zot: restore main branch config

Reviewed-on: #3

.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/keycloak/kustomization.yaml

@@ -0,0 +1,15 @@
+# clusters/atlas/flux-system/applications/keycloak/kustomization.yaml
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: keycloak
+  namespace: flux-system
+spec:
+  interval: 10m
+  prune: true
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+  path: ./services/keycloak
+  targetNamespace: sso
+  timeout: 2m

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

@@ -0,0 +1,17 @@
+# 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
+  - keycloak/kustomization.yaml
+  - oauth2-proxy/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/oauth2-proxy/kustomization.yaml

@@ -0,0 +1,15 @@
+# clusters/atlas/flux-system/applications/oauth2-proxy/kustomization.yaml
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: oauth2-proxy
+  namespace: flux-system
+spec:
+  interval: 10m
+  prune: true
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+  path: ./services/oauth2-proxy
+  targetNamespace: sso
+  timeout: 2m

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: feature/sso
   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: false

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/longhorn/ui-ingress/ingress.yaml

@@ -7,7 +7,7 @@ metadata:
   annotations:
     traefik.ingress.kubernetes.io/router.entrypoints: websecure
     traefik.ingress.kubernetes.io/router.tls: "true"
-    traefik.ingress.kubernetes.io/router.middlewares: longhorn-system-longhorn-basicauth@kubernetescrd,longhorn-system-longhorn-headers@kubernetescrd
+    traefik.ingress.kubernetes.io/router.middlewares: ""
 spec:
   ingressClassName: traefik
   tls:
@@ -21,6 +21,6 @@ spec:
             pathType: Prefix
             backend:
               service:
-                name: longhorn-frontend
+                name: oauth2-proxy-longhorn
                 port:
                   number: 80

infrastructure/longhorn/ui-ingress/kustomization.yaml

@@ -4,3 +4,4 @@ kind: Kustomization
 resources:
   - middleware.yaml
   - ingress.yaml
+  - oauth2-proxy-longhorn.yaml

infrastructure/longhorn/ui-ingress/middleware.yaml

@@ -20,3 +20,20 @@ spec:
   headers:
     customRequestHeaders:
       X-Forwarded-Proto: "https"
+
+---
+
+apiVersion: traefik.io/v1alpha1
+kind: Middleware
+metadata:
+  name: longhorn-forward-auth
+  namespace: longhorn-system
+spec:
+  forwardAuth:
+    address: https://auth.bstein.dev/oauth2/auth
+    trustForwardHeader: true
+    authResponseHeaders:
+      - Authorization
+      - X-Auth-Request-Email
+      - X-Auth-Request-User
+      - X-Auth-Request-Groups

infrastructure/longhorn/ui-ingress/oauth2-proxy-longhorn.yaml

@@ -0,0 +1,102 @@
+# infrastructure/longhorn/ui-ingress/oauth2-proxy-longhorn.yaml
+apiVersion: v1
+kind: Service
+metadata:
+  name: oauth2-proxy-longhorn
+  namespace: longhorn-system
+  labels:
+    app: oauth2-proxy-longhorn
+spec:
+  ports:
+    - name: http
+      port: 80
+      targetPort: 4180
+  selector:
+    app: oauth2-proxy-longhorn
+
+---
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: oauth2-proxy-longhorn
+  namespace: longhorn-system
+  labels:
+    app: oauth2-proxy-longhorn
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: oauth2-proxy-longhorn
+  template:
+    metadata:
+      labels:
+        app: oauth2-proxy-longhorn
+    spec:
+      nodeSelector:
+        node-role.kubernetes.io/worker: "true"
+      affinity:
+        nodeAffinity:
+          preferredDuringSchedulingIgnoredDuringExecution:
+            - weight: 90
+              preference:
+                matchExpressions:
+                  - key: hardware
+                    operator: In
+                    values: ["rpi5","rpi4"]
+      containers:
+        - name: oauth2-proxy
+          image: quay.io/oauth2-proxy/oauth2-proxy:v7.6.0
+          imagePullPolicy: IfNotPresent
+          args:
+            - --provider=oidc
+            - --redirect-url=https://longhorn.bstein.dev/oauth2/callback
+            - --oidc-issuer-url=https://sso.bstein.dev/realms/atlas
+            - --scope=openid profile email groups
+            - --email-domain=*
+            - --allowed-group=admin
+            - --set-xauthrequest=true
+            - --pass-access-token=true
+            - --set-authorization-header=true
+            - --cookie-secure=true
+            - --cookie-samesite=lax
+            - --cookie-refresh=20m
+            - --cookie-expire=168h
+            - --insecure-oidc-allow-unverified-email=true
+            - --upstream=http://longhorn-frontend.longhorn-system.svc.cluster.local
+            - --http-address=0.0.0.0:4180
+            - --skip-provider-button=true
+            - --skip-jwt-bearer-tokens=true
+            - --oidc-groups-claim=groups
+            - --cookie-domain=longhorn.bstein.dev
+          env:
+            - name: OAUTH2_PROXY_CLIENT_ID
+              valueFrom:
+                secretKeyRef:
+                  name: oauth2-proxy-longhorn-oidc
+                  key: client_id
+            - name: OAUTH2_PROXY_CLIENT_SECRET
+              valueFrom:
+                secretKeyRef:
+                  name: oauth2-proxy-longhorn-oidc
+                  key: client_secret
+            - name: OAUTH2_PROXY_COOKIE_SECRET
+              valueFrom:
+                secretKeyRef:
+                  name: oauth2-proxy-longhorn-oidc
+                  key: cookie_secret
+          ports:
+            - containerPort: 4180
+              name: http
+          readinessProbe:
+            httpGet:
+              path: /ping
+              port: 4180
+            initialDelaySeconds: 5
+            periodSeconds: 10
+          livenessProbe:
+            httpGet:
+              path: /ping
+              port: 4180
+            initialDelaySeconds: 20
+            periodSeconds: 20

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 +35,18 @@ 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.web.transport.respondingTimeouts.readTimeout=0s
+          - --entrypoints.web.transport.respondingTimeouts.writeTimeout=0s
+          - --entrypoints.web.transport.respondingTimeouts.idleTimeout=0s
+          - --entrypoints.websecure.transport.respondingTimeouts.readTimeout=0s
+          - --entrypoints.websecure.transport.respondingTimeouts.writeTimeout=0s
+          - --entrypoints.websecure.transport.respondingTimeouts.idleTimeout=0s
+          - --entrypoints.metrics.address=:9100
+          - --metrics.prometheus.entryPoint=metrics
           image: traefik:v3.3.3
           imagePullPolicy: IfNotPresent
           name: traefik
@@ -48,6 +60,9 @@ 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 '${STYX_PASS}'  (change with 'passwd')."
+  echo "   Quick checks on the Pi:"
+  echo "     sudo i2cdetect -y 1"
+  echo "     rpicam-still -n -o test.jpg   # (if rpicam-apps installed)"
+  echo "     libcamera-still -n -o test.jpg # (if legacy libcamera-apps installed)"
+  echo "     systemctl status freenove-case"
+}
+main "$@"

scripts/styx_prep_nvme_luks.sh

@@ -0,0 +1,575 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# --- CONFIG (edit if needed) ---
+# Leave NVME empty → script will auto-detect the SSK dock.
+NVME="${NVME:-}"
+FLAVOR="${FLAVOR:-desktop}"
+# Persistent cache so the image survives reboots.
+IMG_DIR="${IMG_DIR:-/var/cache/styx-rpi}"
+IMG_FILE="${IMG_FILE:-ubuntu-24.04.3-preinstalled-${FLAVOR}-arm64+raspi.img}"
+IMG_BOOT_MNT="${IMG_BOOT_MNT:-/mnt/img-boot}"
+IMG_ROOT_MNT="${IMG_ROOT_MNT:-/mnt/img-root}"
+TGT_ROOT="/mnt/target-root"
+TGT_BOOT="/mnt/target-boot"
+
+STYX_USER="styx"
+STYX_HOSTNAME="titan-ag"
+STYX_PASS="TempPass#123"                # will be forced to change on first login via cloud-init
+SSH_PUBKEY="ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIOb8oMX6u0z3sH/p/WBGlvPXXdbGETCKzWYwR/dd6fZb titan-bastion"
+
+# Video / input prefs
+DSI_FLAGS="video=DSI-1:800x480@60D video=HDMI-A-1:off video=HDMI-A-2:off"
+
+# --- Helpers ---
+fatal(){ echo "ERROR: $*" >&2; exit 1; }
+need(){ command -v "$1" >/dev/null || fatal "Missing tool: $1"; }
+
+require_root(){ [[ $EUID -eq 0 ]] || exec sudo -E "$0" "$@"; }
+
+part() {
+  local n="$1"
+  if [[ "$NVME" =~ [0-9]$ ]]; then
+    echo "${NVME}p${n}"
+  else
+    echo "${NVME}${n}"
+  fi
+}
+
+auto_detect_target_disk() {
+  # If user already set NVME, validate and return
+  if [[ -n "${NVME:-}" ]]; then
+    [[ -b "$NVME" ]] || fatal "NVME='$NVME' is not a block device"
+    return
+  fi
+
+  # Prefer stable by-id symlinks
+  local byid
+  byid=$(ls -1 /dev/disk/by-id/usb-SSK* 2>/dev/null | head -n1 || true)
+  if [[ -n "$byid" ]]; then
+    NVME=$(readlink -f "$byid")
+  else
+    # Heuristic via lsblk -S: look for USB with SSK/Ingram/Storage in vendor/model
+    NVME=$(lsblk -S -p -o NAME,TRAN,VENDOR,MODEL | \
+             awk '/ usb / && ($3 ~ /SSK|Ingram/i || $4 ~ /SSK|Storage/i){print $1; exit}')
+  fi
+
+  [[ -n "${NVME:-}" && -b "$NVME" ]] || fatal "Could not auto-detect SSK USB NVMe dock. Export NVME=/dev/sdX and re-run."
+  echo "Auto-detected target disk: $NVME"
+}
+
+preflight_cleanup() {
+  local img="$IMG_DIR/$IMG_FILE"
+
+  # 1) Unmount image mountpoints and detach only loops for this IMG
+  umount -lf "$IMG_BOOT_MNT" "$IMG_ROOT_MNT" 2>/dev/null || true
+  # losetup -j exits non-zero if no association → tolerate it
+  { losetup -j "$img" | cut -d: -f1 | xargs -r losetup -d; } 2>/dev/null || true
+
+  # 2) Unmount our target mounts
+  umount -lf "$TGT_ROOT/boot/firmware" "$TGT_BOOT" "$TGT_ROOT" 2>/dev/null || true
+
+  # 3) Unmount the actual target partitions if mounted anywhere (tolerate 'not found')
+  for p in "$(part 1)" "$(part 2)"; do
+    # findmnt returns 1 when no match → capture and iterate if any
+    while read -r mnt; do
+      [ -n "$mnt" ] && umount -lf "$mnt" 2>/dev/null || true
+    done < <(findmnt -rno TARGET -S "$p" 2>/dev/null || true)
+  done
+
+  # 4) Close dm-crypt mapping (if it exists)
+  cryptsetup luksClose cryptroot 2>/dev/null || true
+  dmsetup remove -f cryptroot 2>/dev/null || true
+
+  # 5) Let udev settle
+  command -v udevadm >/dev/null && udevadm settle || true
+}
+
+guard_target_device() {
+  # Refuse to operate if NVME appears to be the current system disk
+  local root_src root_disk
+  root_src=$(findmnt -no SOURCE /)
+  root_disk=$(lsblk -no pkname "$root_src" 2>/dev/null || true)
+  if [[ -n "$root_disk" && "/dev/$root_disk" == "$NVME" ]]; then
+    fatal "Refusing to operate on system disk ($NVME). Pick the external NVMe."
+  fi
+}
+
+need_host_fido2() {
+  if ! command -v fido2-token >/dev/null 2>&1; then
+    echo "Host is missing fido2-token. On Arch: sudo pacman -S libfido2"
+    echo "On Debian/Ubuntu host: sudo apt-get install fido2-tools"
+    exit 1
+  fi
+}
+
+ensure_image() {
+  mkdir -p "$IMG_DIR"
+  chmod 755 "$IMG_DIR"
+
+  local BASE="https://cdimage.ubuntu.com/releases/noble/release"
+  local XZ="ubuntu-24.04.3-preinstalled-${FLAVOR}-arm64+raspi.img.xz"
+
+  # If the decompressed .img is missing, fetch/decompress into the cache.
+  if [[ ! -f "$IMG_DIR/$IMG_FILE" ]]; then
+    need curl; need unxz  # Arch: pacman -S curl xz   |  Ubuntu: apt-get install curl xz-utils
+    if [[ ! -f "$IMG_DIR/$XZ" ]]; then
+      echo "Fetching image…"
+      curl -fL -o "$IMG_DIR/$XZ" "$BASE/$XZ"
+    fi
+    echo "Decompressing to $IMG_DIR/$IMG_FILE …"
+    # Keep the .xz for future runs; stream-decompress to the .img
+    if command -v unxz >/dev/null 2>&1; then
+      unxz -c "$IMG_DIR/$XZ" > "$IMG_DIR/$IMG_FILE"
+    else
+      need xz
+      xz -dc "$IMG_DIR/$XZ" > "$IMG_DIR/$IMG_FILE"
+    fi
+    sync
+  else
+    echo "Using cached image: $IMG_DIR/$IMG_FILE"
+  fi
+}
+
+ensure_binfmt_aarch64(){
+  # Register qemu-aarch64 for chrooted ARM64 apt runs
+  if [[ ! -e /proc/sys/fs/binfmt_misc/qemu-aarch64 ]]; then
+    need docker
+    systemctl enable --now docker >/dev/null 2>&1 || true
+    docker run --rm --privileged tonistiigi/binfmt --install arm64 >/dev/null
+  fi
+  if [[ ! -x /usr/local/bin/qemu-aarch64-static ]]; then
+    docker rm -f qemu-static >/dev/null 2>&1 || true
+    docker create --name qemu-static docker.io/multiarch/qemu-user-static:latest >/dev/null
+    docker cp qemu-static:/usr/bin/qemu-aarch64-static /usr/local/bin/
+    install -D -m755 /usr/local/bin/qemu-aarch64-static /usr/local/bin/qemu-aarch64-static
+    docker rm qemu-static >/dev/null
+  fi
+}
+
+open_image() {
+  [[ -r "$IMG_DIR/$IMG_FILE" ]] || fatal "Image not found: $IMG_DIR/$IMG_FILE"
+  mkdir -p "$IMG_BOOT_MNT" "$IMG_ROOT_MNT"
+
+  # Pre-clean: detach any previous loop(s) for this image (tolerate absence)
+  umount -lf "$IMG_BOOT_MNT" 2>/dev/null || true
+  umount -lf "$IMG_ROOT_MNT" 2>/dev/null || true
+  # If no loop is attached, losetup -j returns non-zero → swallow it
+  mapfile -t OLD < <({ losetup -j "$IMG_DIR/$IMG_FILE" | cut -d: -f1; } 2>/dev/null || true)
+  for L in "${OLD[@]:-}"; do losetup -d "$L" 2>/dev/null || true; done
+  command -v udevadm >/dev/null && udevadm settle || true
+
+  # Attach with partition scan; wait for partition nodes to exist
+  LOOP=$(losetup --find --show --partscan "$IMG_DIR/$IMG_FILE") || fatal "losetup failed"
+  command -v udevadm >/dev/null && udevadm settle || true
+  for _ in {1..25}; do
+    [[ -b "${LOOP}p1" && -b "${LOOP}p2" ]] && break
+    sleep 0.1
+    command -v udevadm >/dev/null && udevadm settle || true
+  done
+  [[ -b "${LOOP}p1" ]] || fatal "loop partitions not present for $LOOP"
+
+  # Cleanup on exit: unmount first, then detach loop (tolerate absence)
+  trap 'umount -lf "'"$IMG_BOOT_MNT"'" "'"$IMG_ROOT_MNT"'" 2>/dev/null; losetup -d "'"$LOOP"'" 2>/dev/null' EXIT
+
+  # Mount image partitions read-only
+  mount -o ro "${LOOP}p1" "$IMG_BOOT_MNT"
+  mount -o ro "${LOOP}p2" "$IMG_ROOT_MNT"
+
+  # Sanity checks without using failing pipelines
+  # start*.elf must exist
+  if ! compgen -G "$IMG_BOOT_MNT/start*.elf" > /dev/null; then
+    fatal "start*.elf not found in image"
+  fi
+  # vmlinuz-* must exist
+  if ! compgen -G "$IMG_ROOT_MNT/boot/vmlinuz-*" > /dev/null; then
+    fatal "vmlinuz-* not found in image root"
+  fi
+}
+
+confirm_and_wipe(){
+  lsblk -o NAME,SIZE,MODEL,TRAN,LABEL "$NVME"
+  read -rp "Type EXACTLY 'WIPE' to destroy ALL DATA on $NVME: " ACK
+  [[ "$ACK" == "WIPE" ]] || fatal "Aborted"
+  wipefs -a "$NVME"
+  sgdisk -Zo "$NVME"
+  # GPT: 1: 1MiB..513MiB vfat ESP; 2: rest LUKS
+  parted -s "$NVME" mklabel gpt \
+    mkpart system-boot fat32 1MiB 513MiB set 1 esp on \
+    mkpart cryptroot 513MiB 100%
+  partprobe "$NVME"; sleep 1
+  mkfs.vfat -F32 -n system-boot "$(part 1)"
+}
+
+setup_luks(){
+  echo "Create LUKS2 on $(part 2) (you will be prompted for a passphrase; keep it as fallback)"
+  need cryptsetup
+  cryptsetup luksFormat --type luks2 "$(part 2)"
+  cryptsetup open "$(part 2)" cryptroot
+  mkfs.ext4 -L rootfs /dev/mapper/cryptroot
+}
+
+mount_targets(){
+  mkdir -p "$TGT_ROOT" "$TGT_BOOT"
+  mount /dev/mapper/cryptroot "$TGT_ROOT"
+  mkdir -p "$TGT_ROOT/boot/firmware"
+  mount "$(part 1)" "$TGT_BOOT"
+  mount --bind "$TGT_BOOT" "$TGT_ROOT/boot/firmware"
+}
+
+rsync_root_and_boot(){
+  need rsync
+  rsync -aAXH --numeric-ids --delete \
+  --exclude='/boot/firmware' --exclude='/boot/firmware/**' \
+  --exclude='/dev/*' --exclude='/proc/*' --exclude='/sys/*' \
+  --exclude='/run/*' --exclude='/tmp/*' --exclude='/mnt/*' \
+  --exclude='/media/*' --exclude='/lost+found' \
+  "$IMG_ROOT_MNT"/ "$TGT_ROOT"/
+  rsync -aH --delete "$IMG_BOOT_MNT"/ "$TGT_ROOT/boot/firmware"/
+}
+
+write_crypttab_fstab(){
+  LUUID=$(blkid -s UUID -o value "$(part 2)")
+  printf 'cryptroot UUID=%s none luks,discard,fido2-device=auto\n' "$LUUID" > "$TGT_ROOT/etc/crypttab"
+  cat > "$TGT_ROOT/etc/fstab" <<EOF
+/dev/mapper/cryptroot  /               ext4  defaults,discard,errors=remount-ro  0 1
+LABEL=system-boot      /boot/firmware  vfat  defaults,umask=0077                 0 1
+EOF
+}
+
+fix_firmware_files(){
+  local C="$TGT_ROOT/boot/firmware/config.txt"
+  local CL="$TGT_ROOT/boot/firmware/cmdline.txt"
+  [[ -f "$C" ]] || fatal "missing $C"
+
+  # Always boot the uncompressed Pi 5 kernel
+  if grep -q '^kernel=' "$C"; then
+    sed -i 's#^kernel=.*#kernel=kernel_2712.img#' "$C"
+  else
+    sed -i '1i kernel=kernel_2712.img' "$C"
+  fi
+
+  # Ensure initramfs and cmdline indirection are set
+  grep -q '^initramfs ' "$C" || echo 'initramfs initrd.img followkernel' >> "$C"
+  grep -q '^cmdline=cmdline.txt' "$C" || sed -i '1i cmdline=cmdline.txt' "$C"
+
+  # Display & buses (Pi 5)
+  grep -q '^dtoverlay=vc4-kms-v3d-pi5' "$C" || echo 'dtoverlay=vc4-kms-v3d-pi5' >> "$C"
+  grep -q '^dtparam=i2c_arm=on'        "$C" || echo 'dtparam=i2c_arm=on' >> "$C"
+  grep -q '^dtparam=pciex1=on'         "$C" || echo 'dtparam=pciex1=on' >> "$C"
+  grep -q '^dtparam=pciex1_gen=2'      "$C" || echo 'dtparam=pciex1_gen=2' >> "$C"
+  grep -q '^enable_uart=1'             "$C" || echo 'enable_uart=1' >> "$C"
+
+  # Minimal, correct dracut hints using the bare UUID
+  local LUUID; LUUID=$(blkid -s UUID -o value "$(part 2)")
+  : > "$CL"
+  {
+    echo -n "rd.luks.uuid=$LUUID rd.luks.name=$LUUID=cryptroot "
+    echo -n "root=/dev/mapper/cryptroot rootfstype=ext4 rootwait fixrtc "
+    echo    "console=serial0,115200 console=tty1 ds=nocloud;s=file:///boot/firmware/ ${DSI_FLAGS} rd.debug"
+  } >> "$CL"
+}
+
+seed_cloud_init(){
+  # NoCloud seed to create user, lock down SSH, set hostname, and enable avahi.
+  cat > "$TGT_ROOT/boot/firmware/user-data" <<EOF
+#cloud-config
+hostname: $STYX_HOSTNAME
+manage_etc_hosts: true
+users:
+  - name: $STYX_USER
+    gecos: "$STYX_USER"
+    shell: /bin/bash
+    groups: [sudo,video,i2c]
+    sudo: ALL=(ALL) NOPASSWD:ALL
+    lock_passwd: false
+    ssh_authorized_keys:
+      - $SSH_PUBKEY
+chpasswd:
+  list: |
+    $STYX_USER:$STYX_PASS
+  expire: true
+ssh_pwauth: false
+package_update: true
+packages: [openssh-server, avahi-daemon]
+runcmd:
+  - systemctl enable --now ssh
+  - systemctl enable --now avahi-daemon || true
+EOF
+
+  # Minimal meta-data for NoCloud
+  date +%s | awk '{print "instance-id: iid-titan-ag-"$1"\nlocal-hostname: '"$STYX_HOSTNAME"'"}' \
+    > "$TGT_ROOT/boot/firmware/meta-data"
+}
+
+prep_chroot_mounts(){
+  for d in dev proc sys; do mount --bind "/$d" "$TGT_ROOT/$d"; done
+  mount -t devpts devpts "$TGT_ROOT/dev/pts"
+  # Replace the usual resolv.conf symlink with a real file for apt to work
+  rm -f "$TGT_ROOT/etc/resolv.conf"
+  cp /etc/resolv.conf "$TGT_ROOT/etc/resolv.conf"
+
+  # Block service starts (no systemd in chroot)
+  cat > "$TGT_ROOT/usr/sbin/policy-rc.d" <<'EOP'
+#!/bin/sh
+exit 101
+EOP
+  chmod +x "$TGT_ROOT/usr/sbin/policy-rc.d"
+
+  # Ensure qemu static is present inside chroot
+  install -D -m755 /usr/local/bin/qemu-aarch64-static "$TGT_ROOT/usr/bin/qemu-aarch64-static"
+}
+
+in_chroot(){
+  chroot "$TGT_ROOT" /usr/bin/qemu-aarch64-static /bin/bash -lc '
+set -euo pipefail
+export DEBIAN_FRONTEND=noninteractive TZ=Etc/UTC
+
+# --- APT sources (ports) ---
+cat > /etc/apt/sources.list <<'"'"'EOS'"'"'
+deb http://ports.ubuntu.com/ubuntu-ports noble main restricted universe multiverse
+deb http://ports.ubuntu.com/ubuntu-ports noble-updates main restricted universe multiverse
+deb http://ports.ubuntu.com/ubuntu-ports noble-security main restricted universe multiverse
+EOS
+
+apt-get update
+
+# --- Remove snaps and pin them off ---
+apt-get -y purge snapd || true
+rm -rf /snap /var/snap /var/lib/snapd /home/*/snap || true
+mkdir -p /etc/apt/preferences.d
+cat > /etc/apt/preferences.d/nosnap.pref <<'"'"'EOS'"'"'
+Package: snapd
+Pin: release *
+Pin-Priority: -10
+EOS
+
+# --- Base tools (no flash-kernel; we use dracut) ---
+apt-get install -y --no-install-recommends \
+  openssh-client openssh-server openssh-sftp-server avahi-daemon \
+  cryptsetup dracut fido2-tools libfido2-1 i2c-tools \
+  python3-smbus python3-pil zbar-tools qrencode lm-sensors \
+  file zstd lz4 || true
+
+# Camera apps: try rpicam-apps; otherwise basic libcamera tools
+apt-get install -y rpicam-apps || apt-get install -y libcamera-tools || true
+
+# --- Persistent journal so we can read logs after failed boot ---
+mkdir -p /etc/systemd/journald.conf.d
+cat > /etc/systemd/journald.conf.d/99-persistent.conf <<'"'"'EOS'"'"'
+[Journal]
+Storage=persistent
+EOS
+
+# --- SSH hardening (ensure file exists even if package was half-installed) ---
+if [ ! -f /etc/ssh/sshd_config ]; then
+  mkdir -p /etc/ssh
+  cat > /etc/ssh/sshd_config <<'"'"'EOS'"'"'
+PermitRootLogin no
+PasswordAuthentication no
+KbdInteractiveAuthentication no
+PubkeyAuthentication yes
+# Accept defaults for the rest
+EOS
+fi
+sed -i -e "s/^#\?PasswordAuthentication .*/PasswordAuthentication no/" \
+       -e "s/^#\?KbdInteractiveAuthentication .*/KbdInteractiveAuthentication no/" \
+       -e "s/^#\?PermitRootLogin .*/PermitRootLogin no/" \
+       -e "s/^#\?PubkeyAuthentication .*/PubkeyAuthentication yes/" /etc/ssh/sshd_config || true
+
+# --- Hostname & hosts ---
+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\t'"$STYX_HOSTNAME"'/" /etc/hosts
+else
+  echo -e "127.0.1.1\t'"$STYX_HOSTNAME"'" >> /etc/hosts
+fi
+
+# --- Enable services on first boot ---
+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
+ln -sf /lib/systemd/system/avahi-daemon.service /etc/systemd/system/multi-user.target.wants/avahi-daemon.service || true
+
+# --- Ensure i2c group ---
+getent group i2c >/dev/null || groupadd i2c
+
+# --- Dracut configuration (generic, not host-only) ---
+mkdir -p /etc/dracut.conf.d
+cat > /etc/dracut.conf.d/00-hostonly.conf <<'"'"'EOS'"'"'
+hostonly=no
+EOS
+cat > /etc/dracut.conf.d/10-systemd-crypt.conf <<'"'"'EOS'"'"'
+add_dracutmodules+=" systemd crypt "
+EOS
+cat > /etc/dracut.conf.d/20-drivers.conf <<'"'"'EOS'"'"'
+add_drivers+=" nvme xhci_pci xhci_hcd usbhid hid_generic hid "
+EOS
+cat > /etc/dracut.conf.d/30-fido2.conf <<'"'"'EOS'"'"'
+install_items+="/usr/bin/systemd-cryptsetup /usr/bin/fido2-token /usr/lib/*/libfido2.so* /usr/lib/*/libcbor.so*"
+EOS
+
+# --- Build initramfs and place it where firmware expects it ---
+KVER=$(ls -1 /lib/modules | sort -V | tail -n1)
+dracut --force /boot/initramfs-$KVER.img $KVER
+ln -sf initramfs-$KVER.img /boot/initrd.img
+ln -sf initramfs-$KVER.img /boot/initrd.img-$KVER
+cp -a /boot/initramfs-$KVER.img /boot/firmware/initrd.img
+
+# --- Create uncompressed kernel for Pi 5 firmware ---
+if [ -f "/usr/lib/linux-image-$KVER/Image" ]; then
+  cp -a "/usr/lib/linux-image-$KVER/Image" /boot/firmware/kernel_2712.img
+else
+  FMT=$(file -b "/boot/vmlinuz-$KVER" || true)
+  case "$FMT" in
+    *Zstandard*|*zstd*) zstd -dc "/boot/vmlinuz-$KVER" > /boot/firmware/kernel_2712.img ;;
+    *LZ4*)              lz4  -dc "/boot/vmlinuz-$KVER" > /boot/firmware/kernel_2712.img ;;
+    *gzip*)             zcat     "/boot/vmlinuz-$KVER" > /boot/firmware/kernel_2712.img ;;
+    *)                  cp -a "/boot/vmlinuz-$KVER" /boot/firmware/kernel_2712.img ;;
+  esac
+fi
+
+# --- Ensure Pi 5 DTB is present on the boot partition ---
+DTB=$(find /lib/firmware -type f -name "bcm2712-rpi-5-b.dtb" | sort | tail -n1 || true)
+[ -n "$DTB" ] && cp -a "$DTB" /boot/firmware/
+
+# --- Dracut hook to copy rdsosreport.txt to the FAT partition on failure ---
+mkdir -p /usr/lib/dracut/modules.d/99copylog
+cat > /usr/lib/dracut/modules.d/99copylog/module-setup.sh <<'"'"'EOS'"'"'
+#!/bin/bash
+check() { return 0; }
+depends() { echo base; return 0; }
+install() {
+  # Guard $moddir for nounset; derive if absent
+  local mdir="${moddir:-$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)}"
+  inst_hook emergency 99 "$mdir/copylog.sh"
+}
+EOS
+chmod +x /usr/lib/dracut/modules.d/99copylog/module-setup.sh
+
+cat > /usr/lib/dracut/modules.d/99copylog/copylog.sh <<'"'"'EOS'"'"'
+#!/bin/sh
+set -e
+for dev in /dev/nvme0n1p1 /dev/sda1 /dev/sdb1 /dev/mmcblk0p1; do
+  [ -b "$dev" ] || continue
+  mkdir -p /mnt/bootfat
+  if mount -t vfat "$dev" /mnt/bootfat 2>/dev/null; then
+    if [ -s /run/initramfs/rdsosreport.txt ]; then
+      cp -f /run/initramfs/rdsosreport.txt /mnt/bootfat/rdsosreport.txt 2>/dev/null || true
+      sync || true
+    fi
+    umount /mnt/bootfat || true
+    break
+  fi
+done
+EOS
+chmod +x /usr/lib/dracut/modules.d/99copylog/copylog.sh
+
+# Rebuild to ensure the copylog module is included
+dracut --force /boot/initramfs-$KVER.img $KVER
+ln -sf initramfs-$KVER.img /boot/initrd.img
+cp -a /boot/initramfs-$KVER.img /boot/firmware/initrd.img
+
+true
+'
+}
+
+verify_boot_assets(){
+  echo "---- verify boot assets on FAT ----"
+  file "$TGT_ROOT/boot/firmware/kernel_2712.img" || true
+  ls -lh "$TGT_ROOT/boot/firmware/initrd.img" || true
+  echo "-- config.txt (key lines) --"
+  grep -E '^(kernel|initramfs|cmdline)=|^dtoverlay=|^dtparam=' "$TGT_ROOT/boot/firmware/config.txt" || true
+  echo "-- cmdline.txt --"
+  cat "$TGT_ROOT/boot/firmware/cmdline.txt" || true
+  echo "-- firmware blobs (sample) --"
+  ls -1 "$TGT_ROOT/boot/firmware"/start*.elf "$TGT_ROOT/boot/firmware"/fixup*.dat | head -n 8 || true
+  echo "-- Pi5 DTB --"
+  ls -l "$TGT_ROOT/boot/firmware/"*rpi-5-b.dtb || true
+}
+
+enroll_fido_tokens(){
+  echo "Enrolling FIDO2 Solo keys into $(part 2) ..."
+  need systemd-cryptenroll
+  need fido2-token
+
+  # Collect all hidraw paths from both output styles (some distros print 'Device: /dev/hidrawX')
+  mapfile -t DEVS < <(
+    fido2-token -L \
+      | sed -n 's,^\(/dev/hidraw[0-9]\+\):.*,\1,p; s,^Device:[[:space:]]\+/dev/hidraw\([0-9]\+\).*,/dev/hidraw\1,p' \
+      | sort -u
+  )
+
+  if (( ${#DEVS[@]} == 0 )); then
+    echo "No FIDO2 tokens detected; skipping enrollment (you can enroll later)."
+    echo "Example later: systemd-cryptenroll $(part 2) --fido2-device=/dev/hidrawX --fido2-with-client-pin=no"
+    return 0
+  fi
+
+  # Recommend keeping exactly ONE key plugged during first enrollment to avoid ambiguity.
+  if (( ${#DEVS[@]} > 1 )); then
+    echo "Note: multiple FIDO2 tokens present: ${DEVS[*]}"
+    echo "If enrollment fails, try with only one key inserted."
+  fi
+
+  local rc=0
+  for D in "${DEVS[@]}"; do
+    echo "-> Enrolling $D (you should be asked to touch the key)"
+    if ! SYSTEMD_LOG_LEVEL=debug systemd-cryptenroll "$(part 2)" \
+          --fido2-device="$D" \
+          --fido2-with-client-pin=no \
+          --fido2-with-user-presence=yes \
+          --fido2-with-user-verification=no \
+          --label="solo-$(basename "$D")"; then
+      echo "WARN: enrollment failed for $D"
+      rc=1
+    fi
+  done
+
+  echo "Tokens enrolled (if any):"
+  systemd-cryptenroll "$(part 2)" --list || true
+  return $rc
+}
+
+cleanup(){
+  rm -f "$TGT_ROOT/usr/sbin/policy-rc.d" || true
+  umount -lf "$TGT_ROOT/dev/pts" 2>/dev/null || true
+  for d in dev proc sys; do umount -lf "$TGT_ROOT/$d" 2>/dev/null || true; done
+  umount -lf "$TGT_ROOT/boot/firmware" 2>/dev/null || true
+  umount -lf "$TGT_BOOT" 2>/dev/null || true
+  umount -lf "$TGT_ROOT" 2>/dev/null || true
+  cryptsetup close cryptroot 2>/dev/null || true
+  umount -lf "$IMG_BOOT_MNT" 2>/dev/null || true
+  umount -lf "$IMG_ROOT_MNT" 2>/dev/null || true
+}
+
+main(){
+  require_root
+  need losetup; need parted; need rsync
+  auto_detect_target_disk
+  echo "Target disk: $NVME"
+  ensure_binfmt_aarch64
+  ensure_image
+  preflight_cleanup
+  guard_target_device
+  open_image
+  confirm_and_wipe
+  setup_luks
+  mount_targets
+  rsync_root_and_boot
+  write_crypttab_fstab
+  fix_firmware_files
+  seed_cloud_init
+  prep_chroot_mounts
+  in_chroot
+  verify_boot_assets
+  need_host_fido2
+  enroll_fido_tokens
+  cleanup
+  echo "✅ NVMe prepared."
+  echo "   Install in the Pi 5 and boot with no SD."
+  echo "   Expect LUKS to unlock automatically with a Solo key inserted;"
+  echo "   passphrase fallback remains. Hostname: ${STYX_HOSTNAME}  User: ${STYX_USER}"
+  echo "   On first boot, reach it via: ssh -i ~/.ssh/id_ed25519_titan styx@titan-ag.local"
+}
+
+main "$@"

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/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/keycloak/README.md

@@ -0,0 +1,27 @@
+# services/keycloak
+
+Keycloak is deployed via raw manifests and backed by the shared Postgres (`postgres-service.postgres.svc.cluster.local:5432`). Create these secrets before applying:
+
+```bash
+# DB creds (per-service DB/user in shared Postgres)
+kubectl -n sso create secret generic keycloak-db \
+  --from-literal=username=keycloak \
+  --from-literal=password='<DB_PASSWORD>' \
+  --from-literal=database=keycloak
+
+# Admin console creds (maps to KC admin user)
+kubectl -n sso create secret generic keycloak-admin \
+  --from-literal=username=brad@bstein.dev \
+  --from-literal=password='<ADMIN_PASSWORD>'
+```
+
+Apply:
+
+```bash
+kubectl apply -k services/keycloak
+```
+
+Notes
+- Service: `keycloak.sso.svc:80` (Ingress `sso.bstein.dev`, TLS via cert-manager).
+- Uses Postgres schema `public`; DB/user should be provisioned in the shared Postgres instance.
+- Health endpoints on :9000 are wired for probes.

services/keycloak/deployment.yaml

@@ -0,0 +1,132 @@
+# services/keycloak/deployment.yaml
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: keycloak
+  namespace: sso
+  labels:
+    app: keycloak
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: keycloak
+  template:
+    metadata:
+      labels:
+        app: keycloak
+    spec:
+      affinity:
+        nodeAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            nodeSelectorTerms:
+              - matchExpressions:
+                  - key: hardware
+                    operator: In
+                    values: ["rpi5","rpi4"]
+                  - key: node-role.kubernetes.io/worker
+                    operator: Exists
+              - matchExpressions:
+                  - key: kubernetes.io/hostname
+                    operator: In
+                    values: ["titan-24"]
+          preferredDuringSchedulingIgnoredDuringExecution:
+            - weight: 90
+              preference:
+                matchExpressions:
+                  - key: hardware
+                    operator: In
+                    values: ["rpi5"]
+            - weight: 70
+              preference:
+                matchExpressions:
+                  - key: hardware
+                    operator: In
+                    values: ["rpi4"]
+      securityContext:
+        runAsUser: 1000
+        runAsGroup: 0
+        fsGroup: 1000
+        fsGroupChangePolicy: OnRootMismatch
+      containers:
+        - name: keycloak
+          image: quay.io/keycloak/keycloak:26.0.7
+          imagePullPolicy: IfNotPresent
+          args:
+            - start
+          env:
+            - name: KC_DB
+              value: postgres
+            - name: KC_DB_URL_HOST
+              value: postgres-service.postgres.svc.cluster.local
+            - name: KC_DB_URL_DATABASE
+              valueFrom:
+                secretKeyRef:
+                  name: keycloak-db
+                  key: database
+            - name: KC_DB_USERNAME
+              valueFrom:
+                secretKeyRef:
+                  name: keycloak-db
+                  key: username
+            - name: KC_DB_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: keycloak-db
+                  key: password
+            - name: KC_DB_SCHEMA
+              value: public
+            - name: KC_HOSTNAME
+              value: sso.bstein.dev
+            - name: KC_HOSTNAME_URL
+              value: https://sso.bstein.dev
+            - name: KC_PROXY
+              value: edge
+            - name: KC_PROXY_HEADERS
+              value: xforwarded
+            - name: KC_HTTP_ENABLED
+              value: "true"
+            - name: KC_HTTP_MANAGEMENT_PORT
+              value: "9000"
+            - name: KC_HTTP_MANAGEMENT_BIND_ADDRESS
+              value: 0.0.0.0
+            - name: KC_HEALTH_ENABLED
+              value: "true"
+            - name: KC_METRICS_ENABLED
+              value: "true"
+            - name: KEYCLOAK_ADMIN
+              valueFrom:
+                secretKeyRef:
+                  name: keycloak-admin
+                  key: username
+            - name: KEYCLOAK_ADMIN_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: keycloak-admin
+                  key: password
+          ports:
+            - containerPort: 8080
+              name: http
+            - containerPort: 9000
+              name: metrics
+          readinessProbe:
+            httpGet:
+              path: /health/ready
+              port: 9000
+            initialDelaySeconds: 15
+            periodSeconds: 10
+            failureThreshold: 6
+          livenessProbe:
+            httpGet:
+              path: /health/live
+              port: 9000
+            initialDelaySeconds: 60
+            periodSeconds: 15
+            failureThreshold: 6
+          volumeMounts:
+            - name: data
+              mountPath: /opt/keycloak/data
+      volumes:
+        - name: data
+          persistentVolumeClaim:
+            claimName: keycloak-data

services/keycloak/ingress.yaml

@@ -0,0 +1,24 @@
+# services/keycloak/ingress.yaml
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: keycloak
+  namespace: sso
+  annotations:
+    cert-manager.io/cluster-issuer: letsencrypt
+spec:
+  ingressClassName: traefik
+  rules:
+    - host: sso.bstein.dev
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: keycloak
+                port:
+                  number: 80
+  tls:
+    - hosts: [sso.bstein.dev]
+      secretName: keycloak-tls

services/keycloak/kustomization.yaml

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

services/keycloak/namespace.yaml

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

services/keycloak/pvc.yaml

@@ -0,0 +1,12 @@
+# services/keycloak/pvc.yaml
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: keycloak-data
+  namespace: sso
+spec:
+  accessModes: ["ReadWriteOnce"]
+  resources:
+    requests:
+      storage: 10Gi
+  storageClassName: astreae

services/keycloak/service.yaml

@@ -0,0 +1,15 @@
+# services/keycloak/service.yaml
+apiVersion: v1
+kind: Service
+metadata:
+  name: keycloak
+  namespace: sso
+  labels:
+    app: keycloak
+spec:
+  selector:
+    app: keycloak
+  ports:
+    - name: http
+      port: 80
+      targetPort: http

services/monitoring/README.md

@@ -0,0 +1,28 @@
+# services/monitoring
+
+## Grafana admin secret
+
+The Grafana Helm release expects a pre-existing secret named `grafana-admin`
+in the `monitoring` namespace. Create or rotate it with:
+
+```bash
+kubectl create secret generic grafana-admin \
+  --namespace monitoring \
+  --from-literal=admin-user=admin \
+  --from-literal=admin-password='REPLACE_ME'
+```
+
+Update the password whenever you rotate credentials.
+
+## DCGM exporter image
+
+The NVIDIA GPU metrics DaemonSet expects `registry.bstein.dev/monitoring/dcgm-exporter:4.4.2-4.7.0-ubuntu22.04`, mirrored from `docker.io/nvidia/dcgm-exporter:4.4.2-4.7.0-ubuntu22.04`. Refresh it in Zot when bumping versions:
+
+```bash
+skopeo copy \
+  --all \
+  docker://docker.io/nvidia/dcgm-exporter:4.4.2-4.7.0-ubuntu22.04 \
+  docker://registry.bstein.dev/monitoring/dcgm-exporter:4.4.2-4.7.0-ubuntu22.04
+```
+
+When finished mirroring from the control-plane, you can remove temporary tooling with `sudo apt-get purge -y skopeo && sudo apt-get autoremove -y` and clear `~/.config/containers/auth.json`.

services/monitoring/dashboards/atlas-gpu.json

@@ -0,0 +1,184 @@
+{
+  "uid": "atlas-gpu",
+  "title": "Atlas GPU",
+  "folderUid": "atlas-internal",
+  "editable": true,
+  "panels": [
+    {
+      "id": 1,
+      "type": "piechart",
+      "title": "Namespace GPU Share",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "atlas-vm"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "targets": [
+        {
+          "expr": "100 * ( ( (sum by (namespace) (max_over_time(DCGM_FI_DEV_GPU_UTIL{namespace!=\"\",pod!=\"\"}[$__range]))) or on(namespace) (sum(rate(container_cpu_usage_seconds_total{namespace!=\"\",pod!=\"\",container!=\"\"}[5m])) by (namespace) * 0) ) and on(namespace) ( (topk(10, ( sum(rate(container_cpu_usage_seconds_total{namespace!=\"\",pod!=\"\",container!=\"\"}[5m])) by (namespace) ) + (sum(container_memory_working_set_bytes{namespace!=\"\",pod!=\"\",container!=\"\"}) by (namespace) / 1e9) + ((sum((kube_pod_container_resource_requests{namespace!=\"\",resource=\"nvidia.com/gpu\"} or kube_pod_container_resource_limits{namespace!=\"\",resource=\"nvidia.com/gpu\"})) by (namespace)) or on(namespace) (sum(rate(container_cpu_usage_seconds_total{namespace!=\"\",pod!=\"\",container!=\"\"}[5m])) by (namespace) * 0) * 100)) >= bool 0) ) ) / clamp_min(sum( ( (sum by (namespace) (max_over_time(DCGM_FI_DEV_GPU_UTIL{namespace!=\"\",pod!=\"\"}[$__range]))) or on(namespace) (sum(rate(container_cpu_usage_seconds_total{namespace!=\"\",pod!=\"\",container!=\"\"}[5m])) by (namespace) * 0) ) and on(namespace) ( (topk(10, ( sum(rate(container_cpu_usage_seconds_total{namespace!=\"\",pod!=\"\",container!=\"\"}[5m])) by (namespace) ) + (sum(container_memory_working_set_bytes{namespace!=\"\",pod!=\"\",container!=\"\"}) by (namespace) / 1e9) + ((sum((kube_pod_container_resource_requests{namespace!=\"\",resource=\"nvidia.com/gpu\"} or kube_pod_container_resource_limits{namespace!=\"\",resource=\"nvidia.com/gpu\"})) by (namespace)) or on(namespace) (sum(rate(container_cpu_usage_seconds_total{namespace!=\"\",pod!=\"\",container!=\"\"}[5m])) by (namespace) * 0) * 100)) >= bool 0) ) ), 1)",
+          "refId": "A",
+          "legendFormat": "{{namespace}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent",
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "right"
+        },
+        "pieType": "pie",
+        "displayLabels": [
+          "percent"
+        ],
+        "tooltip": {
+          "mode": "single"
+        },
+        "colorScheme": "interpolateSpectral",
+        "colorBy": "value",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        }
+      }
+    },
+    {
+      "id": 2,
+      "type": "timeseries",
+      "title": "GPU Util by Namespace",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "atlas-vm"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "targets": [
+        {
+          "expr": "sum(DCGM_FI_DEV_GPU_UTIL{namespace!=\"\",pod!=\"\"}) by (namespace)",
+          "refId": "A",
+          "legendFormat": "{{namespace}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "table",
+          "placement": "right"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      }
+    },
+    {
+      "id": 3,
+      "type": "timeseries",
+      "title": "GPU Util by Node",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "atlas-vm"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "targets": [
+        {
+          "expr": "sum by (Hostname) (DCGM_FI_DEV_GPU_UTIL{pod!=\"\"})",
+          "refId": "A",
+          "legendFormat": "{{Hostname}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "table",
+          "placement": "right"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      }
+    },
+    {
+      "id": 4,
+      "type": "table",
+      "title": "Top Pods by GPU Util",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "atlas-vm"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "targets": [
+        {
+          "expr": "topk(10, sum(DCGM_FI_DEV_GPU_UTIL{pod!=\"\"}) by (namespace,pod,Hostname))",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "options": {
+        "showHeader": true
+      },
+      "transformations": [
+        {
+          "id": "labelsToFields",
+          "options": {}
+        }
+      ]
+    }
+  ],
+  "time": {
+    "from": "now-12h",
+    "to": "now"
+  },
+  "annotations": {
+    "list": []
+  },
+  "schemaVersion": 39,
+  "style": "dark",
+  "tags": [
+    "atlas",
+    "gpu"
+  ]
+}