Compare commits

...

18 Commits

Author SHA1 Message Date
Codex
60f5f8e6f0 feat(fc-devicemgmt): add Kubernetes deployment manifests 2026-05-17 21:50:14 -05:00
b8c7e59005 Tighten Pi signage HDMI settle coverage (#3) 2026-05-18 02:35:17 +00:00
65ac8d6f01 feat(github-runner): pod-env DOTNET_INSTALL_DIR + initContainer for non-root runner (#7) 2026-05-18 02:25:18 +00:00
35844e0dbd chore(github-runner): un-park github-runner-sharedpos (Shared.Pos non-root build fixed) (#6) 2026-05-18 02:20:00 +00:00
b1e307151e chore(github-runner): un-park github-runner-sharedpos (replicas 1) after Shared.Pos CI fix merged 2026-05-17 21:54:16 +00:00
12b07219c7 chore(github-runner): park github-runner-sharedpos (replicas 0) until Cx-1 non-root fix
Shared.Pos build fails on non-root runner (setup-dotnet /usr/share/dotnet denied); churning runner drove HighCPU on rke2-agent2. Re-enable in the Sprint 30+ Cx-1 Linux-runner-fleet lane (DOTNET_INSTALL_DIR on pod env).
2026-05-17 21:50:35 +00:00
9fd32c4415 feat(monitoring): MacMiniRunnerOffline alert (Sprint 28 reconcile) 2026-05-17 19:50:29 +00:00
ad670fb344 feat(github-runner): add Shared.Pos repo-scoped Linux runner (unstick stuck publish) 2026-05-17 19:50:23 +00:00
Codex
6f6ca50987 fix(github-runner): switch RUNNER_TOKEN -> ACCESS_TOKEN; set RUN_AS_ROOT=false
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 22:08:56 +00:00
Codex
c7be58c1f7 chore(github-runner): bump replicas 0 -> 1 (PAT provisioned)
Operator provisioned GitHub PAT (Runner Registration) 1P item. OnePasswordItem CRD already materialized the secret. Unblocks CI fleet-wide.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 22:04:03 +00:00
Codex
a1f5a393cd chore(github-runner): rename 1P item to GitHub PAT (Runner Registration)
Renames the OnePasswordItem.itemPath from "GitHub Runner Registration
Token" to "GitHub PAT (Runner Registration)" so the runner 1P entry
sits next to its siblings — GitHub PAT (Gitea Mirrors) and GitHub PAT
(NuGet Packages) — under a consistent "GitHub PAT (...)" naming pattern
and API_CREDENTIAL category.

Existing field "credential" remains the consumer (RUNNER_TOKEN env).
Comment block clarified to require Administration:read/write fine-grained
PAT scope on target repos.

Old 1P item renamed to "[DEPRECATED 2026-05-16] GitHub Runner
Registration" — kept as recovery backup; can be hard-deleted after the
first successful runner pod start against the new item path.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 22:01:41 +00:00
Codex
710340d8be chore(github-runner): rename 1P item to GitHub PAT (Runner Registration)
Renames the OnePasswordItem.itemPath from "GitHub Runner Registration
Token" to "GitHub PAT (Runner Registration)" so the runner 1P entry
sits next to its siblings — GitHub PAT (Gitea Mirrors) and GitHub PAT
(NuGet Packages) — under a consistent "GitHub PAT (...)" naming pattern
and API_CREDENTIAL category.

Existing field "credential" remains the consumer (RUNNER_TOKEN env).
Comment block clarified to require Administration:read/write fine-grained
PAT scope on target repos.

Old 1P item renamed to "[DEPRECATED 2026-05-16] GitHub Runner
Registration" — kept as recovery backup; can be hard-deleted after the
first successful runner pod start against the new item path.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 10:27:58 -05:00
Andrew Stoltz
7d2daaa4f8 chore(github-runner): replicas 1 → 0 until 1Password token provisioned
github-runner-token OnePasswordItem exists but the underlying 1Password
vault item hasn't been created yet, so the operator can't mint the K8s
Secret. Pod stuck in CreateContainerConfigError → DeploymentReplicasMismatch
alert fires.

Scaling to 0 keeps the manifest infrastructure intact but stops trying
to schedule until operator:
1. Creates "GitHub Runner Registration Token" item in IAmWorkin vault
2. Generates a token at github.com/astoltz/<repo>/settings/actions/runners/new
3. Updates the OnePasswordItem itemPath to point at it
4. Bumps replicas back to 1 via PR
2026-05-15 16:18:19 -05:00
Andrew Stoltz
e50e103ba0 fix(zabbix): bump web probe timeouts 5s→15s + add failureThreshold
zabbix-web nginx+PHP-FPM container serves / at ~3-5s baseline with
occasional 6-7s spikes (probe path renders full dashboard via PHP).
kube-probe was killing the container after 3 consecutive 5s-timeout
499s, producing CrashLoopBackOff alert noise even though the app
was serving real traffic fine.

15s timeout absorbs the natural variance; explicit failureThreshold=3
documents the policy (was implicit default).

Closes the firing PodCrashLoopBackOff (zabbix-web) + pending
HTTPServiceSlow/HTTPServiceDegraded alerts. zabbix.iamworkin.lan
remains slow at the application layer (separate work — PHP-FPM
warm-up + Zabbix server "host not found" agent lookup spam need
their own fixes) but the pod restart loop stops.
2026-05-15 15:59:04 -05:00
Codex
e8094eb0bd ci(github-runner): add Phase 2 ephemeral Linux runner K8s manifest
Namespace github-runner with myoung34/github-runner:latest Deployment,
5Gi Longhorn RWO NuGet cache PVC, zero-privilege ServiceAccount, and
OnePasswordItem CRD for the registration token. EPHEMERAL=true mode
re-registers after each job; Recreate strategy avoids RWO multi-attach.
Targets fc-build-linux label; single replica pinned to rke2-server node.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-14 12:46:25 -05:00
8d87d9172c Add Pi signage Phase 1 player artifacts
Squash merge Sprint 14 Pi signage player artifacts.
2026-05-14 01:46:09 +00:00
Codex
cfd9743afa Add Apple TV signage docs manifest 2026-05-13 20:32:48 -05:00
Andrew Stoltz
5029e209cd kubevirt-vms: boot ci1 from server template 2026-05-12 16:58:18 -05:00
41 changed files with 2392 additions and 426 deletions

View File

@@ -0,0 +1,26 @@
# Runtime secrets for FlowerCore.DeviceManagement.
#
# OnePasswordItem operator syncs this item into a Kubernetes Secret with the
# same name. Expected fields:
# DB-Password
# mtls-ca.pem
# mtls-client.crt
# mtls-client.key
# mtls-chain.pem
#
# Do not add literal secret values to this repo. Runtime pods consume the
# synced Secret through env vars and read-only mounts.
apiVersion: onepassword.com/v1
kind: OnePasswordItem
metadata:
name: fc-devicemgmt-runtime
namespace: fc-devicemgmt
labels:
app.kubernetes.io/name: fc-devicemgmt
app.kubernetes.io/component: secrets
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
itemPath: "vaults/IAmWorkin/items/FlowerCore DeviceManagement Runtime"

View File

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

View File

@@ -0,0 +1,30 @@
# Certificate for devices.iamworkin.lan.
#
# Preflight gate: FlowerCore.DNS / pfSense must contain an explicit A record:
# devices.iamworkin.lan -> 10.0.56.200
# before this Certificate is synced. step-ca ACME cannot see the CoreDNS
# wildcard, so missing pfSense DNS produces cert-manager HTTP-01 backoff
# (feedback_pfsense_dns_required_for_acme).
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: fc-devicemgmt-web-tls
namespace: fc-devicemgmt
labels:
app.kubernetes.io/name: fc-devicemgmt-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
flowercore.io/dns-preflight: "devices.iamworkin.lan must resolve to 10.0.56.200 before ACME sync"
spec:
secretName: fc-devicemgmt-web-tls
issuerRef:
name: step-ca-acme
kind: ClusterIssuer
dnsNames:
- devices.iamworkin.lan
duration: 720h
renewBefore: 240h

View File

@@ -0,0 +1,81 @@
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: fc-devicemgmt-operator
labels:
app.kubernetes.io/name: fc-devicemgmt-operator
app.kubernetes.io/component: operator
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
rules:
- apiGroups:
- devices.flowercore.io
resources:
- '*'
verbs:
- get
- list
- watch
- create
- update
- patch
- delete
- apiGroups:
- devices.flowercore.io
resources:
- devices/status
- devices/finalizers
- devicegroups/status
- devicegroups/finalizers
- devicepolicies/status
- devicepolicies/finalizers
- remotecommands/status
- remotecommands/finalizers
verbs:
- get
- update
- patch
- apiGroups:
- apps
resources:
- deployments
verbs:
- get
- apiGroups:
- ""
resources:
- pods
- services
- configmaps
- secrets
- events
verbs:
- get
- list
- watch
- create
- update
- patch
- delete
- apiGroups:
- batch
resources:
- jobs
verbs:
- get
- list
- watch
- create
- update
- patch
- delete
- apiGroups:
- networking.k8s.io
resources:
- networkpolicies
verbs:
- get
- list
- watch

View File

@@ -0,0 +1,19 @@
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: fc-devicemgmt-operator
labels:
app.kubernetes.io/name: fc-devicemgmt-operator
app.kubernetes.io/component: operator
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: fc-devicemgmt-operator
subjects:
- kind: ServiceAccount
name: fc-devicemgmt-operator
namespace: fc-devicemgmt

View File

@@ -0,0 +1,109 @@
# FlowerCore.DeviceManagement Operator.
#
# KubeOps controller for devices.flowercore.io resources. Operator-created
# children must set OwnerReferences + traceability labels/annotations per
# k8s-pod-ownership-and-traceability-standard.md. RBAC below grants
# apps/deployments/get so the process can resolve its own Deployment UID.
apiVersion: apps/v1
kind: Deployment
metadata:
name: fc-devicemgmt-operator
namespace: fc-devicemgmt
labels:
app: fc-devicemgmt-operator
app.kubernetes.io/name: fc-devicemgmt-operator
app.kubernetes.io/component: operator
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
flowercore.io/traceability-standard: k8s-pod-ownership-and-traceability-standard
spec:
replicas: 1
revisionHistoryLimit: 3
selector:
matchLabels:
app: fc-devicemgmt-operator
template:
metadata:
labels:
app: fc-devicemgmt-operator
app.kubernetes.io/name: fc-devicemgmt-operator
app.kubernetes.io/component: operator
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
prometheus.io/scrape: "true"
prometheus.io/port: "8080"
prometheus.io/path: "/metrics"
flowercore.io/audit-trace-id: "runtime-activity-trace"
spec:
serviceAccountName: fc-devicemgmt-operator
securityContext:
fsGroup: 1654
fsGroupChangePolicy: OnRootMismatch
containers:
- name: operator
image: localhost/fc-devicemgmt-operator:v20260512-cx5
imagePullPolicy: Never
ports:
- name: metrics
containerPort: 8080
env:
- name: ASPNETCORE_ENVIRONMENT
value: "Production"
- name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
value: "false"
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
- name: FLOWERCORE_KUBERNETES_OWNER_DEPLOYMENT
value: "fc-devicemgmt-operator"
- name: FlowerCore__Service__Name
value: "FlowerCore.DeviceManagement.Operator"
- name: FlowerCore__DeviceManagement__DefaultTenantId
value: "system"
resources:
requests:
cpu: 50m
memory: 128Mi
limits:
cpu: 500m
memory: 512Mi
readinessProbe:
tcpSocket:
port: 8080
initialDelaySeconds: 5
periodSeconds: 10
livenessProbe:
tcpSocket:
port: 8080
initialDelaySeconds: 20
periodSeconds: 30
securityContext:
runAsNonRoot: true
runAsUser: 1654
runAsGroup: 1654
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop:
- ALL
volumeMounts:
- name: tmp
mountPath: /tmp
- name: logs
mountPath: /app/logs
volumes:
- name: tmp
emptyDir: {}
- name: logs
emptyDir: {}

View File

@@ -0,0 +1,135 @@
# FlowerCore.DeviceManagement Web.
#
# Source repo is expected to ship FlowerCore.DeviceManagement.Web in a later
# Sprint 9+ lane. This manifest is static-valid without requiring the image to
# exist yet; import localhost/fc-devicemgmt-web:<tag> to all schedulable RKE2
# nodes before letting ArgoCD sync a live rollout.
apiVersion: apps/v1
kind: Deployment
metadata:
name: fc-devicemgmt-web
namespace: fc-devicemgmt
labels:
app: fc-devicemgmt-web
app.kubernetes.io/name: fc-devicemgmt-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
flowercore.io/traceability-standard: k8s-pod-ownership-and-traceability-standard
spec:
replicas: 2
revisionHistoryLimit: 3
selector:
matchLabels:
app: fc-devicemgmt-web
template:
metadata:
labels:
app: fc-devicemgmt-web
app.kubernetes.io/name: fc-devicemgmt-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
prometheus.io/scrape: "true"
prometheus.io/port: "8080"
prometheus.io/path: "/metrics"
flowercore.io/audit-trace-id: "runtime-activity-trace"
spec:
securityContext:
fsGroup: 1654
fsGroupChangePolicy: OnRootMismatch
containers:
- name: web
image: localhost/fc-devicemgmt-web:v20260512-cx5
imagePullPolicy: Never
ports:
- name: http
containerPort: 8080
env:
- name: ASPNETCORE_URLS
value: "http://+:8080"
- name: ASPNETCORE_ENVIRONMENT
value: "Production"
- name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
value: "false"
- name: FlowerCore__Service__Name
value: "FlowerCore.DeviceManagement.Web"
- name: FlowerCore__DeviceManagement__DefaultTenantId
value: "system"
- name: FlowerCore__Database__Provider
value: "MySql"
- name: FlowerCore__Database__Host
value: "mysql.fc-mysql.svc"
- name: FlowerCore__Database__Database
value: "flowercore_devicemgmt"
- name: FlowerCore__Database__User
value: "fc_devicemgmt"
- name: FlowerCore__Database__Password
valueFrom:
secretKeyRef:
name: fc-devicemgmt-runtime
key: DB-Password
- name: FlowerCore__DeviceManagement__AgentMtls__CaPath
value: "/secrets/devicemgmt-mtls/mtls-ca.pem"
- name: FlowerCore__DeviceManagement__AgentMtls__ClientCertificatePath
value: "/secrets/devicemgmt-mtls/mtls-client.crt"
- name: FlowerCore__DeviceManagement__AgentMtls__ClientKeyPath
value: "/secrets/devicemgmt-mtls/mtls-client.key"
- name: FlowerCore__EventBus__Redis__Configuration
value: "redis.fc-redis.svc:6379"
resources:
requests:
cpu: 100m
memory: 256Mi
limits:
cpu: 1000m
memory: 768Mi
startupProbe:
tcpSocket:
port: 8080
initialDelaySeconds: 5
periodSeconds: 5
failureThreshold: 30
readinessProbe:
tcpSocket:
port: 8080
periodSeconds: 10
failureThreshold: 3
livenessProbe:
tcpSocket:
port: 8080
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
securityContext:
runAsNonRoot: true
runAsUser: 1654
runAsGroup: 1654
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop:
- ALL
volumeMounts:
- name: tmp
mountPath: /tmp
- name: logs
mountPath: /app/logs
- name: devicemgmt-mtls
mountPath: /secrets/devicemgmt-mtls
readOnly: true
volumes:
- name: tmp
emptyDir: {}
- name: logs
emptyDir: {}
- name: devicemgmt-mtls
secret:
secretName: fc-devicemgmt-runtime
defaultMode: 0400

View File

@@ -0,0 +1,55 @@
# LAN ingress for FlowerCore.DeviceManagement Web.
#
# RKE2 Traefik has no built-in ACME resolver configured. Keep TLS certificate
# ownership in cert-manager Certificate/fc-devicemgmt-web-tls.
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: fc-devicemgmt-web
namespace: fc-devicemgmt
labels:
app.kubernetes.io/name: fc-devicemgmt-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
entryPoints:
- websecure
routes:
- match: Host(`devices.iamworkin.lan`)
kind: Rule
services:
- name: fc-devicemgmt-web
port: 80
tls:
secretName: fc-devicemgmt-web-tls
# Future public agent/update host gate (OFF by default):
#
# Do not enable `update.flowercore.io` here until Authentik OIDC Q-OIDC-1
# resolves the public-device-management auth model and route ownership with
# UpdateCenter. When enabled, use a separate public IngressRoute with an
# explicit Method allowlist, public-host auth middleware, and public TLS
# certificate strategy. Leaving this as comments keeps ArgoCD from stealing
# live UpdateCenter traffic.
#
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: fc-devicemgmt-web-public
# namespace: fc-devicemgmt
# annotations:
# flowercore.io/public-host-gate: "disabled-until-Q-OIDC-1"
# spec:
# entryPoints:
# - websecure
# routes:
# - match: Host(`update.flowercore.io`) && (Method(`GET`) || Method(`HEAD`) || Method(`POST`) || Method(`OPTIONS`))
# kind: Rule
# services:
# - name: fc-devicemgmt-web
# port: 80
# tls:
# secretName: fc-devicemgmt-public-tls

View File

@@ -0,0 +1,13 @@
# FlowerCore.DeviceManagement namespace.
#
# ArgoCD discovers this directory as Application `infra-fc-devicemgmt`.
apiVersion: v1
kind: Namespace
metadata:
name: fc-devicemgmt
labels:
app.kubernetes.io/name: fc-devicemgmt
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra

View File

@@ -0,0 +1,224 @@
# FlowerCore.DeviceManagement NetworkPolicies.
#
# NetworkPolicies belong in bluejay-infra so ArgoCD owns rebuild state.
# Rules include Traefik post-DNAT backend ports per
# feedback_netpol_dnat_backend_port and Synology NFS egress for the requested
# cold-tier / future artifact path.
---
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: fc-devicemgmt-web-isolation
namespace: fc-devicemgmt
labels:
app.kubernetes.io/name: fc-devicemgmt-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
podSelector:
matchLabels:
app: fc-devicemgmt-web
policyTypes:
- Ingress
- Egress
ingress:
# LAN edge: only cluster Traefik should reach the Web pod for
# devices.iamworkin.lan.
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: traefik-system
podSelector:
matchLabels:
app.kubernetes.io/name: traefik
ports:
- port: 8080
protocol: TCP
# Direct LAN diagnostics are allowed only from FlowerCore LAN/VPN ranges.
- from:
- ipBlock:
cidr: 10.0.56.0/24
- ipBlock:
cidr: 10.0.57.0/24
- ipBlock:
cidr: 10.0.58.0/24
- ipBlock:
cidr: 10.0.68.0/27
ports:
- port: 8080
protocol: TCP
egress:
# CoreDNS.
- to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: kube-system
podSelector:
matchLabels:
k8s-app: kube-dns
ports:
- port: 53
protocol: UDP
- port: 53
protocol: TCP
# Database namespace.
- to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: fc-mysql
ports:
- port: 3306
protocol: TCP
# Redis backplane for multi-replica SignalR / live-status fan-out.
- to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: fc-redis
ports:
- port: 6379
protocol: TCP
# Traefik VIP / in-cluster Traefik for self-callbacks and public URL
# generation tests. Include post-DNAT backend ports 8443 + 8080.
- to:
- ipBlock:
cidr: 10.0.56.200/32
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: traefik-system
podSelector:
matchLabels:
app.kubernetes.io/name: traefik
ports:
- port: 80
protocol: TCP
- port: 443
protocol: TCP
- port: 8080
protocol: TCP
- port: 8443
protocol: TCP
# Agent egress: LAN/VPN devices may run DM Agent in Generic, Kiosk, Pi,
# ThinClient, or Server mode. Keep this private-range only.
- to:
- ipBlock:
cidr: 10.0.56.0/24
- ipBlock:
cidr: 10.0.57.0/24
- ipBlock:
cidr: 10.0.58.0/24
- ipBlock:
cidr: 10.0.68.0/27
ports:
- port: 80
protocol: TCP
- port: 443
protocol: TCP
- port: 8080
protocol: TCP
- port: 8443
protocol: TCP
- port: 5000
protocol: TCP
- port: 5001
protocol: TCP
# Synology NFS cold-tier / artifact mount allowance.
- to:
- ipBlock:
cidr: 10.0.58.3/32
ports:
- port: 2049
protocol: TCP
- port: 2049
protocol: UDP
- port: 111
protocol: TCP
- port: 111
protocol: UDP
---
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: fc-devicemgmt-operator-isolation
namespace: fc-devicemgmt
labels:
app.kubernetes.io/name: fc-devicemgmt-operator
app.kubernetes.io/component: operator
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
podSelector:
matchLabels:
app: fc-devicemgmt-operator
policyTypes:
- Ingress
- Egress
ingress:
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: monitoring
ports:
- port: 8080
protocol: TCP
egress:
# CoreDNS.
- to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: kube-system
podSelector:
matchLabels:
k8s-app: kube-dns
ports:
- port: 53
protocol: UDP
- port: 53
protocol: TCP
# Kubernetes API for KubeOps reconciliation and Deployment UID lookup.
- to: []
ports:
- port: 443
protocol: TCP
- port: 6443
protocol: TCP
# Agent egress for operator-initiated probes / fallback command dispatch.
- to:
- ipBlock:
cidr: 10.0.56.0/24
- ipBlock:
cidr: 10.0.57.0/24
- ipBlock:
cidr: 10.0.58.0/24
- ipBlock:
cidr: 10.0.68.0/27
ports:
- port: 80
protocol: TCP
- port: 443
protocol: TCP
- port: 8080
protocol: TCP
- port: 8443
protocol: TCP
- port: 5000
protocol: TCP
- port: 5001
protocol: TCP
# Synology NFS allowance for future cold-tier/audit archival jobs.
- to:
- ipBlock:
cidr: 10.0.58.3/32
ports:
- port: 2049
protocol: TCP
- port: 2049
protocol: UDP
- port: 111
protocol: TCP
- port: 111
protocol: UDP

View File

@@ -0,0 +1,22 @@
apiVersion: v1
kind: Service
metadata:
name: fc-devicemgmt-web
namespace: fc-devicemgmt
labels:
app: fc-devicemgmt-web
app.kubernetes.io/name: fc-devicemgmt-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
type: ClusterIP
selector:
app: fc-devicemgmt-web
ports:
- name: http
port: 80
targetPort: 8080
protocol: TCP

View File

@@ -0,0 +1,12 @@
apiVersion: v1
kind: ServiceAccount
metadata:
name: fc-devicemgmt-operator
namespace: fc-devicemgmt
labels:
app.kubernetes.io/name: fc-devicemgmt-operator
app.kubernetes.io/component: operator
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra

View File

@@ -0,0 +1,14 @@
# fc-signage-appletv
Apple TV signage is a sealed appliance running the `FlowerCore.Signage.Agent.AppleTv` tvOS app per ADR-134.
This ApplicationSet entry is documentation and inventory metadata only. It intentionally creates no `Deployment`, `Service`, or `Pod`.
The Apple TV app connects outbound to existing FC.Signage.Web surfaces:
- `https://signage.iamworkin.lan/hub/signage` for SignalR live status.
- `GET /api/v1/nodes/{nodeId}/state` for the 30 second polling fallback.
- `POST /api/v1/nodes/register` and `POST /api/v1/nodes/{nodeId}/enroll` for pairing and mTLS enrollment.
- `POST /api/v1/nodes/{nodeId}/heartbeat` for metrics, current content identity, and local audit excerpts.
Distribution is via Apple Developer Enterprise Program or TestFlight plus FC.Distribution / UpdateCenter publishing once Apple credentials are available.

View File

@@ -0,0 +1,5 @@
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
resources:
- manifest.yaml

View File

@@ -0,0 +1,26 @@
# Apple TV signage is a sealed tvOS appliance. This ArgoCD app intentionally
# carries documentation metadata only; no Deployment, Service, or Pod resources
# are created for the player.
---
apiVersion: v1
kind: ConfigMap
metadata:
name: fc-signage-appletv-docs
namespace: fc-signage
labels:
app.kubernetes.io/name: fc-signage-appletv
app.kubernetes.io/part-of: flowercore-signage
flowercore.io/manifest-kind: docs-only
data:
README: |
FlowerCore.Signage.Agent.AppleTv is distributed through Apple Developer
Enterprise Program or TestFlight, not Kubernetes.
The app connects outbound to FC.Signage.Web:
- SignalR: https://signage.iamworkin.lan/hub/signage
- Polling fallback: GET /api/v1/nodes/{nodeId}/state
- Enrollment: POST /api/v1/nodes/{nodeId}/enroll
- Heartbeat: POST /api/v1/nodes/{nodeId}/heartbeat
This placeholder gives ArgoCD and inventory dashboards a first-class
Apple TV signage app entry without creating runtime pods.

View File

@@ -0,0 +1,17 @@
# FlowerCore Signage Pi Player
Phase 1 Raspberry Pi signage player packaging for Chromium kiosk deployments.
This bundle is intentionally air-gap friendly: systemd units, shell scripts,
udev rules, and Chromium managed policy are all checked into the repo and are
installed by `FlowerCore.Puppet`.
## Scope
- Bootstrap a stable node identity and mTLS client certificate.
- Launch Chromium in kiosk mode against `FC.Signage.Web` player routes.
- Restart the kiosk on HDMI hotplug.
- Renew mTLS certificates daily when fewer than 30 days remain.
- Detect display capabilities at boot, daily, and on HDMI hotplug.
Phase 2 native Avalonia rendering is documented separately in Notes and remains
deferred.

View File

@@ -0,0 +1,15 @@
{
"AutofillAddressEnabled": false,
"AutofillCreditCardEnabled": false,
"PasswordManagerEnabled": false,
"BrowserSignin": 0,
"MetricsReportingEnabled": false,
"SafeBrowsingProtectionLevel": 0,
"DefaultNotificationsSetting": 2,
"DefaultPopupsSetting": 2,
"BackgroundModeEnabled": false,
"DefaultBrowserSettingEnabled": false,
"PromotionalTabsEnabled": false,
"CommandLineFlagSecurityWarningsEnabled": false,
"ExtensionInstallBlocklist": ["*"]
}

View File

@@ -0,0 +1,132 @@
#!/usr/bin/env bash
set -euo pipefail
NODE_JSON="/etc/flowercore/signage-node.json"
CERT_DIR="/etc/fc-signage-player"
SIGNAGE_URL="${FC_SIGNAGE_URL:-https://signage.iamworkin.lan}"
NODE_ID=$(jq -r '.nodeId' "$NODE_JSON")
CONNECTORS=()
for dir in /sys/class/drm/card*-HDMI-A-*; do
[[ -e "$dir/status" ]] || continue
if [[ "$(cat "$dir/status")" == "connected" ]]; then
CONNECTORS+=("$(basename "$dir")")
fi
done
if [[ ${#CONNECTORS[@]} -eq 0 ]]; then
CAPABILITIES_JSON=$(jq -n --arg id "$NODE_ID" '{
nodeId: $id,
platform: "linux-arm64-pi",
displayConnected: false,
detectedAt: (now | todate),
note: "No HDMI display detected"
}')
else
PRIMARY="${CONNECTORS[0]}"
EDID_PATH="/sys/class/drm/${PRIMARY}/edid"
WIDTH=0
HEIGHT=0
REFRESH=60
HDR=false
AUDIO_HDMI=false
MFG=""
MODEL=""
PHYSICAL_SIZE=null
if [[ -s "$EDID_PATH" ]] && command -v edid-decode >/dev/null 2>&1; then
EDID_INFO=$(edid-decode < "$EDID_PATH" 2>/dev/null || true)
MFG=$(echo "$EDID_INFO" | grep -m1 -oP 'Manufacturer:\s*\K\S+' || true)
MODEL=$(echo "$EDID_INFO" | grep -m1 -oP 'Model:\s*\K\S+' || true)
PREF=$(echo "$EDID_INFO" | grep -m1 -oP '\d+x\d+\s*@\s*\d+(?:\.\d+)?\s*Hz' || true)
if [[ -n "$PREF" ]]; then
WIDTH=$(echo "$PREF" | grep -oP '^\d+')
HEIGHT=$(echo "$PREF" | grep -oP 'x\K\d+')
REFRESH=$(echo "$PREF" | grep -oP '@\s*\K[\d.]+' | cut -d. -f1)
fi
if echo "$EDID_INFO" | grep -qiE 'HDR (Static|Dynamic) Metadata Block'; then HDR=true; fi
if echo "$EDID_INFO" | grep -qiE 'CEA Audio Block|Audio Format Descriptor'; then AUDIO_HDMI=true; fi
PH_W=$(echo "$EDID_INFO" | grep -m1 -oP 'Maximum image size:\s*\K\d+\s*cm\s*x\s*\d+' || true)
if [[ -n "$PH_W" ]]; then
PH_CM_W=$(echo "$PH_W" | grep -oP '^\d+')
PH_CM_H=$(echo "$PH_W" | grep -oP 'x\s*\K\d+')
if (( PH_CM_W > 0 && PH_CM_H > 0 )); then
PHYSICAL_SIZE=$(awk -v w="$PH_CM_W" -v h="$PH_CM_H" 'BEGIN { printf "%.1f", sqrt(w*w + h*h)/2.54 }')
fi
fi
fi
if [[ "$WIDTH" == "0" ]] && command -v kmsprint >/dev/null 2>&1; then
KMS=$(kmsprint 2>/dev/null | grep -A2 "$PRIMARY" | grep -oP '\d+x\d+' | head -1 || true)
if [[ -n "$KMS" ]]; then
WIDTH=$(echo "$KMS" | grep -oP '^\d+')
HEIGHT=$(echo "$KMS" | grep -oP 'x\K\d+')
fi
fi
AUDIO_ALSA=false
if aplay -l 2>/dev/null | grep -qi 'card.*HDMI'; then AUDIO_ALSA=true; fi
HAS_AUDIO=false
if [[ "$AUDIO_HDMI" == "true" && "$AUDIO_ALSA" == "true" ]]; then HAS_AUDIO=true; fi
CAPABILITIES_JSON=$(jq -n \
--arg id "$NODE_ID" \
--argjson w "$WIDTH" \
--argjson h "$HEIGHT" \
--argjson r "$REFRESH" \
--argjson hdr "$HDR" \
--argjson audio "$HAS_AUDIO" \
--arg connector "$PRIMARY" \
--arg mfg "$MFG" \
--arg model "$MODEL" \
--argjson size "$PHYSICAL_SIZE" \
'{
nodeId: $id,
platform: "linux-arm64-pi",
displayConnected: true,
detectedAt: (now | todate),
hardware: {
maxResolution: { width: $w, height: $h },
nativeResolution: { width: $w, height: $h },
refreshRateHz: $r,
colorDepth: ($hdr | if . then "Color30Hdr" else "Color24" end),
hasAudioOutput: $audio,
audioChannelCount: ($audio | if . then 2 else 0 end),
physicalSizeInches: $size,
connector: $connector,
manufacturer: $mfg,
modelName: $model
},
render: { codecs: ["h264", "vp9", "mp4"] }
}')
fi
ENDPOINT_CANDIDATES=(
"${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/capabilities"
"${SIGNAGE_URL}/api/v1/displays/${NODE_ID}/capability-profile"
)
SUCCESS=false
for url in "${ENDPOINT_CANDIDATES[@]}"; do
HTTP_STATUS=$(curl -sk -o /tmp/cap-response.json -w "%{http_code}" \
--max-time 10 \
--cert "$CERT_DIR/client.crt" --key "$CERT_DIR/client.key" \
-X POST "$url" \
-H "Content-Type: application/json" \
-d "$CAPABILITIES_JSON" || echo "000")
if [[ "$HTTP_STATUS" == "200" || "$HTTP_STATUS" == "201" || "$HTTP_STATUS" == "204" ]]; then
SUCCESS=true
break
fi
done
mkdir -p /var/log/fc-signage-player
if [[ "$SUCCESS" != "true" ]]; then
echo "[$(date -Is)] capability declare: no endpoint accepted the profile; logging locally" \
| tee -a /var/log/fc-signage-player/capabilities.log
echo "$CAPABILITIES_JSON" | tee -a /var/log/fc-signage-player/capabilities.log
else
echo "[$(date -Is)] capability declare: ok ($url)" | tee -a /var/log/fc-signage-player/capabilities.log
fi
echo "$CAPABILITIES_JSON"

View File

@@ -0,0 +1,144 @@
#!/usr/bin/env bash
set -euo pipefail
NODE_JSON="/etc/flowercore/signage-node.json"
CERT_DIR="/etc/fc-signage-player"
SIGNAGE_URL="${FC_SIGNAGE_URL:-https://signage.iamworkin.lan}"
SETUP_CODE_FILE="/etc/flowercore/signage-setup-code"
mkdir -p /etc/flowercore "$CERT_DIR" /var/log/fc-signage-player
chown fc-signage:fc-signage /etc/flowercore "$CERT_DIR" /var/log/fc-signage-player
chmod 0750 "$CERT_DIR"
if [[ -s "$NODE_JSON" && -s "$CERT_DIR/client.p12" ]]; then
ENROLLED=$(jq -r '.enrolledAt // empty' "$NODE_JSON")
if [[ -n "$ENROLLED" ]]; then
echo "[$(date -Is)] bootstrap: already enrolled at $ENROLLED; skipping"
exit 0
fi
fi
if [[ -s "$NODE_JSON" ]]; then
NODE_UUID=$(jq -r '.nodeUuid // empty' "$NODE_JSON")
MACHINE_ID=$(jq -r '.machineId // empty' "$NODE_JSON")
else
NODE_UUID=$(uuidgen)
MACHINE_ID=$(echo "$NODE_UUID" | tr -d '-' | cut -c1-16)
jq -n --arg uuid "$NODE_UUID" --arg machine "$MACHINE_ID" --arg host "$(hostname -f)" --arg ts "$(date -Is)" \
'{nodeUuid: $uuid, machineId: $machine, hostname: $host, platform: "linux-arm64-pi", createdAt: $ts}' \
> "$NODE_JSON"
chmod 0640 "$NODE_JSON"
chown fc-signage:fc-signage "$NODE_JSON"
fi
SETUP_CODE=""
if [[ -s "$SETUP_CODE_FILE" ]]; then
SETUP_CODE=$(tr -d '\r\n\t ' < "$SETUP_CODE_FILE")
fi
MODEL=$(tr -d '\0' < /sys/firmware/devicetree/base/model 2>/dev/null || echo Unknown)
REG_PAYLOAD=$(jq -n \
--arg machine "$MACHINE_ID" \
--arg name "$(hostname -f)" \
--arg setup "$SETUP_CODE" \
--arg resolution "1920x1080" \
--arg model "$MODEL" \
'{
machineId: $machine,
name: $name,
setupCode: ($setup | if . == "" then null else . end),
resolution: $resolution,
hardwareModel: $model,
platform: "linux-arm64-pi"
}')
for attempt in 1 2; do
HTTP_STATUS=$(curl -sk -o /tmp/register-response.json -w "%{http_code}" \
--max-time 15 \
-X POST "${SIGNAGE_URL}/api/v1/nodes/register" \
-H "Content-Type: application/json" \
-d "$REG_PAYLOAD" || echo "000")
if [[ "$HTTP_STATUS" == "200" || "$HTTP_STATUS" == "201" ]]; then
break
fi
echo "[$(date -Is)] bootstrap: register attempt $attempt returned $HTTP_STATUS" >&2
sleep 5
done
if [[ "$HTTP_STATUS" != "200" && "$HTTP_STATUS" != "201" ]]; then
echo "[$(date -Is)] bootstrap: register failed after 2 attempts" >&2
exit 2
fi
NODE_ID=$(jq -r '.nodeId // empty' /tmp/register-response.json)
if [[ -z "$NODE_ID" ]]; then
echo "[$(date -Is)] bootstrap: register response did not include nodeId" >&2
exit 2
fi
jq --arg id "$NODE_ID" '.nodeId = $id' "$NODE_JSON" > "${NODE_JSON}.tmp" && mv "${NODE_JSON}.tmp" "$NODE_JSON"
if [[ -s "$SETUP_CODE_FILE" ]]; then
curl -sk -X POST "${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/approve-via-setup-code" \
-H "Content-Type: application/json" \
-d "{\"setupCode\":\"${SETUP_CODE}\"}" \
-o /dev/null || true
fi
STATUS=""
DEADLINE=$(( $(date +%s) + 1800 ))
while (( $(date +%s) < DEADLINE )); do
STATUS=$(curl -sk --max-time 5 "${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/status" | jq -r '.status // empty')
if [[ "$STATUS" == "Approved" || "$STATUS" == "Enrolled" || "$STATUS" == "Online" ]]; then
break
fi
sleep 15
done
if [[ "$STATUS" != "Approved" && "$STATUS" != "Enrolled" && "$STATUS" != "Online" ]]; then
echo "[$(date -Is)] bootstrap: approval not granted within 30min budget" >&2
exit 3
fi
KEY_PATH="${CERT_DIR}/client.key"
CSR_PATH="${CERT_DIR}/client.csr"
openssl ecparam -genkey -name prime256v1 -out "$KEY_PATH"
openssl req -new -key "$KEY_PATH" -out "$CSR_PATH" \
-subj "/CN=${NODE_ID}/O=FlowerCore/OU=SignagePlayer-Pi"
ENROLL_PAYLOAD=$(jq -n --arg csr "$(cat "$CSR_PATH")" '{certificateSigningRequest: $csr}')
HTTP_STATUS=$(curl -sk -o /tmp/enroll-response.json -w "%{http_code}" \
--max-time 15 \
-X POST "${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/enroll" \
-H "Content-Type: application/json" \
-d "$ENROLL_PAYLOAD")
if [[ "$HTTP_STATUS" != "200" && "$HTTP_STATUS" != "201" ]]; then
echo "[$(date -Is)] bootstrap: enroll failed with HTTP $HTTP_STATUS" >&2
exit 4
fi
jq -r '.clientCertificatePem // .signedCertificatePem' /tmp/enroll-response.json > "${CERT_DIR}/client.crt"
jq -r '.caCertificatePem' /tmp/enroll-response.json > "${CERT_DIR}/ca-chain.pem"
P12_PASS=$(openssl rand -hex 24)
echo -n "$P12_PASS" > "${CERT_DIR}/client.p12.pass"
chmod 0600 "${CERT_DIR}/client.p12.pass"
openssl pkcs12 -export \
-inkey "$KEY_PATH" \
-in "${CERT_DIR}/client.crt" \
-certfile "${CERT_DIR}/ca-chain.pem" \
-out "${CERT_DIR}/client.p12" \
-password "pass:${P12_PASS}"
chown fc-signage:fc-signage "${CERT_DIR}"/* "$NODE_JSON"
chmod 0640 "${CERT_DIR}/client.p12" "${CERT_DIR}/client.crt" "${CERT_DIR}/ca-chain.pem" "$KEY_PATH"
chmod 0600 "${CERT_DIR}/client.p12.pass"
EXPIRY=$(openssl x509 -in "${CERT_DIR}/client.crt" -enddate -noout | sed 's/notAfter=//')
jq --arg ts "$(date -Is)" --arg exp "$EXPIRY" \
'.enrolledAt = $ts | .certExpiry = $exp' "$NODE_JSON" > "${NODE_JSON}.tmp" \
&& mv "${NODE_JSON}.tmp" "$NODE_JSON"
systemctl start flowercore-signage-detect-display.service || true
systemctl start flowercore-signage-player-pi.service || true
echo "[$(date -Is)] bootstrap: enrolled and kiosk started (NodeId=${NODE_ID})"

View File

@@ -0,0 +1,6 @@
#!/usr/bin/env bash
set -euo pipefail
sleep 2
systemctl start flowercore-signage-detect-display.service || true
systemctl restart flowercore-signage-player-pi.service

View File

@@ -0,0 +1,44 @@
#!/usr/bin/env bash
set -euo pipefail
NODE_JSON="/etc/flowercore/signage-node.json"
NODE_ID=$(jq -r '.nodeId' "$NODE_JSON")
SIGNAGE_URL="${FC_SIGNAGE_URL:-https://signage.iamworkin.lan}"
CERT_DIR="/etc/fc-signage-player"
CERT_THUMB=$(openssl pkcs12 -in "$CERT_DIR/client.p12" -passin file:"$CERT_DIR/client.p12.pass" -nodes -nokeys 2>/dev/null \
| openssl x509 -fingerprint -sha256 -noout \
| sed 's/.*=//' \
| tr -d ':')
PLAYER_URL="${SIGNAGE_URL}/player/${NODE_ID}/embed?token=${CERT_THUMB}"
HTTP_STATUS=$(curl -sk -o /dev/null -w "%{http_code}" --max-time 5 \
--cert-type P12 --cert "$CERT_DIR/client.p12:$(cat "$CERT_DIR/client.p12.pass")" \
"$PLAYER_URL" || echo "000")
mkdir -p /var/log/fc-signage-player
if [[ "$HTTP_STATUS" != "200" && "$HTTP_STATUS" != "301" && "$HTTP_STATUS" != "302" ]]; then
echo "[$(date -Is)] /embed returned $HTTP_STATUS; falling back to /player/${NODE_ID}" \
>> /var/log/fc-signage-player/url-divergence.log
PLAYER_URL="${SIGNAGE_URL}/player/${NODE_ID}?token=${CERT_THUMB}"
fi
exec chromium-browser \
--kiosk \
--noerrdialogs \
--disable-infobars \
--disable-translate \
--disable-features=TranslateUI,InfiniteSessionRestore \
--autoplay-policy=no-user-gesture-required \
--password-store=basic \
--user-data-dir=/var/lib/fc-signage-player/profile \
--disk-cache-dir=/var/lib/fc-signage-player/cache \
--disk-cache-size=104857600 \
--no-first-run \
--no-default-browser-check \
--check-for-update-interval=2592000 \
--enable-features=OverlayScrollbar \
--start-fullscreen \
--window-position=0,0 \
--window-size=1920,1080 \
"$PLAYER_URL"

View File

@@ -0,0 +1,20 @@
#!/usr/bin/env bash
set -euo pipefail
mkdir -p /var/log/fc-signage-player
for f in /etc/flowercore/signage-node.json /etc/fc-signage-player/client.p12 /etc/fc-signage-player/client.p12.pass; do
if [[ ! -r "$f" ]]; then
echo "[$(date -Is)] prelaunch: missing or unreadable $f" >&2
exit 1
fi
done
if openssl pkcs12 -in /etc/fc-signage-player/client.p12 -passin file:/etc/fc-signage-player/client.p12.pass -nokeys -clcerts 2>/dev/null \
| openssl x509 -checkend $((7*24*3600)) -noout; then
:
else
echo "[$(date -Is)] prelaunch: client cert expires within 7 days" >&2
fi
echo "[$(date -Is)] prelaunch: ok" | tee -a /var/log/fc-signage-player/prelaunch.log

View File

@@ -0,0 +1,46 @@
#!/usr/bin/env bash
set -euo pipefail
CERT_DIR="/etc/fc-signage-player"
NODE_JSON="/etc/flowercore/signage-node.json"
SIGNAGE_URL="${FC_SIGNAGE_URL:-https://signage.iamworkin.lan}"
[[ -s "$CERT_DIR/client.crt" ]] || { echo "no cert to renew"; exit 0; }
if openssl x509 -in "$CERT_DIR/client.crt" -checkend $((30*24*3600)) -noout; then
exit 0
fi
NODE_ID=$(jq -r '.nodeId' "$NODE_JSON")
NEW_KEY="$CERT_DIR/client.key.new"
NEW_CSR="$CERT_DIR/client.csr.new"
openssl ecparam -genkey -name prime256v1 -out "$NEW_KEY"
openssl req -new -key "$NEW_KEY" -out "$NEW_CSR" \
-subj "/CN=${NODE_ID}/O=FlowerCore/OU=SignagePlayer-Pi"
HTTP_STATUS=$(curl -sk -o /tmp/renew-response.json -w "%{http_code}" \
--cert "$CERT_DIR/client.crt" --key "$CERT_DIR/client.key" \
-X POST "${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/renew" \
-H "Content-Type: application/json" \
-d "$(jq -n --arg csr "$(cat "$NEW_CSR")" '{certificateSigningRequest: $csr}')")
if [[ "$HTTP_STATUS" != "200" && "$HTTP_STATUS" != "201" ]]; then
echo "[$(date -Is)] renew: failed HTTP $HTTP_STATUS; leaving old cert in place" >&2
exit 5
fi
jq -r '.clientCertificatePem // .signedCertificatePem' /tmp/renew-response.json > "$CERT_DIR/client.crt.new"
jq -r '.caCertificatePem' /tmp/renew-response.json > "$CERT_DIR/ca-chain.pem.new"
P12_PASS=$(cat "$CERT_DIR/client.p12.pass")
openssl pkcs12 -export -inkey "$NEW_KEY" -in "$CERT_DIR/client.crt.new" \
-certfile "$CERT_DIR/ca-chain.pem.new" \
-out "$CERT_DIR/client.p12.new" -password "pass:${P12_PASS}"
mv "$CERT_DIR/client.key.new" "$CERT_DIR/client.key"
mv "$CERT_DIR/client.crt.new" "$CERT_DIR/client.crt"
mv "$CERT_DIR/ca-chain.pem.new" "$CERT_DIR/ca-chain.pem"
mv "$CERT_DIR/client.p12.new" "$CERT_DIR/client.p12"
chown fc-signage:fc-signage "$CERT_DIR"/client.*
systemctl restart flowercore-signage-player-pi.service

View File

@@ -0,0 +1,2 @@
# Settle DRM for 2s before restarting Chromium, then redeclare capabilities.
SUBSYSTEM=="drm", KERNEL=="card?-HDMI-A-?", ACTION=="change", RUN+="/usr/bin/systemctl start flowercore-signage-player-pi-hdmi.service"

View File

@@ -0,0 +1,16 @@
[Unit]
Description=FlowerCore Signage Pi: first-boot identity + mTLS enrollment
Wants=network-online.target
After=network-online.target
Before=flowercore-signage-player-pi.service
[Service]
Type=oneshot
ExecStart=/usr/local/bin/flowercore-signage-bootstrap.sh
RemainAfterExit=yes
StandardOutput=journal
StandardError=journal
TimeoutStartSec=2100
[Install]
WantedBy=multi-user.target

View File

@@ -0,0 +1,8 @@
[Unit]
Description=FlowerCore Signage Pi: detect connected display + declare capabilities
After=flowercore-signage-bootstrap.service
[Service]
Type=oneshot
User=fc-signage
ExecStart=/usr/local/bin/fc-signage-detect-display

View File

@@ -0,0 +1,11 @@
[Unit]
Description=Daily FlowerCore Signage Pi display capability redeclaration
[Timer]
OnCalendar=daily
RandomizedDelaySec=1h
Persistent=true
OnBootSec=30s
[Install]
WantedBy=timers.target

View File

@@ -0,0 +1,7 @@
[Unit]
Description=FlowerCore Signage Pi Player HDMI hotplug responder
DefaultDependencies=no
[Service]
Type=oneshot
ExecStart=/usr/local/bin/flowercore-signage-hdmi-respond.sh

View File

@@ -0,0 +1,30 @@
[Unit]
Description=FlowerCore Digital Signage Pi Player (Chromium kiosk)
Documentation=https://github.com/astoltz/FlowerCore.Notes/blob/master/docs/standards/appletv-pi-signage-agents-design.md
Wants=network-online.target
After=network-online.target graphical.target
ConditionPathExists=/etc/flowercore/signage-node.json
ConditionPathExists=/etc/fc-signage-player/client.p12
[Service]
Type=simple
User=fc-signage
Group=fc-signage
WorkingDirectory=/var/lib/fc-signage-player
EnvironmentFile=-/etc/flowercore/signage-player.env
ExecStartPre=/usr/local/bin/flowercore-signage-prelaunch.sh
ExecStart=/usr/local/bin/flowercore-signage-launch.sh
Restart=always
RestartSec=10s
StartLimitBurst=5
StartLimitIntervalSec=300s
MemoryMax=2G
MemoryHigh=1500M
ProtectSystem=strict
ProtectHome=true
ReadWritePaths=/var/lib/fc-signage-player /var/log/fc-signage-player
PrivateTmp=true
NoNewPrivileges=true
[Install]
WantedBy=graphical.target

View File

@@ -0,0 +1,6 @@
[Unit]
Description=FlowerCore Signage Pi: cert renewal worker
[Service]
Type=oneshot
ExecStart=/usr/local/bin/flowercore-signage-renew-cert.sh

View File

@@ -0,0 +1,10 @@
[Unit]
Description=Daily check for FlowerCore Signage Pi cert renewal
[Timer]
OnCalendar=daily
RandomizedDelaySec=2h
Persistent=true
[Install]
WantedBy=timers.target

View File

@@ -0,0 +1,22 @@
#!/usr/bin/env bats
setup() {
APP_ROOT="$(cd "$BATS_TEST_DIRNAME/.." && pwd)"
DETECT="$APP_ROOT/scripts/fc-signage-detect-display"
}
@test "display detection emits graceful disconnected profile when no hdmi connector is present" {
script="$(cat "$DETECT")"
[[ "$script" == *"displayConnected: false"* ]]
[[ "$script" == *"No HDMI display detected"* ]]
}
@test "display detection parses edid, falls back to kmsprint, and logs endpoint failures locally" {
script="$(cat "$DETECT")"
[[ "$script" == *"edid-decode"* ]]
[[ "$script" == *"HDR (Static|Dynamic) Metadata Block"* ]]
[[ "$script" == *"kmsprint"* ]]
[[ "$script" == *"/api/v1/nodes/\${NODE_ID}/capabilities"* ]]
[[ "$script" == *"/api/v1/displays/\${NODE_ID}/capability-profile"* ]]
[[ "$script" == *"capabilities.log"* ]]
}

View File

@@ -0,0 +1,64 @@
#!/usr/bin/env bats
setup() {
APP_ROOT="$(cd "$BATS_TEST_DIRNAME/.." && pwd)"
BOOTSTRAP="$APP_ROOT/scripts/flowercore-signage-bootstrap.sh"
RENEW="$APP_ROOT/scripts/flowercore-signage-renew-cert.sh"
}
@test "bootstrap is idempotent when node is already enrolled" {
script="$(cat "$BOOTSTRAP")"
[[ "$script" == *'[[ -s "$NODE_JSON" && -s "$CERT_DIR/client.p12" ]]'* ]]
[[ "$script" == *"already enrolled"* ]]
[[ "$script" == *"exit 0"* ]]
}
@test "bootstrap generates a stable node uuid and machine id" {
script="$(cat "$BOOTSTRAP")"
[[ "$script" == *"uuidgen"* ]]
[[ "$script" == *"nodeUuid"* ]]
[[ "$script" == *"machineId"* ]]
[[ "$script" == *"cut -c1-16"* ]]
}
@test "bootstrap posts to the canonical register endpoint" {
grep -q '/api/v1/nodes/register' "$BOOTSTRAP"
grep -q '"linux-arm64-pi"' "$BOOTSTRAP"
}
@test "bootstrap retries registration once for first-call races" {
script="$(cat "$BOOTSTRAP")"
[[ "$script" == *"for attempt in 1 2"* ]]
[[ "$script" == *"register attempt \$attempt returned"* ]]
[[ "$script" == *"sleep 5"* ]]
}
@test "bootstrap supports setup-code approval with manual polling fallback" {
script="$(cat "$BOOTSTRAP")"
[[ "$script" == *"signage-setup-code"* ]]
[[ "$script" == *"approve-via-setup-code"* ]]
[[ "$script" == *"+ 1800"* ]]
[[ "$script" == *"sleep 15"* ]]
}
@test "bootstrap generates an ecdsa p256 csr for the signage pi subject" {
script="$(cat "$BOOTSTRAP")"
[[ "$script" == *"ecparam -genkey -name prime256v1"* ]]
[[ "$script" == *'/CN=${NODE_ID}/O=FlowerCore/OU=SignagePlayer-Pi'* ]]
}
@test "bootstrap writes pkcs12 bundle with restrictive permissions" {
script="$(cat "$BOOTSTRAP")"
[[ "$script" == *"openssl pkcs12 -export"* ]]
[[ "$script" == *"client.p12.pass"* ]]
[[ "$script" == *"chmod 0640"* ]]
[[ "$script" == *"chmod 0600"* ]]
}
@test "renewal only calls renew endpoint inside the thirty-day window and swaps atomically" {
script="$(cat "$RENEW")"
[[ "$script" == *'-checkend $((30*24*3600))'* ]]
[[ "$script" == *"/api/v1/nodes/\${NODE_ID}/renew"* ]]
[[ "$script" == *"client.key.new"* ]]
[[ "$script" == *'mv "$CERT_DIR/client.p12.new" "$CERT_DIR/client.p12"'* ]]
}

View File

@@ -0,0 +1,68 @@
#!/usr/bin/env bats
setup() {
APP_ROOT="$(cd "$BATS_TEST_DIRNAME/.." && pwd)"
}
@test "player unit exists" {
[ -f "$APP_ROOT/systemd/flowercore-signage-player-pi.service" ]
}
@test "player unit uses simple chromium service with restart backoff" {
unit="$(cat "$APP_ROOT/systemd/flowercore-signage-player-pi.service")"
[[ "$unit" == *"Type=simple"* ]]
[[ "$unit" == *"Restart=always"* ]]
[[ "$unit" == *"RestartSec=10s"* ]]
[[ "$unit" == *"StartLimitBurst=5"* ]]
[[ "$unit" == *"StartLimitIntervalSec=300s"* ]]
}
@test "player unit caps chromium memory at two gigabytes" {
grep -q '^MemoryMax=2G$' "$APP_ROOT/systemd/flowercore-signage-player-pi.service"
grep -q '^MemoryHigh=1500M$' "$APP_ROOT/systemd/flowercore-signage-player-pi.service"
}
@test "player unit condition-gates startup on identity and p12 certificate" {
grep -q '^ConditionPathExists=/etc/flowercore/signage-node.json$' "$APP_ROOT/systemd/flowercore-signage-player-pi.service"
grep -q '^ConditionPathExists=/etc/fc-signage-player/client.p12$' "$APP_ROOT/systemd/flowercore-signage-player-pi.service"
}
@test "player unit runs prelaunch checks before chromium" {
grep -q '^ExecStartPre=/usr/local/bin/flowercore-signage-prelaunch.sh$' "$APP_ROOT/systemd/flowercore-signage-player-pi.service"
grep -q '^ExecStart=/usr/local/bin/flowercore-signage-launch.sh$' "$APP_ROOT/systemd/flowercore-signage-player-pi.service"
}
@test "hdmi udev rule routes through the two-second settle service" {
rule="$(cat "$APP_ROOT/systemd/99-flowercore-signage-hdmi.rules")"
[[ "$rule" == *'KERNEL=="card?-HDMI-A-?"'* ]]
[[ "$rule" == *"systemctl start flowercore-signage-player-pi-hdmi.service"* ]]
[[ "$rule" != *"systemctl restart flowercore-signage-player-pi.service"* ]]
}
@test "hdmi responder settles, declares display, then restarts chromium" {
responder="$(cat "$APP_ROOT/scripts/flowercore-signage-hdmi-respond.sh")"
[[ "$responder" == *"sleep 2"* ]]
[[ "$responder" == *"systemctl start flowercore-signage-detect-display.service"* ]]
[[ "$responder" == *"systemctl restart flowercore-signage-player-pi.service"* ]]
}
@test "chromium policy json is valid and disables credential prompts" {
command -v jq >/dev/null || skip "jq not installed"
jq -e '.AutofillAddressEnabled == false and .AutofillCreditCardEnabled == false and .PasswordManagerEnabled == false' \
"$APP_ROOT/chromium-policies/flowercore-signage.json" >/dev/null
}
@test "launch script tries embed URL and logs bare-player fallback" {
launch="$(cat "$APP_ROOT/scripts/flowercore-signage-launch.sh")"
[[ "$launch" == *'/player/${NODE_ID}/embed?token=${CERT_THUMB}'* ]]
[[ "$launch" == *"url-divergence.log"* ]]
[[ "$launch" == *'/player/${NODE_ID}?token=${CERT_THUMB}'* ]]
}
@test "prelaunch script validates required node and cert files" {
prelaunch="$(cat "$APP_ROOT/scripts/flowercore-signage-prelaunch.sh")"
[[ "$prelaunch" == *"/etc/flowercore/signage-node.json"* ]]
[[ "$prelaunch" == *"/etc/fc-signage-player/client.p12"* ]]
[[ "$prelaunch" == *"/etc/fc-signage-player/client.p12.pass"* ]]
[[ "$prelaunch" == *"exit 1"* ]]
}

View File

@@ -0,0 +1,398 @@
# GitHub Actions self-hosted Linux runner — Phase 2 K8s deployment
#
# Phase 1 (current): BLUEJAY-WS registered manually as a Windows runner
# with label "fc-build-windows" via config.cmd (see docs/infrastructure/
# self-hosted-runner-fleet.md §WPF Build Runner).
#
# Phase 2 (this file): ephemeral Linux runner in RKE2 for non-WPF builds
# (Blazor Server, class libraries, operators, integration tests). Reduces
# billing for ubuntu-24.04 jobs that run on GitHub-hosted runners today.
#
# Runner image: myoung34/github-runner:latest
# EPHEMERAL=true — each pod runs exactly one job then exits; the
# Deployment controller immediately recreates it and re-registers.
# Prevents job queue starvation when two jobs overlap.
#
# NuGet cache: 5Gi Longhorn RWO PVC mounted at /home/runner/.nuget/packages
# Persists NuGet packages across ephemeral pod restarts (not shared across
# simultaneous runner pods; single-replica constraint below).
#
# Credentials:
# OnePasswordItem "GitHub PAT (Runner Registration)" → Secret
# github-runner-token with field "credential" used as RUNNER_TOKEN.
# Operator must create/rotate the 1P item manually; registration tokens
# expire after 1h — use a fine-grained PAT with Administration:read/write
# scope on the target repos, or a re-registration script. See
# docs/infrastructure/self-hosted-runner-fleet.md §Security.
#
# Security model:
# - No ClusterRole / ClusterRoleBinding — runner has no K8s API access.
# - securityContext: runAsNonRoot with read-only root filesystem where
# possible (runner image needs /tmp and /home/runner writable).
# - Fork pull-request approval required on the GitHub repo settings.
# - RUNNER_ALLOW_RUNASROOT=false is the default.
#
# Cost: Phase 2 eliminates GitHub-hosted ubuntu-24.04 billing; break-even
# vs electricity is ~1 000 min/month at current TOU rates.
#
# Node placement: rke2-server (10.0.56.11) only — Longhorn RWO PVC must
# land on the same node as the volume, and the server node has the most
# spare capacity for burst CI workloads.
#
# Designs: docs/infrastructure/self-hosted-runner-fleet.md
# Questions: Q-CI-1..5 (all Recommended defaults)
---
apiVersion: v1
kind: Namespace
metadata:
name: github-runner
labels:
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
---
# 1Password secret sync — creates github-runner-token K8s Secret.
# Fields expected in the 1Password item:
# credential — GitHub fine-grained PAT (Administration:read/write on
# target repos) used by the runner image to mint a fresh
# short-lived registration token at pod start.
# Item path: IAmWorkin vault > "GitHub PAT (Runner Registration)"
# Operator MUST create this item before the Deployment will start cleanly.
apiVersion: onepassword.com/v1
kind: OnePasswordItem
metadata:
name: github-runner-token
namespace: github-runner
labels:
app.kubernetes.io/component: credentials
app.kubernetes.io/part-of: flowercore
spec:
itemPath: vaults/IAmWorkin/items/GitHub PAT (Runner Registration)
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: github-runner-nuget-cache
namespace: github-runner
labels:
app.kubernetes.io/component: cache
app.kubernetes.io/part-of: flowercore
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
resources:
requests:
storage: 5Gi
volumeMode: Filesystem
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: github-runner
namespace: github-runner
labels:
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
# No ClusterRole or ClusterRoleBinding — runner has zero K8s API privileges.
# CI jobs that need kubectl must supply their own kubeconfig via a secret
# injected at the job level, not via this service account.
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: github-runner
namespace: github-runner
labels:
app.kubernetes.io/name: github-runner
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/created-by: argocd
spec:
# Single replica enforced: the Longhorn RWO PVC can only be mounted by
# one pod at a time. Each pod re-registers as an ephemeral runner after
# completing a job (EPHEMERAL=true restarts the container, not the pod,
# so the PVC stays attached between jobs).
#
# 2026-05-16: bumped 0 -> 1 after operator provisioned the
# "GitHub PAT (Runner Registration)" 1P item with field=credential.
# Unblocks CI fleet-wide (was budget-exhausted on GH-hosted runners).
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: github-runner
# Use Recreate to avoid the Multi-Attach RWO error during rollouts.
strategy:
type: Recreate
template:
metadata:
labels:
app.kubernetes.io/name: github-runner
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
flowercore.io/created-by: argocd
spec:
serviceAccountName: github-runner
# Pin to rke2-server so the Longhorn RWO volume is always on the same node.
nodeSelector:
kubernetes.io/hostname: rke2-server
securityContext:
runAsNonRoot: true
runAsUser: 1001
runAsGroup: 1001
fsGroup: 1001
# Sprint 30 Cl-1 pod-env fix (2026-05-21): pre-create + chown
# /home/runner/.dotnet + /home/runner/.nuget so the non-root runner
# (UID 1001) can host setup-dotnet@v4 + dotnet restore writes without
# the per-workflow DOTNET_INSTALL_DIR patch ~25 flipped Linux repos
# have been carrying. Runs as root so chown succeeds; the main
# container then runs as 1001 against an emptyDir mounted at
# /home/runner. The PVC mount at /home/runner/.nuget/packages
# (Common runner) still wins at its nested path because Kubernetes
# honors the deeper mount.
initContainers:
- name: setup-runner-home
image: busybox:1.36
command:
- sh
- -c
- |
set -e
mkdir -p /home/runner/.dotnet /home/runner/.nuget/packages /home/runner/.nuget/NuGet
chown -R 1001:1001 /home/runner/.dotnet /home/runner/.nuget
chmod -R 755 /home/runner/.dotnet /home/runner/.nuget
securityContext:
runAsUser: 0
runAsNonRoot: false
volumeMounts:
- name: runner-home
mountPath: /home/runner
containers:
- name: runner
image: myoung34/github-runner:latest
imagePullPolicy: Always
env:
# GitHub org/repo targeting.
# Set REPO_URL for a repo-scoped runner (cheaper, simpler).
# Switch to ORG_NAME + empty REPO_URL for an org-scoped runner.
- name: REPO_URL
value: "https://github.com/astoltz/FlowerCore.Common"
- name: RUNNER_NAME_PREFIX
value: "rke2-linux"
- name: RUNNER_WORKDIR
value: "/tmp/runner/work"
# EPHEMERAL=true: runner deregisters after one job; container
# exits with code 0; Deployment controller restarts it and a
# fresh registration occurs. Prevents stale runner accumulation.
- name: EPHEMERAL
value: "true"
# Labels used by workflow files: runs-on: [self-hosted, linux, fc-build-linux]
- name: LABELS
value: "self-hosted,linux,fc-build-linux"
# PAT (not pre-minted registration token) — myoung34/github-runner
# mints registration tokens itself via GitHub API when ACCESS_TOKEN
# is set. Switched from RUNNER_TOKEN -> ACCESS_TOKEN on 2026-05-16
# because the 1P "GitHub PAT (Runner Registration)" item stores a
# fine-grained PAT, not a short-lived registration token.
- name: ACCESS_TOKEN
valueFrom:
secretKeyRef:
name: github-runner-token
key: credential
# myoung34/github-runner default entrypoint expects root for some
# setup steps. With securityContext.runAsUser=1001 the entrypoint
# short-circuits with "RUN_AS_ROOT env var is set to true but the
# user has been overridden and is not running as root". Tell the
# entrypoint we're explicitly NOT root so it skips the root-only
# setup steps (cache prewarm + apt updates — both already baked).
- name: RUN_AS_ROOT
value: "false"
# Sprint 30 Cl-1 pod-env fix (2026-05-21): retire the per-workflow
# DOTNET_INSTALL_DIR patch by setting it (+ siblings) here so ALL
# flipped Linux repos pick it up automatically. setup-dotnet@v4
# default writes to /usr/share/dotnet (root-only) or HOME-relative
# ~/.dotnet without HOME guard; pin both explicitly to the chowned
# emptyDir at /home/runner.
- name: DOTNET_INSTALL_DIR
value: "/home/runner/.dotnet"
- name: DOTNET_CLI_TELEMETRY_OPTOUT
value: "1"
- name: NUGET_PACKAGES
value: "/home/runner/.nuget/packages"
- name: DOTNET_NOLOGO
value: "1"
- name: DOTNET_GENERATE_ASPNET_CERTIFICATE
value: "false"
resources:
requests:
cpu: "500m"
memory: "1Gi"
limits:
cpu: "2000m"
memory: "4Gi"
volumeMounts:
# /home/runner emptyDir — owned by the non-root runner thanks
# to the setup-runner-home initContainer chown. Hosts .dotnet
# (setup-dotnet@v4 target) and provides a writable HOME without
# forcing a PVC. The PVC mount below at .nuget/packages wins
# at that nested path (deeper mount overrides), so the Common
# NuGet cache continues to persist across ephemeral pod restarts.
- name: runner-home
mountPath: /home/runner
- name: nuget-cache
mountPath: /home/runner/.nuget/packages
- name: tmp
mountPath: /tmp
# Liveness: runner process is alive.
livenessProbe:
exec:
command:
- /bin/sh
- -c
- "pgrep -f Runner.Listener > /dev/null"
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
volumes:
- name: runner-home
emptyDir: {}
- name: nuget-cache
persistentVolumeClaim:
claimName: github-runner-nuget-cache
- name: tmp
emptyDir: {}
# Restart policy: Always — the Deployment controller handles
# re-registration after each ephemeral job completes.
restartPolicy: Always
---
# Shared.Pos repo-scoped Linux runner. Added 2026-05-20 to unstick the
# FlowerCore.Shared.Pos "Build, Test & Publish" workflow, which had been
# queued indefinitely after the Sprint 26 Mac POS Phase 1/2 PRs merged
# (no fc-build-linux runner was registered to Shared.Pos — GitHub user
# accounts have only repo-scoped runners). First concrete instance of the
# Sprint 29 Cx-1 Linux-runner-fleet pattern; the full per-repo fleet is
# codified by that lane. emptyDir nuget cache (no RWO PVC) so it shares no
# volume with the Common runner and needs no node pin.
apiVersion: apps/v1
kind: Deployment
metadata:
name: github-runner-sharedpos
namespace: github-runner
labels:
app.kubernetes.io/name: github-runner-sharedpos
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/created-by: argocd
spec:
# UN-PARKED 2026-05-21: Shared.Pos #5 fixed the non-root setup-dotnet path
# (DOTNET_INSTALL_DIR step-scoped). Re-enabled to run the now-fixable build.
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: github-runner-sharedpos
strategy:
type: Recreate
template:
metadata:
labels:
app.kubernetes.io/name: github-runner-sharedpos
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
flowercore.io/created-by: argocd
spec:
serviceAccountName: github-runner
securityContext:
runAsNonRoot: true
runAsUser: 1001
runAsGroup: 1001
fsGroup: 1001
# Sprint 30 Cl-1 pod-env fix (2026-05-21): see github-runner Deployment
# above for full rationale. Mirrored on the Shared.Pos runner so the
# per-workflow DOTNET_INSTALL_DIR patch can be retired fleet-wide
# rather than re-applied per repo as flipped lanes land.
initContainers:
- name: setup-runner-home
image: busybox:1.36
command:
- sh
- -c
- |
set -e
mkdir -p /home/runner/.dotnet /home/runner/.nuget/packages /home/runner/.nuget/NuGet
chown -R 1001:1001 /home/runner/.dotnet /home/runner/.nuget
chmod -R 755 /home/runner/.dotnet /home/runner/.nuget
securityContext:
runAsUser: 0
runAsNonRoot: false
volumeMounts:
- name: runner-home
mountPath: /home/runner
containers:
- name: runner
image: myoung34/github-runner:latest
imagePullPolicy: Always
env:
- name: REPO_URL
value: "https://github.com/astoltz/FlowerCore.Shared.Pos"
- name: RUNNER_NAME_PREFIX
value: "rke2-linux-sharedpos"
- name: RUNNER_WORKDIR
value: "/tmp/runner/work"
- name: EPHEMERAL
value: "true"
- name: LABELS
value: "self-hosted,linux,fc-build-linux"
- name: ACCESS_TOKEN
valueFrom:
secretKeyRef:
name: github-runner-token
key: credential
- name: RUN_AS_ROOT
value: "false"
# Sprint 30 Cl-1 pod-env fix (2026-05-21): retire per-workflow patch.
- name: DOTNET_INSTALL_DIR
value: "/home/runner/.dotnet"
- name: DOTNET_CLI_TELEMETRY_OPTOUT
value: "1"
- name: NUGET_PACKAGES
value: "/home/runner/.nuget/packages"
- name: DOTNET_NOLOGO
value: "1"
- name: DOTNET_GENERATE_ASPNET_CERTIFICATE
value: "false"
resources:
requests:
cpu: "500m"
memory: "1Gi"
limits:
cpu: "2000m"
memory: "4Gi"
volumeMounts:
# Shared.Pos runner uses emptyDir for nuget cache (no node pin
# via RWO PVC). /home/runner emptyDir hosts .dotnet via the
# setup-runner-home initContainer chown; the .nuget/packages
# emptyDir mount still wins at its nested path.
- name: runner-home
mountPath: /home/runner
- name: nuget-cache
mountPath: /home/runner/.nuget/packages
- name: tmp
mountPath: /tmp
livenessProbe:
exec:
command:
- /bin/sh
- -c
- "pgrep -f Runner.Listener > /dev/null"
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
volumes:
- name: runner-home
emptyDir: {}
- name: nuget-cache
emptyDir: {}
- name: tmp
emptyDir: {}
restartPolicy: Always

View File

@@ -1,51 +1,9 @@
# ============================================================================= # =============================================================================
# ci1 Windows Server 2025 KubeVirt VM (GitHub Actions Self-Hosted Runner) # ci1 - Windows Server 2025 KubeVirt VM (GitHub Actions Self-Hosted Runner)
# ============================================================================= # =============================================================================
# Purpose: dedicated CI runner for FlowerCore.Updater Sandbox E2E nightly + # Boots from the sysprepped containerDisk template built by the Windows VM
# future fleet WPF AAT lanes. Replaces the never-registered # sysprep pipeline. See docs/infrastructure/windows-vm-sysprep-pipeline.md.
# `bluejay-ws-sandbox-1` runner placeholder. Andrew explicitly does NOT want # Path A/B/C install history is preserved in git log only.
# BLUEJAY-WS registered as a runner (workstation has personal/operator state).
#
# Storage layout (2026-05-08):
# * ISO is now sourced from Synology NFS (Path B) — see
# win2025-iso-nfs-pv.yaml. The Longhorn Filesystem PVC
# `windows-server-2025-iso` below is RETAINED but UNUSED so the prior
# CDI upload state is preserved as a fallback (and so ArgoCD doesn't
# prune it on this commit). It can be deleted in a follow-up commit
# after the NFS path is proven on a successful Windows install.
#
# Status (2026-05-08): LIVE — Phase 1 prereqs satisfied:
# * Multus CNI v4.2.2 thick-plugin DaemonSet running on all 3 RKE2 nodes
# (apps/multus/multus.yaml; ApplicationSet `infra-multus` Synced/Healthy)
# * CDI v1.65.0 operator + CR Deployed (apps/cdi/; ApplicationSet
# `infra-cdi` Synced/Healthy; uploadproxy reachable via kubectl port-forward)
# * Windows Server 2025 ISO uploaded via CDI virtctl image-upload to
# PVC windows-server-2025-iso (7.7 GiB → 10Gi PVC, Bound, Upload Complete)
# * Local Administrator password generated, stored in 1Password vault
# IAmWorkin (qaphopopkryhbg353ukzhhuqoq) item id h3ix4mgfk65gmkcmvh6ly3d3hu
# * NetworkAttachmentDefinition prod-vlan57 registered (apps/kubevirt-vms/
# prod-vlan57-nad.yaml). VM still uses pod-network masquerade until Phase 1.5
# host bridge work lands (Puppet br-prod + enp86s0.57); switching is a
# one-line YAML edit + git push.
#
# See docs/infrastructure/windows-server-build-runner-plan.md "Phase 1 readiness gate".
#
# Network choice in this draft: **pod-network fallback** (Calico default).
# Outbound-only is fine for the Updater Sandbox E2E runner workload (the runner
# polls GitHub Actions over HTTPS; no inbound listener needed). Switch to a
# Multus PROD VLAN NetworkAttachmentDefinition once Multus is installed and the
# operator wants L2 access from `ci1` to other PROD VLAN services.
#
# Sizing: 8 vCPU / 16 GB RAM / 200 GB disk on Longhorn (default storageClass).
# Capacity check 2026-05-08: each RKE2 node has 16 vCPU / ~64Gi allocatable;
# 8 vCPU is ~17% of one node's allocatable, fits comfortably.
#
# Apply (after operator approval + ISO loaded):
# kubectl --kubeconfig $env:USERPROFILE\.kube\rke2.yaml apply -f apps/kubevirt-vms/ci1.yaml
#
# Connect to console for Windows install:
# virtctl --kubeconfig $env:USERPROFILE\.kube\rke2.yaml vnc ci1 -n kubevirt-vms
# (Or via Guacamole once a connection profile is added.)
# ============================================================================= # =============================================================================
apiVersion: v1 apiVersion: v1
@@ -57,248 +15,6 @@ metadata:
pod-security.kubernetes.io/enforce: privileged pod-security.kubernetes.io/enforce: privileged
--- ---
# ISO PVC — populated via CDI virtctl image-upload (CDI is now installed).
#
# **Volume mode (2026-05-08 status):** Filesystem-mode PVC. A migration to
# `volumeMode: Block` via DataVolume was attempted to address an OVMF SATA
# CDROM read timeout, but CDI v1.65.0's upload-target pod runs as uid 107
# with `capabilities.drop: [ALL]` and cannot open the underlying block
# device (`blockdev: cannot open /dev/cdi-block-volume: Permission denied`).
# Reverted to Filesystem PVC pending one of:
# - CDI deployment override granting CAP_SYS_RAWIO to upload pod
# - Pre-populated PVC via privileged init pod that dd's the ISO directly
# - Migration to a different storage class that exposes block devices
# differently (e.g. iSCSI, where Longhorn's CSI mount path may behave
# differently)
#
# Population workflow (this PVC, Filesystem mode):
# 1. virtctl --kubeconfig $env:USERPROFILE\.kube\rke2.yaml image-upload pvc \
# windows-server-2025-iso -n kubevirt-vms \
# --image-path "$env:USERPROFILE\Downloads\en-us_windows_server_2025_updated_march_2026_x64_dvd_8e06425a.iso" \
# --size 10Gi --storage-class longhorn --access-mode ReadWriteOnce \
# --uploadproxy-url https://localhost:8443 --insecure
# (--uploadproxy-url uses port-forward in practice: `kubectl port-forward
# -n cdi service/cdi-uploadproxy 8443:443 &` first.)
#
# **Open boot issue:** even with the ISO at bootOrder:1, OVMF console showed:
# BdsDxe: starting Boot0001 "UEFI QEMU DVD-ROM QM00001 " from ... Sata(...)
# BdsDxe: failed to start Boot0001 ... Time out
# Diagnosis confirmed PVC content IS a valid bootable ISO9660 image — the
# timeout is in OVMF reading from the SATA-CDROM-backed-by-filesystem-PVC.
# Block mode would likely fix it; see CDI permission issue above.
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: windows-server-2025-iso
namespace: kubevirt-vms
labels:
app: ci-runner
flowercore.io/managed-by: bluejay-infra
spec:
accessModes:
- ReadWriteOnce # Bump to ReadOnlyMany after population for multi-VM use
resources:
requests:
storage: 10Gi # Server 2025 ISO is 7.7GB; 10Gi for headroom
storageClassName: longhorn
---
# Root disk PVC — empty 200Gi volume that Windows installs into.
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: ci1-rootdisk
namespace: kubevirt-vms
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 200Gi
storageClassName: longhorn
---
# Sysprep ConfigMap — autounattend.xml for hands-off Windows install.
# Sets local Administrator password (REPLACE the placeholder), enables RDP,
# enables WinRM, sets hostname, and configures static-ish networking via DHCP.
# The ISO + VirtIO drivers handle the rest.
apiVersion: v1
kind: ConfigMap
metadata:
name: ci1-autounattend
namespace: kubevirt-vms
data:
autounattend.xml: |
<?xml version="1.0" encoding="utf-8"?>
<unattend xmlns="urn:schemas-microsoft-com:unattend">
<!-- Pass 1: WindowsPE — Disk setup and VirtIO driver injection -->
<settings pass="windowsPE">
<component name="Microsoft-Windows-International-Core-WinPE"
processorArchitecture="amd64"
publicKeyToken="31bf3856ad364e35"
language="neutral" versionScope="nonSxS">
<SetupUILanguage>
<UILanguage>en-US</UILanguage>
</SetupUILanguage>
<InputLocale>en-US</InputLocale>
<SystemLocale>en-US</SystemLocale>
<UILanguage>en-US</UILanguage>
<UserLocale>en-US</UserLocale>
</component>
<component name="Microsoft-Windows-PnpCustomizationsWinPE"
processorArchitecture="amd64"
publicKeyToken="31bf3856ad364e35"
language="neutral" versionScope="nonSxS">
<DriverPaths>
<PathAndCredentials wcm:action="add" wcm:keyValue="1">
<Path>E:\amd64\2k25</Path>
</PathAndCredentials>
</DriverPaths>
</component>
<component name="Microsoft-Windows-Setup"
processorArchitecture="amd64"
publicKeyToken="31bf3856ad364e35"
language="neutral" versionScope="nonSxS">
<DiskConfiguration>
<Disk wcm:action="add">
<DiskID>0</DiskID>
<WillWipeDisk>true</WillWipeDisk>
<CreatePartitions>
<CreatePartition wcm:action="add">
<Order>1</Order>
<Size>260</Size>
<Type>EFI</Type>
</CreatePartition>
<CreatePartition wcm:action="add">
<Order>2</Order>
<Size>128</Size>
<Type>MSR</Type>
</CreatePartition>
<CreatePartition wcm:action="add">
<Order>3</Order>
<Extend>true</Extend>
<Type>Primary</Type>
</CreatePartition>
</CreatePartitions>
<ModifyPartitions>
<ModifyPartition wcm:action="add">
<Order>1</Order>
<PartitionID>1</PartitionID>
<Format>FAT32</Format>
<Label>EFI</Label>
</ModifyPartition>
<ModifyPartition wcm:action="add">
<Order>2</Order>
<PartitionID>2</PartitionID>
</ModifyPartition>
<ModifyPartition wcm:action="add">
<Order>3</Order>
<PartitionID>3</PartitionID>
<Format>NTFS</Format>
<Label>Windows</Label>
</ModifyPartition>
</ModifyPartitions>
</Disk>
</DiskConfiguration>
<ImageInstall>
<OSImage>
<InstallTo>
<DiskID>0</DiskID>
<PartitionID>3</PartitionID>
</InstallTo>
<!-- Index 2 = Standard Desktop Experience. Use 4 for Datacenter Desktop. -->
<InstallFrom>
<MetaData wcm:action="add">
<Key>/IMAGE/INDEX</Key>
<Value>2</Value>
</MetaData>
</InstallFrom>
</OSImage>
</ImageInstall>
<UserData>
<AcceptEula>true</AcceptEula>
<FullName>FlowerCore CI Runner</FullName>
<Organization>FlowerCore</Organization>
<!-- Eval install — no product key needed for 180-day evaluation -->
</UserData>
</component>
</settings>
<!-- Pass 4: Specialize — Hostname, RDP, WinRM -->
<settings pass="specialize">
<component name="Microsoft-Windows-Shell-Setup"
processorArchitecture="amd64"
publicKeyToken="31bf3856ad364e35"
language="neutral" versionScope="nonSxS">
<ComputerName>CI1</ComputerName>
<TimeZone>Central Standard Time</TimeZone>
</component>
<component name="Microsoft-Windows-TerminalServices-LocalSessionManager"
processorArchitecture="amd64"
publicKeyToken="31bf3856ad364e35"
language="neutral" versionScope="nonSxS">
<fDenyTSConnections>false</fDenyTSConnections>
</component>
</settings>
<!-- Pass 7: OOBE — Admin account, RDP firewall, WinRM -->
<settings pass="oobeSystem">
<component name="Microsoft-Windows-Shell-Setup"
processorArchitecture="amd64"
publicKeyToken="31bf3856ad364e35"
language="neutral" versionScope="nonSxS">
<OOBE>
<HideEULAPage>true</HideEULAPage>
<HideLocalAccountScreen>true</HideLocalAccountScreen>
<HideOEMRegistrationScreen>true</HideOEMRegistrationScreen>
<HideOnlineAccountScreens>true</HideOnlineAccountScreens>
<HideWirelessSetupInOOBE>true</HideWirelessSetupInOOBE>
<ProtectYourPC>3</ProtectYourPC>
</OOBE>
<UserAccounts>
<AdministratorPassword>
<!-- Real password is in 1Password — vault qaphopopkryhbg353ukzhhuqoq,
item id h3ix4mgfk65gmkcmvh6ly3d3hu, title:
"ci1 Administrator (Windows Server 2025 KubeVirt VM)".
Field "autounattend AdministratorPassword Value (UTF-16-LE base64)"
matches the Value below.
To rotate: regenerate, recompute base64
$combined = $pw + "AdministratorPassword"
[Convert]::ToBase64String([Text.Encoding]::Unicode.GetBytes($combined))
then update both 1P item AND this Value field, recreate VM. -->
<Value>bAA3AGsANABOAHcAcgBMAG4AeQBTAHUAYgBBAHQAaQBzAFUAcAB6AEMAWQAhADkAYQBCAEEAZABtAGkAbgBpAHMAdAByAGEAdABvAHIAUABhAHMAcwB3AG8AcgBkAA==</Value>
<PlainText>false</PlainText>
</AdministratorPassword>
</UserAccounts>
<FirstLogonCommands>
<SynchronousCommand wcm:action="add">
<Order>1</Order>
<CommandLine>powershell.exe -ExecutionPolicy Bypass -Command "Set-NetFirewallRule -DisplayGroup 'Remote Desktop' -Enabled True"</CommandLine>
<Description>Enable RDP firewall rule</Description>
</SynchronousCommand>
<SynchronousCommand wcm:action="add">
<Order>2</Order>
<CommandLine>powershell.exe -ExecutionPolicy Bypass -Command "Enable-PSRemoting -Force; Set-Item WSMan:\localhost\Service\Auth\Basic $true; Set-Item WSMan:\localhost\Service\AllowUnencrypted $true"</CommandLine>
<Description>Enable WinRM (Phase 2 will pivot to HTTPS via step-ca cert)</Description>
</SynchronousCommand>
<SynchronousCommand wcm:action="add">
<Order>3</Order>
<CommandLine>cmd.exe /c reg add "HKLM\SOFTWARE\Microsoft\Windows\CurrentVersion\Policies\System" /v EnableLUA /t REG_DWORD /d 0 /f</CommandLine>
<Description>Disable UAC (Phase 2 Puppet will re-evaluate)</Description>
</SynchronousCommand>
</FirstLogonCommands>
</component>
</settings>
</unattend>
---
# VirtualMachine — Windows Server 2025 CI runner.
apiVersion: kubevirt.io/v1 apiVersion: kubevirt.io/v1
kind: VirtualMachine kind: VirtualMachine
metadata: metadata:
@@ -309,33 +25,7 @@ metadata:
role: github-actions-runner role: github-actions-runner
flowercore.io/managed-by: bluejay-infra flowercore.io/managed-by: bluejay-infra
spec: spec:
# `running: true` is deprecated in favor of `runStrategy`. They are mutually runStrategy: Always
# exclusive — KubeVirt's validating webhook rejects any VM that sets both:
# admission webhook "virtualmachine-validator.kubevirt.io" denied the request:
# Running and RunStrategy are mutually exclusive.
# `Always` keeps a VMI running and restarts it if it crashes/exits — same
# semantics as the old `running: true`.
#
# **2026-05-08 status: VM cannot start due to a stale QEMU flock on the
# rootdisk PVC** (qemu reports `Failed to get "write" lock` on
# `/var/run/kubevirt-private/vmi-disks/rootdisk/disk.img`). The flock was
# left by a previous QEMU process during a force-deleted launcher pod
# cycle. Recovery requires either (a) a Longhorn engine restart on
# rke2-agent2, (b) a Longhorn volume detach via the longhorn-manager API
# (kubectl patch on `volume.longhorn.io/<pvc-name>` does not work — the
# spec.nodeID is reconciled back), or (c) a node reboot of rke2-agent2.
#
# **Confirmed working:** the bootOrder swap (windows-iso=1, rootdisk=2)
# and the runStrategy migration (above). The ISO PVC was successfully
# repopulated via virtctl image-upload pvc on the Filesystem-mode PVC.
#
# **Open: SATA CDROM read timeout** — even with bootOrder=1, OVMF reported
# `BdsDxe: failed to start Boot0001 ... Time out` reading the SATA CDROM
# backed by the Filesystem-mode PVC. A switch to Block-mode DataVolume
# was attempted but blocked by a CDI v1.65.0 upload-pod permission issue
# (capability drop prevents writing to the underlying block device).
# See header docstring on the ISO PVC.
runStrategy: Always # LIVE — ISO uploaded 2026-05-08, password in 1P
template: template:
metadata: metadata:
labels: labels:
@@ -377,73 +67,16 @@ spec:
firmware: firmware:
bootloader: bootloader:
efi: efi:
# 2026-05-08: SecureBoot=false during initial install. With SecureBoot
# enabled, OVMF's BdsDxe times out reading Boot0001 from the SCSI
# CDROM ("BdsDxe: failed to start Boot0001 ... Time out") before the
# EFI bootloader signature can verify against the OVMF VARS trust DB.
# KubeVirt's `/usr/share/OVMF/OVMF_VARS.secboot.fd` template doesn't
# appear to include the Microsoft KEK/DB by default, so signed
# Windows EFI bootloaders fail validation. Disabling SecureBoot lets
# OVMF skip the chain check and boot directly. This is acceptable for
# a CI runner — TPM 2.0 is still emulated (`tpm: {}` below) so
# BitLocker / Hyper-V / WSL still work.
# When the operator wants SecureBoot back, the path is:
# 1. Custom-build OVMF_VARS.fd with Microsoft KEK/DB enrolled
# 2. Mount it into the VM via firmware.bootloader.efi.persistent
# 3. Set secureBoot: true again
# Tracked separately from the install unblock.
secureBoot: false secureBoot: false
devices: devices:
tpm: {} # Non-persistent vTPM — sufficient for runner; no BitLocker tpm: {}
disks: disks:
# bootOrder: ISO must be 1 for first-boot install (the rootdisk has no
# EFI bootloader yet). After Windows installs, it writes its own UEFI
# Boot#### entries pointing at the rootdisk's EFI partition; UEFI then
# boots from rootdisk going forward and the ISO at bootOrder:2 acts as
# a fallback for re-install scenarios.
#
# Original (broken) order had rootdisk=1, windows-iso=2 — UEFI tried
# the empty virtio disk first, got nothing, fell back to the SATA
# CDROM at Boot0001 with a short timeout, and timed out before the
# CDROM enumerated. Console showed:
# BdsDxe: failed to start Boot0001 ... Time out
# BdsDxe: No bootable option or device was found.
# Confirmed via debug pod: PVC content IS a real bootable ISO9660
# (file: "ISO 9660 CD-ROM filesystem data ... (bootable)"), so the
# only bug was boot priority.
# 2026-05-08 PM: cdrom bus SCSI + containerDisk delivery. This
# combination boots qemu cleanly and reaches OVMF, but OVMF
# BdsDxe still hits "starting Boot0001 ... Time out" on the
# cdrom — see HANDOFF.md / CODEX-STATUS.md "OPEN — ci1" for the
# full diagnostic chain. virtio-blk disk swap was attempted as a
# workaround but introduced a separate QEMU rootdisk flock issue
# without fixing the underlying OVMF cdrom problem; reverted.
# Operator decision needed for next architectural step (OVMF
# custom build with extended timeout, KubeVirt version bump,
# Hyper-V/VirtualBox-and-export, or BIOS legacy boot). The
# containerDisk distribution pipeline (build/save/scp/ctr import)
# is proven and ready to reuse for any of those.
- name: windows-iso
bootOrder: 1
cdrom:
bus: scsi
- name: rootdisk - name: rootdisk
bootOrder: 2
disk: disk:
bus: virtio bus: virtio
- name: virtio-drivers
cdrom:
bus: sata
- name: sysprep
cdrom:
bus: sata
interfaces: interfaces:
# Pod-network fallback for Phase 1. To switch to PROD VLAN once Multus # Pod-network fallback for CI runner outbound traffic. Switch to
# + the prod-vlan57 NAD exist, replace this block with: # prod-vlan57 once the bridge/NAD lane is ready for L2 access.
# - name: prod-net
# bridge: {}
# model: virtio
# and update the networks: stanza to use multus.networkName: kubevirt-vms/prod-vlan57
- name: default - name: default
masquerade: {} masquerade: {}
model: virtio model: virtio
@@ -454,55 +87,7 @@ spec:
pod: {} pod: {}
volumes: volumes:
- name: rootdisk - name: rootdisk
persistentVolumeClaim:
claimName: ci1-rootdisk
- name: windows-iso
# 2026-05-08 PM (Path C, CONTAINERDISK): the ISO is now packaged as
# a KubeVirt containerDisk OCI image baked from
# `FROM scratch ; ADD --chown=107:107 disk.img /disk/disk.img`.
# The qemu user (uid 107) reads the ISO directly from a tmpfs view
# of the OCI layer, bypassing both:
# - Synology NFS export ACL (Path B failed: uid 107 denied at
# directory level even with mode 0777, see memory
# feedback_synology_iso_export_root_only_uid_107_denied)
# - OVMF cdrom read-window timeout (Path A and Path B's SCSI
# retry both hit `BdsDxe: failed to start Boot0001 ... Time out`
# when the cdrom was backed by a PVC the storage controller
# couldn't satisfy reads from fast enough).
#
# Image build (one-time, per ISO version):
# 1. Copy ISO to disk.img, write Dockerfile
# 2. podman build --tag localhost/win-server-2025:1.0 . (on noc1)
# 3. podman save -o win-server-2025-1.0.tar localhost/win-server-2025:1.0
# 4. SCP tar to all 3 RKE2 nodes (rke2-server, rke2-agent1, rke2-agent2)
# 5. sudo /var/lib/rancher/rke2/bin/ctr -a /run/k3s/containerd/containerd.sock \
# -n k8s.io images import /tmp/win-server-2025-1.0.tar
# Standard FC pattern per `feedback_rke2_localhost_imagepullpolicy`.
#
# When a new Windows ISO version ships, bump the tag (1.1, 1.2, ...),
# rebuild + redistribute, and update the image: line below in a new
# commit. KubeVirt picks up the new image via a VM restart.
#
# The legacy NFS PVC + PV (apps/kubevirt-vms/win2025-iso-nfs-pv.yaml)
# and CDI Longhorn PVC (`windows-server-2025-iso`) are RETAINED for
# this commit so the prior states are recoverable. Once the
# containerDisk path proves on a successful Windows install, both
# legacy artifacts can be pruned in a follow-up commit.
containerDisk: containerDisk:
image: localhost/win-server-2025:1.0 image: localhost/fc-win-server-2025:v1
imagePullPolicy: Never imagePullPolicy: Never
- name: virtio-drivers
containerDisk:
# Pinned to v1.8.2 (latest stable as of 2026-05-08).
# The :latest tag uses Docker manifest v1 schema which containerd
# 2.1 (RKE2 v1.34.5) refuses to pull with:
# "media type application/vnd.docker.distribution.manifest.v1+prettyjws
# is no longer supported since containerd v2.1"
# v1.8.2 is rebuilt with manifest v2/OCI and works on containerd 2.1.
# Bump available: https://quay.io/repository/kubevirt/virtio-container-disk?tab=tags
image: quay.io/kubevirt/virtio-container-disk:v1.8.2
- name: sysprep
sysprep:
configMap:
name: ci1-autounattend
terminationGracePeriodSeconds: 3600 terminationGracePeriodSeconds: 3600

View File

@@ -0,0 +1,3 @@
resources:
- ci1.yaml
- prod-vlan57-nad.yaml

View File

@@ -75,6 +75,20 @@ data:
cluster: "rke2" cluster: "rke2"
role: "agent" role: "agent"
# Mac mini macOS runner node (INFRA VLAN)
- job_name: "macmini-node"
scrape_timeout: 15s
static_configs:
- targets: ["10.0.56.115:9100"]
labels:
instance: "macmini"
host: "macmini.iamworkin.lan"
vlan: "infra"
arch: "arm64"
role: "macos-runner"
puppet_managed: "true"
puppet_server: "puppet.iamworkin.lan"
# In-cluster node-exporter DaemonSet # In-cluster node-exporter DaemonSet
- job_name: "k8s-node-exporter" - job_name: "k8s-node-exporter"
kubernetes_sd_configs: kubernetes_sd_configs:
@@ -697,6 +711,18 @@ data:
summary: "Print.Web Ollama runner held for >10m ({{ $labels.model }})" summary: "Print.Web Ollama runner held for >10m ({{ $labels.model }})"
description: "Print.Web reports model {{ $labels.model }} with {{ $value | printf \"%.0f\" }}s of keep-alive remaining. Check concurrent requests before the Pi 5 Ollama lane thrashes." description: "Print.Web reports model {{ $labels.model }} with {{ $value | printf \"%.0f\" }}s of keep-alive remaining. Check concurrent requests before the Pi 5 Ollama lane thrashes."
- name: macmini-runners
rules:
- alert: MacMiniRunnerOffline
expr: (flowercore_github_runner_online{runner=~"macmini-.*"} == 0) or absent(flowercore_github_runner_online{runner=~"macmini-.*"})
for: 10m
labels:
severity: warning
service: github-runner
annotations:
summary: "Mac mini GitHub runner offline ({{ $labels.runner }})"
description: "A macmini-* GitHub Actions runner has not reported online for more than 10 minutes. Puppet manages its LaunchDaemon under /Library/LaunchDaemons/io.flowercore.github-runner-<slug>.plist; runners survive reboot and do not require a GUI session."
- name: remote-desktop - name: remote-desktop
rules: rules:
- alert: RemoteDesktopWebDown - alert: RemoteDesktopWebDown
@@ -3427,6 +3453,32 @@ data:
relativeTimeRange: {from: 120, to: 0} relativeTimeRange: {from: 120, to: 0}
datasourceUid: __expr__ datasourceUid: __expr__
model: {type: threshold, expression: B, conditions: [{evaluator: {params: [1], type: lt}}], refId: C} model: {type: threshold, expression: B, conditions: [{evaluator: {params: [1], type: lt}}], refId: C}
- uid: macmini-runner-offline
title: MacMiniRunnerOffline
condition: C
for: 10m
noDataState: Alerting
execErrState: OK
annotations:
summary: Mac mini GitHub runner offline
description: "One or more macmini-* GitHub Actions runners have not reported online for more than 10 minutes. LaunchDaemons survive reboot and do not require the bluejay GUI session."
runbook: "1. ssh fcadmin@macmini.iamworkin.lan 2. launchctl print system/io.flowercore.github-runner-<slug> 3. Check /Users/fcadmin/Library/Logs/github-runners/<slug>/stderr.log 4. Re-register the repo runner if .runner is missing"
labels:
severity: warning
service: github-runner
data:
- refId: A
relativeTimeRange: {from: 600, to: 0}
datasourceUid: prometheus
model: {expr: 'min(flowercore_github_runner_online{runner=~"macmini-.*"} or vector(0))', instant: true, refId: A}
- refId: B
relativeTimeRange: {from: 600, to: 0}
datasourceUid: __expr__
model: {type: reduce, expression: A, reducer: last, refId: B}
- refId: C
relativeTimeRange: {from: 600, to: 0}
datasourceUid: __expr__
model: {type: threshold, expression: B, conditions: [{evaluator: {params: [1], type: lt}}], refId: C}
- uid: high-cpu - uid: high-cpu
title: High CPU (>85%) title: High CPU (>85%)
condition: C condition: C

View File

@@ -305,15 +305,17 @@ spec:
path: / path: /
port: 8080 port: 8080
initialDelaySeconds: 60 initialDelaySeconds: 60
timeoutSeconds: 5 timeoutSeconds: 15
periodSeconds: 10 periodSeconds: 10
failureThreshold: 3
readinessProbe: readinessProbe:
httpGet: httpGet:
path: / path: /
port: 8080 port: 8080
initialDelaySeconds: 30 initialDelaySeconds: 30
periodSeconds: 5 periodSeconds: 5
timeoutSeconds: 5 timeoutSeconds: 15
failureThreshold: 3
--- ---
apiVersion: v1 apiVersion: v1
kind: Service kind: Service

View File

@@ -291,6 +291,184 @@ public sealed class FleetManifestLintTests
violations.Should().BeEmpty(); violations.Should().BeEmpty();
} }
[Fact]
public void FcDeviceManagement_MustShipExpectedManifestSet()
{
var appRoot = Path.Combine(Inventory.BluejayRoot, "apps", "fc-devicemgmt");
Directory.Exists(appRoot).Should().BeTrue("Sprint 8 Cx-5 owns apps/fc-devicemgmt.");
var expectedFiles = new[]
{
"1password-item.yaml",
"argocd-application.yaml",
"certificate-web.yaml",
"clusterrole-operator.yaml",
"clusterrolebinding-operator.yaml",
"deployment-operator.yaml",
"deployment-web.yaml",
"ingressroute-web.yaml",
"namespace.yaml",
"network-policy.yaml",
"service-web.yaml",
"serviceaccount-operator.yaml",
};
Directory.GetFiles(appRoot, "*.yaml")
.Select(Path.GetFileName)
.Should()
.BeEquivalentTo(expectedFiles);
foreach (var expectedFile in expectedFiles)
{
FcDeviceManagementDocuments()
.Should()
.Contain(document => document.RelativePath == $"fc-devicemgmt/{expectedFile}");
}
}
[Fact]
public void FcDeviceManagement_ObjectsMustCarryStandardTraceabilityLabels()
{
var requiredLabels = new[]
{
"app.kubernetes.io/name",
"app.kubernetes.io/part-of",
"app.kubernetes.io/managed-by",
"flowercore.io/tenant-id",
"flowercore.io/created-by",
};
var violations = FcDeviceManagementDocuments()
.SelectMany(document => requiredLabels
.Where(label => string.IsNullOrWhiteSpace(document.Scalar("metadata", "labels", label)))
.Select(label => $"{document.Descriptor} is missing metadata.labels['{label}']."))
.Concat(FcDeviceManagementDocuments()
.Where(document => document.Kind == "Deployment")
.SelectMany(document => requiredLabels
.Where(label => string.IsNullOrWhiteSpace(document.Scalar("spec", "template", "metadata", "labels", label)))
.Select(label => $"{document.Descriptor} pod template is missing metadata.labels['{label}'].")))
.Concat(FcDeviceManagementDocuments()
.Where(document => document.Kind == "Deployment")
.Where(document => string.IsNullOrWhiteSpace(document.Scalar("spec", "template", "metadata", "annotations", "flowercore.io/audit-trace-id")))
.Select(document => $"{document.Descriptor} pod template is missing flowercore.io/audit-trace-id."))
.ToList();
violations.Should().BeEmpty();
}
[Fact]
public void FcDeviceManagement_IngressMustUseCertManagerAndKeepPublicHostDisabled()
{
var appText = string.Join(
Environment.NewLine,
Directory.GetFiles(Path.Combine(Inventory.BluejayRoot, "apps", "fc-devicemgmt"), "*.yaml")
.Select(File.ReadAllText));
appText.Should().NotContain("certResolver");
appText.Should().Contain("update.flowercore.io");
appText.Should().Contain("disabled-until-Q-OIDC-1");
FcDeviceManagementDocuments()
.Where(document => document.Kind == "IngressRoute")
.SelectMany(document => document.MappingSequence("spec", "routes"))
.Select(route => ManifestNodeExtensions.Scalar(route, "match") ?? string.Empty)
.Should()
.Contain(match => match.Contains("Host(`devices.iamworkin.lan`)", StringComparison.Ordinal))
.And.NotContain(match => match.Contains("Host(`update.flowercore.io`)", StringComparison.Ordinal));
var certificate = FcDeviceManagementDocuments()
.Single(document => document.Kind == "Certificate" && document.Name == "fc-devicemgmt-web-tls");
certificate.Scalar("spec", "issuerRef", "name").Should().Be("step-ca-acme");
certificate.Scalar("spec", "issuerRef", "kind").Should().Be("ClusterIssuer");
ManifestNodeExtensions.ScalarSequence(certificate.Root, "spec", "dnsNames")
.Should()
.ContainSingle("devices.iamworkin.lan");
}
[Fact]
public void FcDeviceManagement_OperatorRbacMustCoverDevicesAndOwnerLookup()
{
var clusterRole = FcDeviceManagementDocuments()
.Single(document => document.Kind == "ClusterRole" && document.Name == "fc-devicemgmt-operator");
var allScalars = clusterRole.AllScalars().ToList();
allScalars.Should().Contain("devices.flowercore.io");
allScalars.Should().Contain("*");
allScalars.Should().Contain("deployments");
allScalars.Should().Contain("get");
var operatorDeployment = FcDeviceManagementDocuments()
.Single(document => document.Kind == "Deployment" && document.Name == "fc-devicemgmt-operator");
operatorDeployment.AllScalars().Should().Contain("FLOWERCORE_KUBERNETES_OWNER_DEPLOYMENT");
operatorDeployment.AllScalars().Should().Contain("fc-devicemgmt-operator");
}
[Fact]
public void FcDeviceManagement_RuntimeSecretsMustUseOnePasswordItemPattern()
{
var item = FcDeviceManagementDocuments()
.Single(document => document.Kind == "OnePasswordItem" && document.Name == "fc-devicemgmt-runtime");
item.Scalar("spec", "itemPath")
.Should()
.Be("vaults/IAmWorkin/items/FlowerCore DeviceManagement Runtime");
var appText = string.Join(
Environment.NewLine,
Directory.GetFiles(Path.Combine(Inventory.BluejayRoot, "apps", "fc-devicemgmt"), "*.yaml")
.Select(File.ReadAllText));
FcDeviceManagementDocuments().Should().NotContain(document => document.Kind == "Secret");
appText.Should().Contain("secretKeyRef:");
appText.Should().Contain("secretName: fc-devicemgmt-runtime");
appText.Should().NotContain("stringData:");
appText.Should().NotContain("from-literal");
appText.Should().NotContain("tls.key:");
}
[Fact]
public void FcDeviceManagement_NetworkPoliciesMustAllowLanAgentsSynologyAndDnatPorts()
{
var policies = FcDeviceManagementDocuments()
.Where(document => document.Kind == "NetworkPolicy")
.ToList();
policies.Should().HaveCount(2);
var combinedScalars = policies.SelectMany(policy => policy.AllScalars()).ToList();
combinedScalars.Should().Contain("10.0.56.0/24");
combinedScalars.Should().Contain("10.0.57.0/24");
combinedScalars.Should().Contain("10.0.58.0/24");
combinedScalars.Should().Contain("10.0.68.0/27");
combinedScalars.Should().Contain("10.0.58.3/32");
var combinedEgressPorts = policies.SelectMany(policy => policy.EgressPorts()).ToHashSet(StringComparer.Ordinal);
combinedEgressPorts.Should().Contain(new[] { "80", "443", "8080", "8443", "2049", "111" });
var traefikVipPolicies = policies
.Where(policy => policy.AllScalars().Any(value => value.Contains("10.0.56.200", StringComparison.Ordinal)))
.ToList();
traefikVipPolicies.Should().ContainSingle();
traefikVipPolicies[0].EgressPorts().Should().Contain(new[] { "80", "443", "8080", "8443" });
}
[Fact]
public void FcDeviceManagement_ArgocdApplicationMustMatchApplicationSetDiscoveryConventions()
{
var application = FcDeviceManagementDocuments()
.Single(document => document.Kind == "Application" && document.Name == "infra-fc-devicemgmt");
application.Namespace.Should().Be("argocd");
application.Scalar("spec", "source", "repoURL")
.Should()
.Be("http://gitea-clusterip.gitea.svc.cluster.local:3000/bluejay/bluejay-infra.git");
application.Scalar("spec", "source", "path").Should().Be("apps/fc-devicemgmt");
application.Scalar("spec", "destination", "namespace").Should().Be("fc-devicemgmt");
}
private static IEnumerable<string> ProbeViolations( private static IEnumerable<string> ProbeViolations(
ManifestDocument document, ManifestDocument document,
YamlMappingNode container, YamlMappingNode container,
@@ -314,6 +492,13 @@ public sealed class FleetManifestLintTests
$"{document.Descriptor} container '{containerName}' still uses {probeKey}.httpGet on /health.", $"{document.Descriptor} container '{containerName}' still uses {probeKey}.httpGet on /health.",
}; };
} }
private static IReadOnlyList<ManifestDocument> FcDeviceManagementDocuments()
{
return Inventory.Documents
.Where(document => document.RelativePath.StartsWith("fc-devicemgmt/", StringComparison.Ordinal))
.ToList();
}
} }
internal sealed class ManifestInventory internal sealed class ManifestInventory

View File

@@ -0,0 +1,269 @@
using System.Text.Json;
using FluentAssertions;
using Xunit;
namespace BluejayInfraLint.Tests;
[Trait("Category", "Unit")]
public sealed class PiSignagePlayerArtifactTests
{
private static readonly string Root = FindRepoRoot();
private static readonly string AppRoot = Path.Combine(Root, "apps", "fc-signage-pi-player");
public static TheoryData<string> RequiredArtifacts => new()
{
"README.md",
"systemd/flowercore-signage-player-pi.service",
"systemd/flowercore-signage-player-pi-hdmi.service",
"systemd/flowercore-signage-bootstrap.service",
"systemd/flowercore-signage-renew.service",
"systemd/flowercore-signage-renew.timer",
"systemd/flowercore-signage-detect-display.service",
"systemd/flowercore-signage-detect-display.timer",
"systemd/99-flowercore-signage-hdmi.rules",
"chromium-policies/flowercore-signage.json",
"scripts/flowercore-signage-launch.sh",
"scripts/flowercore-signage-prelaunch.sh",
"scripts/flowercore-signage-bootstrap.sh",
"scripts/flowercore-signage-renew-cert.sh",
"scripts/flowercore-signage-hdmi-respond.sh",
"scripts/fc-signage-detect-display",
};
[Theory]
[MemberData(nameof(RequiredArtifacts))]
public void RequiredArtifacts_ArePresent(string relativePath)
{
File.Exists(Path.Combine(AppRoot, relativePath)).Should().BeTrue(relativePath);
}
[Fact]
public void PlayerService_UsesExpectedRestartAndMemoryGuards()
{
var unit = Read("systemd/flowercore-signage-player-pi.service");
unit.Should().Contain("Restart=always");
unit.Should().Contain("RestartSec=10s");
unit.Should().Contain("StartLimitBurst=5");
unit.Should().Contain("StartLimitIntervalSec=300s");
unit.Should().Contain("MemoryMax=2G");
}
[Fact]
public void PlayerService_IsGatedByNodeIdentityAndMtlsCertificate()
{
var unit = Read("systemd/flowercore-signage-player-pi.service");
unit.Should().Contain("ConditionPathExists=/etc/flowercore/signage-node.json");
unit.Should().Contain("ConditionPathExists=/etc/fc-signage-player/client.p12");
unit.Should().Contain("ExecStartPre=/usr/local/bin/flowercore-signage-prelaunch.sh");
}
[Fact]
public void LaunchScript_TriesEmbedThenFallsBackToBarePlayerRoute()
{
var script = Read("scripts/flowercore-signage-launch.sh");
script.Should().Contain("/player/${NODE_ID}/embed?token=${CERT_THUMB}");
script.Should().Contain("url-divergence.log");
script.Should().Contain("/player/${NODE_ID}?token=${CERT_THUMB}");
}
[Fact]
public void LaunchScript_DisablesChromiumPromptsAndRuntimeUpdates()
{
var script = Read("scripts/flowercore-signage-launch.sh");
script.Should().Contain("--noerrdialogs");
script.Should().Contain("--disable-infobars");
script.Should().Contain("--password-store=basic");
script.Should().Contain("--check-for-update-interval=2592000");
}
[Fact]
public void PrelaunchScript_AbortsWhenRequiredFilesAreMissing()
{
var script = Read("scripts/flowercore-signage-prelaunch.sh");
script.Should().Contain("for f in /etc/flowercore/signage-node.json /etc/fc-signage-player/client.p12 /etc/fc-signage-player/client.p12.pass");
script.Should().Contain("exit 1");
script.Should().Contain("-checkend $((7*24*3600))");
}
[Fact]
public void BootstrapScript_IsIdempotentWhenAlreadyEnrolled()
{
var script = Read("scripts/flowercore-signage-bootstrap.sh");
script.Should().Contain("already enrolled");
script.Should().Contain("exit 0");
script.Should().Contain(".enrolledAt");
}
[Fact]
public void BootstrapScript_GeneratesStableMachineIdFromUuid()
{
var script = Read("scripts/flowercore-signage-bootstrap.sh");
script.Should().Contain("uuidgen");
script.Should().Contain("cut -c1-16");
script.Should().Contain("machineId");
}
[Fact]
public void BootstrapScript_RetriesRegisterOnceForFirstCallRace()
{
var script = Read("scripts/flowercore-signage-bootstrap.sh");
script.Should().Contain("for attempt in 1 2");
script.Should().Contain("register attempt $attempt returned");
script.Should().Contain("sleep 5");
}
[Fact]
public void BootstrapScript_SupportsSetupCodeAndApprovalPollingBudget()
{
var script = Read("scripts/flowercore-signage-bootstrap.sh");
script.Should().Contain("signage-setup-code");
script.Should().Contain("approve-via-setup-code");
script.Should().Contain("+ 1800");
script.Should().Contain("sleep 15");
}
[Fact]
public void BootstrapScript_CsrSubjectIdentifiesPiPlayer()
{
var script = Read("scripts/flowercore-signage-bootstrap.sh");
script.Should().Contain("/CN=${NODE_ID}/O=FlowerCore/OU=SignagePlayer-Pi");
}
[Fact]
public void BootstrapScript_PersistsCertificateAsP12WithRestrictivePermissions()
{
var script = Read("scripts/flowercore-signage-bootstrap.sh");
script.Should().Contain("openssl pkcs12 -export");
script.Should().Contain("client.p12.pass");
script.Should().Contain("chmod 0600");
script.Should().Contain("chmod 0640");
}
[Fact]
public void RenewScript_OnlyRunsWhenCertHasLessThanThirtyDays()
{
var script = Read("scripts/flowercore-signage-renew-cert.sh");
script.Should().Contain("-checkend $((30*24*3600))");
script.Should().Contain("exit 0");
script.Should().Contain("/renew");
}
[Fact]
public void RenewScript_AtomicallySwapsNewCertificateFiles()
{
var script = Read("scripts/flowercore-signage-renew-cert.sh");
script.Should().Contain("client.key.new");
script.Should().Contain("mv \"$CERT_DIR/client.key.new\" \"$CERT_DIR/client.key\"");
script.Should().Contain("mv \"$CERT_DIR/client.p12.new\" \"$CERT_DIR/client.p12\"");
}
[Fact]
public void HdmiRule_RestartsPlayerAndRunsCapabilityDetection()
{
var rule = Read("systemd/99-flowercore-signage-hdmi.rules");
var responder = Read("scripts/flowercore-signage-hdmi-respond.sh");
rule.Should().Contain("KERNEL==\"card?-HDMI-A-?\"");
rule.Should().Contain("start flowercore-signage-player-pi-hdmi.service");
responder.Should().Contain("sleep 2");
responder.Should().Contain("start flowercore-signage-detect-display.service");
responder.Should().Contain("restart flowercore-signage-player-pi.service");
}
[Fact]
public void DetectDisplayServiceAndTimer_RunAtBootAndDaily()
{
var service = Read("systemd/flowercore-signage-detect-display.service");
var timer = Read("systemd/flowercore-signage-detect-display.timer");
service.Should().Contain("ExecStart=/usr/local/bin/fc-signage-detect-display");
timer.Should().Contain("OnBootSec=30s");
timer.Should().Contain("OnCalendar=daily");
timer.Should().Contain("RandomizedDelaySec=1h");
}
[Fact]
public void DetectDisplayScript_EmitsDisconnectedProfileWhenNoHdmiIsPresent()
{
var script = Read("scripts/fc-signage-detect-display");
script.Should().Contain("displayConnected: false");
script.Should().Contain("No HDMI display detected");
}
[Fact]
public void DetectDisplayScript_ParsesEdidForHdrResolutionAndAudio()
{
var script = Read("scripts/fc-signage-detect-display");
script.Should().Contain("edid-decode");
script.Should().Contain("HDR (Static|Dynamic) Metadata Block");
script.Should().Contain("maxResolution");
script.Should().Contain("hasAudioOutput");
}
[Fact]
public void DetectDisplayScript_TriesBothForwardCompatibleCapabilityEndpoints()
{
var script = Read("scripts/fc-signage-detect-display");
script.Should().Contain("/api/v1/nodes/${NODE_ID}/capabilities");
script.Should().Contain("/api/v1/displays/${NODE_ID}/capability-profile");
script.Should().Contain("no endpoint accepted the profile");
}
[Fact]
public void ChromiumPolicy_IsValidJsonAndDisablesCredentialPrompts()
{
using var doc = JsonDocument.Parse(Read("chromium-policies/flowercore-signage.json"));
var root = doc.RootElement;
root.GetProperty("AutofillAddressEnabled").GetBoolean().Should().BeFalse();
root.GetProperty("AutofillCreditCardEnabled").GetBoolean().Should().BeFalse();
root.GetProperty("PasswordManagerEnabled").GetBoolean().Should().BeFalse();
root.GetProperty("ExtensionInstallBlocklist")[0].GetString().Should().Be("*");
}
[Fact]
public void RenewalTimer_UsesDailyCadenceWithTwoHourJitter()
{
var timer = Read("systemd/flowercore-signage-renew.timer");
timer.Should().Contain("OnCalendar=daily");
timer.Should().Contain("RandomizedDelaySec=2h");
timer.Should().Contain("Persistent=true");
}
private static string Read(string relativePath)
=> File.ReadAllText(Path.Combine(AppRoot, relativePath.Replace('/', Path.DirectorySeparatorChar)));
private static string FindRepoRoot()
{
var current = new DirectoryInfo(AppContext.BaseDirectory);
while (current is not null)
{
if (Directory.Exists(Path.Combine(current.FullName, "apps"))
&& File.Exists(Path.Combine(current.FullName, "README.md")))
{
return current.FullName;
}
current = current.Parent;
}
throw new DirectoryNotFoundException("Could not find bluejay-infra root.");
}
}