name: prometheus
+        namespace: flux-system
+  upgrade:
+    disableWait: true
+  values:
+    rbac:
+      pspEnabled: false
+    service:
+      annotations:
+        prometheus.io/scrape: "true"
+        prometheus.io/port: "9100"
+
+---
+
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: victoria-metrics-single
+  namespace: monitoring
+spec:
+  interval: 15m
+  chart:
+    spec:
+      chart: victoria-metrics-single
+      version: "~0.15.0"      # or omit to track appVersion
+      sourceRef:
+        kind: HelmRepository
+        name: victoria-metrics
+        namespace: flux-system
+  values:
+    server:
+      # keep ~3 months; change as you like (supports "d", "y")
+      extraArgs:
+        retentionPeriod: "90d"   # VM flag -retentionPeriod=90d. :contentReference[oaicite:11]{index=11}
+
+      persistentVolume:
+        enabled: true
+        size: 100Gi              # adjust; uses default StorageClass (Longhorn)
+        # storageClassName: ""   # set if you want a specific class
+
+      # Enable built-in Kubernetes scraping
+      scrape:
+        enabled: true            # chart enables promscrape. :contentReference[oaicite:12]{index=12}
+        config:
+          global:
+            scrape_interval: 15s
+
+          scrape_configs:
+            # VM self-metrics
+            - job_name: victoriametrics
+              static_configs:
+                - targets: ["localhost:8428"]
+
+            # --- K8s control-plane & nodes (from VM docs guide) ---
+            - job_name: "kubernetes-apiservers"
+              kubernetes_sd_configs: [{ role: endpoints }]
+              scheme: https
+              tls_config:
+                ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+                insecure_skip_verify: true
+              bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+              relabel_configs:
+                - action: keep
+                  source_labels: [__meta_kubernetes_namespace,__meta_kubernetes_service_name,__meta_kubernetes_endpoint_port_name]
+                  regex: default;kubernetes;https
+
+            - job_name: "kubernetes-nodes"
+              scheme: https
+              tls_config:
+                ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+                insecure_skip_verify: true
+              bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+              kubernetes_sd_configs: [{ role: node }]
+              relabel_configs:
+                - action: labelmap
+                  regex: __meta_kubernetes_node_label_(.+)
+                - target_label: __address__
+                  replacement: kubernetes.default.svc:443
+                - source_labels: [__meta_kubernetes_node_name]
+                  regex: (.+)
+                  target_label: __metrics_path__
+                  replacement: /api/v1/nodes/$1/proxy/metrics
+
+            - job_name: "kubernetes-nodes-cadvisor"
+              scheme: https
+              tls_config:
+                ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+                insecure_skip_verify: true
+              bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+              kubernetes_sd_configs: [{ role: node }]
+              relabel_configs:
+                - action: labelmap
+                  regex: __meta_kubernetes_node_label_(.+)
+                - target_label: __address__
+                  replacement: kubernetes.default.svc:443
+                - source_labels: [__meta_kubernetes_node_name]
+                  regex: (.+)
+                  target_label: __metrics_path__
+                  replacement: /api/v1/nodes/$1/proxy/metrics/cadvisor
+
+            # --- Annotated Services (generic autodiscovery) ---
+            - job_name: "kubernetes-service-endpoints"
+              kubernetes_sd_configs: [{ role: endpoints }]
+              relabel_configs:
+                - action: keep
+                  source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
+                  regex: "true"
+                - action: replace
+                  source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
+                  regex: (https?)
+                  target_label: __scheme__
+                - action: replace
+                  source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
+                  target_label: __metrics_path__
+                - action: replace
+                  regex: (.+)(?::\d+);(\d+)
+                  replacement: $1:$2
+                  source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
+                  target_label: __address__
+
+            # --- Annotated Pods (generic autodiscovery) ---
+            - job_name: "kubernetes-pods"
+              kubernetes_sd_configs: [{ role: pod }]
+              relabel_configs:
+                - action: keep
+                  source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
+                  regex: "true"
+                - action: drop
+                  source_labels: [__meta_kubernetes_pod_container_port_name]
+                  regex: ".*health.*"
+                - action: replace
+                  source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
+                  target_label: __metrics_path__
+                - action: replace
+                  regex: (.+):(?:\d+);(\d+)
+                  replacement: $1:$2
+                  source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
+                  target_label: __address__
+
+            # --- kube-state-metrics (via its Service) ---
+            - job_name: "kube-state-metrics"
+              kubernetes_sd_configs: [{ role: endpoints }]
+              relabel_configs:
+                - action: keep
+                  source_labels: [__meta_kubernetes_service_label_app_kubernetes_io_name]
+                  regex: kube-state-metrics
+
+            # --- Longhorn ---
+            - job_name: "longhorn-backend"
+              static_configs:
+                - targets: ["longhorn-backend.longhorn-system.svc:9500"]
+              metrics_path: /metrics
+
+            # --- cert-manager (pods expose on 9402) ---
+            - job_name: "cert-manager"
+              kubernetes_sd_configs: [{ role: pod }]
+              relabel_configs:
+                - action: keep
+                  source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_pod_label_app_kubernetes_io_name]
+                  regex: cert-manager;cert-manager
+                - action: drop
+                  source_labels: [__meta_kubernetes_pod_container_port_name]
+                  regex: ".*health.*"
+                - action: replace
+                  source_labels: [__address__]
+                  regex: "(.+):\\d+"
+                  replacement: "$1:9402"
+                  target_label: __address__
+
+            # --- Flux controllers (default :8080/metrics) ---
+            - job_name: "flux"
+              kubernetes_sd_configs: [{ role: pod }]
+              relabel_configs:
+                - action: keep
+                  source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_pod_label_app_kubernetes_io_part_of]
+                  regex: flux-system;flux

services/monitoring/kustomization.yaml

@@ -0,0 +1,8 @@
+# services/monitoring/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+namespace: monitoring
+resources:
+  - namespace.yaml
+  - rbac.yaml
+  - helmrelease.yaml

services/monitoring/namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring

services/monitoring/rbac.yaml

@@ -0,0 +1,33 @@
+# services/monitoring/rbac.yaml
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: vmsingle-scrape
+rules:
+  - apiGroups: [""]
+    resources:
+      - nodes
+      - nodes/proxy
+      - nodes/metrics
+      - services
+      - endpoints
+      - pods
+    verbs: ["get","list","watch"]
+  - apiGroups: ["networking.k8s.io","extensions"]
+    resources: ["ingresses"]
+    verbs: ["get","list","watch"]
+
+---
+
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: vmsingle-scrape
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: vmsingle-scrape
+subjects:
+  - kind: ServiceAccount
+    name: victoria-metrics-single
+    namespace: monitoring

services/pegasus/configmap.yaml

@@ -0,0 +1,48 @@
+# services/pegasus/configmap.yaml
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: pegasus-config
+  namespace: jellyfin
+data:
+  PEGASUS_MEDIA_ROOT: "/media"
+  PEGASUS_BIND: ":8080"
+
+---
+
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: pegasus-user-map
+  namespace: jellyfin
+data:
+  user-map.yaml: |
+    map:
+      mary_grace_allison:
+        - "allison"
+        - "gavilan"
+      maddie_rejcek:
+        - "rangeejcek"
+        - "gavilan"
+      carol_mcguinness:
+        - "mcguinness_family"
+        - "gavilan"
+      ed_stein:
+        - "stein_family"
+        - "gavilan"
+      brad_stein:
+        - "stein_brad"
+        - "gavilan"
+      lisa_stein:
+        - "scott"
+      channa_cox:
+        - "cox"
+        - "gavilan"
+      chelie_sheehan:
+        - "sheehan"
+        - "gavilan"
+      olya_bulgakova:
+        - "bulgakova"
+      sean_mcguinness:
+        - "mcguinness_sean"
+        - "gavilan"

services/pegasus/deployment.yaml

@@ -0,0 +1,114 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: pegasus
+  namespace: jellyfin
+spec:
+  replicas: 1
+  revisionHistoryLimit: 3
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxSurge: 0
+      maxUnavailable: 1
+  selector: { matchLabels: { app: pegasus } }
+  template:
+    metadata: { labels: { app: pegasus } }
+    spec:
+      nodeSelector:
+        kubernetes.io/arch: amd64
+      imagePullSecrets:
+        - name: zot-regcred
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 65532
+        runAsGroup: 65532
+        fsGroup: 65532
+        fsGroupChangePolicy: "OnRootMismatch"
+      initContainers:
+        - name: fix-perms
+          image: alpine:3.20
+          command:
+            - sh
+            - -lc
+            - |
+              set -eux
+
+              # Scratch area for tus uploads (always writable)
+              mkdir -p /media/.pegasus-tus
+              chmod 0777 /media/.pegasus-tus
+
+              # Make each top-level library dir group-writable and setgid,
+              # and try to set its group to 65532 (so the app can write).
+              for d in /media/*; do
+                [ -d "$d" ] || continue
+                base="$(basename "$d")"
+                [ "$base" = ".pegasus-tus" ] && continue
+                # chgrp can fail on some backends; don't block the pod if it does.
+                chgrp 65532 "$d" || true
+                chmod 2775 "$d" || true
+              done
+          securityContext:
+            runAsUser: 0
+            runAsGroup: 0
+            runAsNonRoot: false
+            allowPrivilegeEscalation: false
+          volumeMounts:
+            - { name: media, mountPath: /media }
+
+      containers:
+        - name: pegasus
+          image: registry.bstein.dev/pegasus:1.2.32 # {"$imagepolicy": "jellyfin:pegasus"}
+          imagePullPolicy: Always
+          command: ["/pegasus"]
+          env:
+            - name: PEGASUS_MEDIA_ROOT
+              valueFrom: { configMapKeyRef: { name: pegasus-config, key: PEGASUS_MEDIA_ROOT } }
+            - name: PEGASUS_BIND
+              valueFrom: { configMapKeyRef: { name: pegasus-config, key: PEGASUS_BIND } }
+            - name: PEGASUS_USER_MAP_FILE
+              value: "/config/user-map.yaml"
+            - name: PEGASUS_SESSION_KEY
+              valueFrom: { secretKeyRef: { name: pegasus-secrets, key: PEGASUS_SESSION_KEY } }
+            - name: JELLYFIN_URL
+              valueFrom: { secretKeyRef: { name: pegasus-secrets, key: JELLYFIN_URL } }
+            - name: JELLYFIN_API_KEY
+              valueFrom: { secretKeyRef: { name: pegasus-secrets, key: JELLYFIN_API_KEY } }
+            - name: PEGASUS_DEBUG
+              value: "1"
+            - name: PEGASUS_DRY_RUN
+              value: "0"
+          ports: [{ name: http, containerPort: 8080 }]
+          readinessProbe:
+            httpGet: { path: /healthz, port: http }
+            initialDelaySeconds: 2
+            periodSeconds: 5
+            timeoutSeconds: 1
+          livenessProbe:
+            httpGet: { path: /healthz, port: http }
+            initialDelaySeconds: 10
+            periodSeconds: 10
+            timeoutSeconds: 2
+          securityContext:
+            allowPrivilegeEscalation: false
+            readOnlyRootFilesystem: true
+            capabilities: { drop: ["ALL"] }
+          resources:
+            requests: { cpu: 100m, memory: 256Mi }
+            limits:   { cpu: 1000m, memory: 1Gi }
+          volumeMounts:
+            - name: media
+              mountPath: /media
+            - name: config
+              mountPath: /config
+              readOnly: true
+            - name: tmp
+              mountPath: /tmp
+      volumes:
+        - name: media
+          persistentVolumeClaim:
+            claimName: jellyfin-media-asteria-new
+        - name: config
+          configMap: { name: pegasus-user-map }
+        - name: tmp
+          emptyDir: {}

services/pegasus/image.yaml

@@ -0,0 +1,25 @@
+# services/pegasus/image.yaml
+apiVersion: image.toolkit.fluxcd.io/v1beta2
+kind: ImageRepository
+metadata:
+  name: pegasus
+  namespace: jellyfin
+spec:
+  image: registry.bstein.dev/pegasus
+  interval: 1m0s
+  secretRef:
+    name: zot-regcred
+
+---
+
+apiVersion: image.toolkit.fluxcd.io/v1beta2
+kind: ImagePolicy
+metadata:
+  name: pegasus
+  namespace: jellyfin
+spec:
+  imageRepositoryRef:
+    name: pegasus
+  policy:
+    semver:
+      range: "1.x"

services/pegasus/ingress.yaml

@@ -0,0 +1,25 @@
+# services/pegasus/ingress.yaml
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: pegasus
+  namespace: jellyfin
+  annotations:
+    kubernetes.io/ingress.class: traefik
+    traefik.ingress.kubernetes.io/router.entrypoints: websecure
+    traefik.ingress.kubernetes.io/router.tls: "true"
+    cert-manager.io/cluster-issuer: letsencrypt-prod
+spec:
+  tls:
+    - hosts: [ "pegasus.bstein.dev" ]
+      secretName: pegasus-bstein-dev-tls
+  rules:
+    - host: pegasus.bstein.dev
+      http:
+        paths:
+          - pathType: Prefix
+            path: /
+            backend:
+              service:
+                name: pegasus
+                port: { number: 80 }

services/pegasus/kustomization.yaml

@@ -0,0 +1,21 @@
+# services/pegasus/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - configmap.yaml
+  - service.yaml
+  - deployment.yaml
+  - ingress.yaml
+patches:
+  - target: { kind: Deployment, name: pegasus, namespace: jellyfin }
+    patch: |
+      - op: add
+        path: /spec/template/spec/containers/-
+        value:
+          name: shell
+          image: alpine:3.20
+          command: ["sh","-c","sleep infinity"]
+          securityContext: { runAsUser: 10001, runAsGroup: 10001, allowPrivilegeEscalation: false }
+          volumeMounts:
+            - { name: media, mountPath: /media }
+            - { name: config, mountPath: /config, readOnly: true }

services/pegasus/service.yaml

@@ -0,0 +1,12 @@
+# services/pegasus/service.yaml
+apiVersion: v1
+kind: Service
+metadata:
+  name: pegasus
+  namespace: jellyfin
+spec:
+  selector: { app: pegasus }
+  ports:
+    - name: http
+      port: 80
+      targetPort: http

services/sui-metrics/base/configmap.yaml

@@ -0,0 +1,16 @@
+# services/sui-metrics/base/configmap.yaml
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: sui-metrics-config
+  namespace: sui-metrics
+data:
+  vmagent.yaml: |
+    global:
+      scrape_interval: 15s
+      scrape_timeout: 10s
+    scrape_configs:
+      - job_name: oceanus-node-exporter
+        static_configs:
+          - targets:
+              - "192.168.22.23:9100"

services/sui-metrics/base/deployment.yaml

@@ -0,0 +1,63 @@
+# services/sui-metrics/base/deployment.yaml
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: sui-metrics
+  namespace: sui-metrics
+  labels:
+    app: sui-metrics
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: sui-metrics
+  template:
+    metadata:
+      labels:
+        app: sui-metrics
+    spec:
+      serviceAccountName: sui-metrics
+      containers:
+        - name: vmagent
+          image: victoriametrics/vmagent:v1.103.0
+          imagePullPolicy: IfNotPresent
+          args:
+            - -promscrape.config=/etc/vmagent/config/vmagent.yaml
+            - -remoteWrite.url=$(REMOTE_WRITE_URL)
+            - -remoteWrite.tmpDataPath=/var/lib/vmagent
+            - -loggerFormat=json
+          ports:
+            - name: http
+              containerPort: 8429
+              protocol: TCP
+          env:
+            - name: TZ
+              value: Etc/UTC
+            - name: REMOTE_WRITE_URL
+              value: http://victoria-metrics-single.monitoring.svc.cluster.local:8428/api/v1/write
+          resources:
+            requests:
+              cpu: 100m
+              memory: 256Mi
+            limits:
+              cpu: 500m
+              memory: 512Mi
+          volumeMounts:
+            - name: config
+              mountPath: /etc/vmagent/config
+              readOnly: true
+            - name: data
+              mountPath: /var/lib/vmagent
+          securityContext:
+            allowPrivilegeEscalation: false
+            runAsNonRoot: true
+            runAsUser: 65534
+            runAsGroup: 65534
+            capabilities:
+              drop: ["ALL"]
+      volumes:
+        - name: config
+          configMap:
+            name: sui-metrics-config
+        - name: data
+          emptyDir: {}

services/sui-metrics/base/kustomization.yaml

@@ -0,0 +1,10 @@
+# services/sui-metrics/base/kustomization.yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+namespace: sui-metrics
+resources:
+  - namespace.yaml
+  - serviceaccount.yaml
+  - configmap.yaml
+  - deployment.yaml
+  - service.yaml

services/sui-metrics/base/namespace.yaml

@@ -0,0 +1,5 @@
+# services/sui-metrics/base/namespace.yaml
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: sui-metrics

services/sui-metrics/base/service.yaml

@@ -0,0 +1,16 @@
+# services/sui-metrics/base/service.yaml
+apiVersion: v1
+kind: Service
+metadata:
+  name: sui-metrics
+  namespace: sui-metrics
+  labels:
+    app: sui-metrics
+spec:
+  type: ClusterIP
+  selector:
+    app: sui-metrics
+  ports:
+    - name: http
+      port: 8429
+      targetPort: 8429

services/sui-metrics/base/serviceaccount.yaml

@@ -0,0 +1,6 @@
+# services/sui-metrics/base/serviceaccount.yaml
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: sui-metrics
+  namespace: sui-metrics