Compare commits

..

1 Commits

Author SHA1 Message Date
Codex
05af0c48f9 Mirror voice stack monitoring assets 2026-05-06 17:35:59 -05:00
80 changed files with 239 additions and 16701 deletions

View File

@@ -118,7 +118,6 @@ That test project sweeps `bluejay-infra/apps/**` plus the canonical sibling `Flo
## References ## References
- OpenVox noc1 durability runbook: `docs/runbooks/openvoxserver-quadlet-durability.md`
- Cert-manager recovery playbook: `FlowerCore.Notes/memory/project_cert_manager_recovery_2026_04_22.md` - Cert-manager recovery playbook: `FlowerCore.Notes/memory/project_cert_manager_recovery_2026_04_22.md`
- Why pfSense DNS is required: `FlowerCore.Notes/memory/feedback_pfsense_dns_required_for_acme.md` - Why pfSense DNS is required: `FlowerCore.Notes/memory/feedback_pfsense_dns_required_for_acme.md`
- Public DNS operator host: `https://dns.iamworkin.lan` - Public DNS operator host: `https://dns.iamworkin.lan`

View File

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

View File

@@ -1,69 +0,0 @@
# CDI — Containerized Data Importer
KubeVirt's `containerized-data-importer` for populating PVCs from external
sources (HTTP, HTTPS, container registry, S3, virtctl upload). Required to
import the Windows Server 2025 ISO into the `windows-server-2025-iso` PVC
that `apps/kubevirt-vms/ci1.yaml` mounts as a CDROM.
## Files
| File | Source | Purpose |
| ----------------- | ----------------------------------------------------------------------------------------------------------------- | -------------------------------------------------- |
| `cdi-operator.yaml` | [`v1.65.0`](https://github.com/kubevirt/containerized-data-importer/releases/tag/v1.65.0) — verbatim copy | Installs operator + CRDs (5779 lines, large) |
| `cdi-cr.yaml` | [`v1.65.0`](https://github.com/kubevirt/containerized-data-importer/releases/tag/v1.65.0) — annotated + commented | Tells operator to deploy CDI components |
`cdi-operator.yaml` is **vendored verbatim** from the upstream release for
air-gap reproducibility (no internet fetch at deploy time, ArgoCD prune
contracts hold). To bump versions:
```bash
CDI_VER=v1.66.0 # for example
curl -sL "https://github.com/kubevirt/containerized-data-importer/releases/download/${CDI_VER}/cdi-operator.yaml" \
-o apps/cdi/cdi-operator.yaml
curl -sL "https://github.com/kubevirt/containerized-data-importer/releases/download/${CDI_VER}/cdi-cr.yaml" \
-o /tmp/cdi-cr-new.yaml # then re-apply project header diff
git diff apps/cdi/ # review
git commit + push
```
## Verify after deploy
```bash
kubectl -n cdi get pods # operator + apiserver + deployment + uploadproxy
kubectl get cdis cdi -o jsonpath='{.status.phase}' # "Deployed"
kubectl get crd | grep cdi.kubevirt.io
# Expected CRDs: datavolumes.cdi.kubevirt.io, cdiconfigs.cdi.kubevirt.io,
# storageprofiles.cdi.kubevirt.io, dataimportcrons.cdi.kubevirt.io,
# datasources.cdi.kubevirt.io, objecttransfers.cdi.kubevirt.io
```
## Use after install
```yaml
# Example DataVolume that imports from HTTP
apiVersion: cdi.kubevirt.io/v1beta1
kind: DataVolume
metadata:
name: my-iso
spec:
source:
http:
url: "https://server/path/to.iso"
pvc:
accessModes: [ReadWriteOnce]
resources:
requests:
storage: 10Gi
storageClassName: longhorn
```
```bash
# Or upload from local disk via virtctl
virtctl image-upload pvc my-iso \
--image-path ./my.iso \
--size 10Gi \
--storage-class longhorn \
--access-mode ReadWriteOnce \
--uploadproxy-url https://cdi-uploadproxy.cdi.svc:443 \
--insecure
```

View File

@@ -1,36 +0,0 @@
# =============================================================================
# CDI CR — Tells the CDI operator to install CDI components into the cluster.
# =============================================================================
# After cdi-operator.yaml is applied, the operator watches for THIS resource
# (CDI named "cdi"). When found, it deploys cdi-apiserver, cdi-deployment,
# cdi-uploadproxy, cdi-cronjob, and the importer/uploadserver/cloner pods.
#
# Configuration:
# - HonorWaitForFirstConsumer: PVCs created by DataVolumes wait for first
# pod to schedule before binding (lets storage class pick best node).
# - WebhookPvcRendering: validates PVC creation against CDI policies.
# - imagePullPolicy IfNotPresent: re-pull only on tag rotation.
# - nodeSelector linux: pin to Linux nodes (no Windows worker support).
#
# Andrew may want to add a `uploadProxyURLOverride` later to expose the
# uploadproxy via Traefik IngressRoute for `virtctl image-upload` from
# BLUEJAY-WS without `kubectl port-forward`. Phase 2 enhancement.
# =============================================================================
apiVersion: cdi.kubevirt.io/v1beta1
kind: CDI
metadata:
name: cdi
annotations:
bluejay.iamworkin.lan/source: "kubevirt/containerized-data-importer v1.65.0"
spec:
config:
featureGates:
- HonorWaitForFirstConsumer
- WebhookPvcRendering
imagePullPolicy: IfNotPresent
infra:
nodeSelector:
kubernetes.io/os: linux
workload:
nodeSelector:
kubernetes.io/os: linux

File diff suppressed because it is too large Load Diff

View File

@@ -30,41 +30,3 @@ spec:
port: 80 port: 80
tls: tls:
secretName: chat-web-tls secretName: chat-web-tls
---
# Public host profile marker. The app treats this header as authoritative for
# the public twin, while the internal chat.iamworkin.lan route does not attach
# it and keeps the operator-oriented UI.
apiVersion: traefik.io/v1alpha1
kind: Middleware
metadata:
name: chat-public-profile-header
namespace: fc-chat
spec:
headers:
customRequestHeaders:
X-FC-Chat-Host-Profile: "public"
---
# Public Cloudflare-fronted twin for the anonymous chat surface. Operator
# paths are intentionally absent from the allowlist below, so /admin,
# /operator, /console, /ops, /api/operator, and /operatorhub miss this route
# and return Traefik 404 before reaching the pod. Operator action still needed:
# create/verify Cloudflare DNS chat.flowercore.io -> public Traefik endpoint
# and mirror the cf-origin-flowercore-io TLS secret into namespace fc-chat.
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: chat-web-public
namespace: fc-chat
spec:
entryPoints:
- websecure
routes:
- match: Host(`chat.flowercore.io`) && (Path(`/`) || Path(`/chat`) || PathPrefix(`/_blazor`) || PathPrefix(`/_framework`) || PathPrefix(`/_content`) || PathPrefix(`/avatars`) || PathPrefix(`/css`) || PathPrefix(`/js`) || PathPrefix(`/favicon`) || PathPrefix(`/chathub`)) && (Method(`GET`) || Method(`HEAD`) || Method(`POST`) || Method(`OPTIONS`))
kind: Rule
middlewares:
- name: chat-public-profile-header
services:
- name: chat-web
port: 80
tls:
secretName: cf-origin-flowercore-io

View File

@@ -1,18 +1,5 @@
# FlowerCore Remote Desktop — TLS + Ingress # FlowerCore Remote Desktop — TLS + Ingress
# # Deployment and Service managed by deploy script (not ArgoCD)
# Source-of-truth split:
# - bluejay-infra OWNS: Certificate, IngressRoute, all NetworkPolicies
# (see network-policies.yaml in this directory).
# - FlowerCore.RemoteDesktop scripts/deploy-web.sh OWNS: Deployment +
# Service. Reason: image refs like `localhost/fc-desktop:linux-xfce`
# only exist on each node's containerd after a manual import, so a
# Deployment manifest in bluejay-infra would race the image-import
# step and crash-loop.
#
# NetworkPolicies moved into bluejay-infra 2026-05-07 — previously they
# were applied via the deploy script's kubectl apply calls, which broke
# cluster-rebuild repeatability. See
# feedback_networkpolicies_belong_in_bluejay_infra.md.
--- ---
apiVersion: cert-manager.io/v1 apiVersion: cert-manager.io/v1
kind: Certificate kind: Certificate

View File

@@ -1,332 +0,0 @@
# FlowerCore Remote Desktop — NetworkPolicies (GitOps-managed)
#
# Moved into bluejay-infra 2026-05-07 as part of the regroup audit. These
# four policies were previously applied via FlowerCore.RemoteDesktop's
# scripts/deploy-web.sh `kubectl apply` calls, which meant a fresh cluster
# rebuild from bluejay-infra alone would miss them — Browser Lab session
# isolation, control-plane allow-list, and HTTP-01 cert renewal would all
# silently fail to come up.
#
# Source-of-truth contract:
# - bluejay-infra OWNS all NetworkPolicy + Certificate + IngressRoute
# resources for fc-desktop.
# - FlowerCore.RemoteDesktop's scripts/deploy-web.sh continues to own
# the Deployment + Service apply (because the image ref
# `localhost/fc-desktop:linux-xfce` only exists on each node's
# containerd after a manual import — it can't be pulled from a
# registry, so a Deployment manifest in bluejay-infra would race the
# image-import step and crash-loop).
---
# 1) desktop-isolation — Browser Lab session pods.
#
# Locks down pods labeled `app.kubernetes.io/name=remote-desktop` (every
# session pod regardless of template). Allows guacd ingress for the VNC/RDP
# display lane and remotedesktop-web's pre-handoff probing. Egress: NFS to
# Synology, DNS, Traefik (cluster + LB VIP), Intranet (Browser Lab home).
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: desktop-isolation
namespace: fc-desktop
labels:
app.kubernetes.io/part-of: remotedesktop
app.kubernetes.io/component: isolation
spec:
podSelector:
matchLabels:
app.kubernetes.io/name: remote-desktop
policyTypes:
- Ingress
- Egress
ingress:
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: guacamole
ports:
- port: 3000
protocol: TCP
- port: 3001
protocol: TCP
- port: 5901
protocol: TCP
- port: 3389
protocol: TCP
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: fc-desktop
podSelector:
matchLabels:
app.kubernetes.io/name: remotedesktop-web
ports:
- port: 3000
protocol: TCP
- port: 5901
protocol: TCP
egress:
# NFS to Synology
- 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
- to:
- ipBlock:
cidr: 10.0.58.3/32
ports:
- port: 445
protocol: TCP
- to: []
ports:
- port: 53
protocol: UDP
- port: 53
protocol: TCP
- to:
- ipBlock:
cidr: 10.0.56.200/32
- ipBlock:
cidr: 10.43.33.87/32
- 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: 8000
protocol: TCP
- port: 8443
protocol: TCP
- to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: intranet
podSelector:
matchLabels:
app: intranet-web
ports:
- port: 5300
protocol: TCP
---
# 2) fc-desktop-default-deny — namespace-wide catch-all.
#
# Selects every pod EXCEPT remotedesktop-web (the public-surface control
# plane) and applies default-deny semantics for both Ingress and Egress.
# Closes the gap where session pods land WITHOUT the desktop-isolation
# policy's `app.kubernetes.io/name=remote-desktop` label, plus prevents
# arbitrary debug sidecars / kubectl debug images from getting cluster
# access.
#
# CRITICAL: also catches transient cm-acme-http-solver pods (that's the
# bug this whole regroup chased). The cm-acme-http-solver-allow policy
# below is the explicit carve-out.
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: fc-desktop-default-deny
namespace: fc-desktop
labels:
app.kubernetes.io/part-of: remotedesktop
app.kubernetes.io/component: isolation
spec:
podSelector:
matchExpressions:
- key: app.kubernetes.io/name
operator: NotIn
values:
- remotedesktop-web
policyTypes:
- Ingress
- Egress
---
# 3) remotedesktop-web-isolation — control plane explicit allow-list.
#
# remotedesktop-web is the only pod label the default-deny excludes, so
# without this policy the control plane would have wide-open Ingress AND
# Egress. This re-introduces a tight allow-list:
# - Ingress: Traefik only on TCP/8080
# - Egress: CoreDNS, K8s API, Guacamole admin, NFS, Intranet,
# Traefik (cluster + LB), and the fc-desktop namespace itself
# (for session pod readiness probing).
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: remotedesktop-web-isolation
namespace: fc-desktop
labels:
app.kubernetes.io/part-of: remotedesktop
app.kubernetes.io/component: isolation
spec:
podSelector:
matchLabels:
app.kubernetes.io/name: remotedesktop-web
policyTypes:
- Ingress
- Egress
ingress:
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: traefik-system
podSelector:
matchLabels:
app.kubernetes.io/name: traefik
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
# K8s API server
- to: []
ports:
- port: 443
protocol: TCP
- port: 6443
protocol: TCP
# Guacamole admin
- to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: guacamole
ports:
- port: 8080
protocol: TCP
# NFS to Synology
- 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
# Intranet web
- to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: intranet
podSelector:
matchLabels:
app: intranet-web
ports:
- port: 5300
protocol: TCP
# Cluster Traefik pods (in-cluster service resolution + Guacamole
# routing handoff where web app builds URLs against the public host
# but resolves internally).
- to:
- 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
# fc-desktop namespace — session pod probing during browser-access
# readiness checks.
- to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: fc-desktop
ports:
- port: 3000
protocol: TCP
- port: 3001
protocol: TCP
- port: 5901
protocol: TCP
- port: 3389
protocol: TCP
---
# 4) cm-acme-http-solver-allow — cert-manager HTTP-01 carve-out.
#
# Without this, fc-desktop-default-deny catches the transient solver pods
# cert-manager creates for each renewal (they don't carry the
# remotedesktop-web label). Caused 8-day silent renewal failure on
# desktop.iamworkin.lan in 2026-04-28..2026-05-07 (see
# feedback_certmanager_renewal_stuck_when_solver_blocked_by_namespace_default_deny.md).
#
# Authorizes:
# - Ingress on TCP/8089 from cluster Traefik (which proxies the external
# HTTP-01 GET on port 80 through to the solver).
# - Egress for cluster DNS (defensive — newer cert-manager probes from
# inside the solver too).
#
# The `acme.cert-manager.io/http01-solver=true` label is set by
# cert-manager itself on every solver pod automatically.
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: cm-acme-http-solver-allow
namespace: fc-desktop
labels:
app.kubernetes.io/part-of: remotedesktop
app.kubernetes.io/component: cert-renewal
spec:
podSelector:
matchLabels:
acme.cert-manager.io/http01-solver: "true"
policyTypes:
- Ingress
- Egress
ingress:
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: traefik-system
podSelector:
matchLabels:
app.kubernetes.io/name: traefik
ports:
- port: 8089
protocol: TCP
egress:
- to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: kube-system
podSelector:
matchLabels:
k8s-app: kube-dns
ports:
- port: 53
protocol: UDP
- port: 53
protocol: TCP

View File

@@ -1,26 +0,0 @@
# 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

@@ -1,30 +0,0 @@
# 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

@@ -1,81 +0,0 @@
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

@@ -1,19 +0,0 @@
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

@@ -1,109 +0,0 @@
# 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:v20260519-sp34cl3-fix
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

@@ -1,151 +0,0 @@
# 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.
#
# SCALED TO 0 — 2026-05-19 morning-routine cleanup.
# The Web pod cannot start until TWO upstream gaps close:
# 1. MySQL DB instance `flowercore_devicemgmt` (user `fc_devicemgmt`) is
# provisioned via fc-mysql Manager. The cluster currently has ZERO
# MySqlInstanceCrds and no `mysql.fc-mysql.svc:3306` Service, so the
# deployment-web container env `FlowerCore__Database__Host=mysql.fc-mysql.svc`
# points at nothing. Provision via the fc-mysql Manager UI/REST/MCP.
# 2. 1Password vault item `IAmWorkin/FlowerCore DeviceManagement Runtime`
# with 5 fields (DB-Password, mtls-ca.pem, mtls-client.crt, mtls-client.key,
# mtls-chain.pem) — see apps/fc-devicemgmt/1password-item.yaml. Mint mTLS
# from step-ca-agent ClusterIssuer per ADR-126; DB-Password must match the
# password configured for the MySQL user.
# Re-enable: change replicas back to 2 after both gaps close. The image tag
# in this file (v20260512-cx5) MAY also need a refresh — it predates the
# Sprint 34 Cl-3 operator fix; Web may have an analogous bug.
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: 0
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

@@ -1,55 +0,0 @@
# 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

@@ -1,13 +0,0 @@
# 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

@@ -1,224 +0,0 @@
# 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

@@ -1,22 +0,0 @@
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

@@ -1,12 +0,0 @@
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

@@ -118,7 +118,7 @@ spec:
# dotnet.exe publish -c Release -o deploy/app \ # dotnet.exe publish -c Release -o deploy/app \
# src/FlowerCore.Distribution.Web/FlowerCore.Distribution.Web.csproj # src/FlowerCore.Distribution.Web/FlowerCore.Distribution.Web.csproj
# podman build -t localhost/fc-distribution:v<tag> -f deploy/Dockerfile.deploy deploy # podman build -t localhost/fc-distribution:v<tag> -f deploy/Dockerfile.deploy deploy
image: localhost/fc-distribution:v202605061948 image: localhost/fc-distribution:v202604240010
imagePullPolicy: Never imagePullPolicy: Never
ports: ports:
- containerPort: 8080 - containerPort: 8080
@@ -151,10 +151,6 @@ spec:
value: "/signing/aistation-field/chain.pem" value: "/signing/aistation-field/chain.pem"
- name: FlowerCore__Distribution__Signing__EditionCerts__aistation-field__KeyPath - name: FlowerCore__Distribution__Signing__EditionCerts__aistation-field__KeyPath
value: "/signing/aistation-field/private-key.pem" value: "/signing/aistation-field/private-key.pem"
# Public distribution host is GET/HEAD-only at Traefik; this
# entitlement list controls which editions are readable there.
- name: FlowerCore__Distribution__EntitlementPublic__PublicEditions__0
value: "*"
resources: resources:
requests: requests:
cpu: 100m cpu: 100m
@@ -266,12 +262,8 @@ spec:
kind: ClusterIssuer kind: ClusterIssuer
dnsNames: dnsNames:
- dist.iamworkin.lan - dist.iamworkin.lan
# step-ca ACME caps lifetime at 30d; requesting 90d silently capped duration: 2160h # 90d
# made renewBefore=cert-lifetime → perpetual renewal loop (10880+ CRs renewBefore: 720h # 30d
# in 18h on 2026-05-07). Match working 720h/240h pattern from other
# FC services.
duration: 720h # 30d (step-ca cap)
renewBefore: 240h # 10d
--- ---
apiVersion: traefik.io/v1alpha1 apiVersion: traefik.io/v1alpha1
kind: IngressRoute kind: IngressRoute

View File

@@ -1,171 +0,0 @@
# fc-redis — SignalR backplane for cross-product event bus
#
# Lands per Q-SO-1 resolution (2026-05-11 PM): SignalR backplane in Phase A,
# not Phase C as originally drafted. Operator directive: "Redis can be
# deployed just fine as it's another FlowerCore technology we'll want to
# manage."
#
# Phase A scope (this file):
# - Single Redis 7.x Alpine pod
# - 1Gi Longhorn RWO PVC for AOF persistence
# - ClusterIP Service at `redis.fc-redis.svc.cluster.local:6379`
# - No AUTH (in-cluster only; not exposed externally)
# - No IngressRoute (backplane is server-to-server only)
#
# Consumers (Phase A IMPL across FC services):
# - FlowerCore.Signage.Web (OpsConsoleHub)
# - FlowerCore.Scoreboard.Web (ScoreboardHub)
# - FlowerCore.SignalControl.Web
# - FlowerCore.DMS.Web
# - Any other product joining the cross-product event bus
#
# Each consumer adds:
# services.AddSignalR()
# .AddStackExchangeRedis(
# "redis.fc-redis.svc.cluster.local:6379",
# opts => opts.Configuration.ChannelPrefix =
# StackExchange.Redis.RedisChannel.Literal("fc-opsconsole"));
#
# Phase B / C follow-ons (out of scope here):
# - Redis Sentinel for HA (3-node)
# - AUTH password from 1Password Connect (rotate via /rotate-password)
# - redis_exporter sidecar for Prometheus scrape
# - Network policies restricting which namespaces can dial 6379
#
# Design: docs/signage/operations-console-phase-2-design.md §3.5
# Decision: Q-SO-1 (RESOLVED 2026-05-11 PM)
# Memory: feedback_blooming_ui_pattern_no_iframes
---
apiVersion: v1
kind: Namespace
metadata:
name: fc-redis
labels:
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: fc-redis-data
namespace: fc-redis
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
resources:
requests:
storage: 1Gi
---
apiVersion: v1
kind: ConfigMap
metadata:
name: fc-redis-config
namespace: fc-redis
data:
redis.conf: |
# Phase A — minimal config; no AUTH, no replication.
bind 0.0.0.0
protected-mode no
port 6379
tcp-backlog 511
timeout 0
tcp-keepalive 300
# Persistence: AOF (fsync every second is the standard SignalR-backplane
# durability sweet spot — the backplane only needs to survive Redis
# restarts, not absolute zero loss).
appendonly yes
appendfsync everysec
auto-aof-rewrite-percentage 100
auto-aof-rewrite-min-size 64mb
# Reasonable defaults — let Redis pick most things.
maxmemory-policy allkeys-lru
maxmemory 256mb
# Logging
loglevel notice
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: fc-redis
namespace: fc-redis
labels:
app: fc-redis
spec:
replicas: 1
strategy:
type: Recreate # RWO PVC; do not do rolling update
selector:
matchLabels:
app: fc-redis
template:
metadata:
labels:
app: fc-redis
spec:
securityContext:
runAsNonRoot: true
runAsUser: 999 # redis:7-alpine default uid
runAsGroup: 999
fsGroup: 999
containers:
- name: redis
image: redis:7-alpine
imagePullPolicy: IfNotPresent
command: ["redis-server", "/etc/redis/redis.conf"]
ports:
- name: redis
containerPort: 6379
resources:
requests:
cpu: "50m"
memory: "128Mi"
limits:
cpu: "500m"
memory: "384Mi"
volumeMounts:
- name: data
mountPath: /data
- name: config
mountPath: /etc/redis
readOnly: true
livenessProbe:
tcpSocket:
port: 6379
initialDelaySeconds: 5
periodSeconds: 10
readinessProbe:
exec:
command: ["redis-cli", "ping"]
initialDelaySeconds: 2
periodSeconds: 5
securityContext:
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop: [ALL]
volumes:
- name: data
persistentVolumeClaim:
claimName: fc-redis-data
- name: config
configMap:
name: fc-redis-config
---
apiVersion: v1
kind: Service
metadata:
name: redis
namespace: fc-redis
spec:
type: ClusterIP
selector:
app: fc-redis
ports:
- name: redis
port: 6379
targetPort: 6379
protocol: TCP

View File

@@ -1,14 +0,0 @@
# 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

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

View File

@@ -1,26 +0,0 @@
# 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

@@ -1,17 +0,0 @@
# 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

@@ -1,15 +0,0 @@
{
"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

@@ -1,132 +0,0 @@
#!/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

@@ -1,144 +0,0 @@
#!/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

@@ -1,6 +0,0 @@
#!/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

@@ -1,44 +0,0 @@
#!/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

@@ -1,20 +0,0 @@
#!/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

@@ -1,46 +0,0 @@
#!/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

@@ -1,2 +0,0 @@
# 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

@@ -1,16 +0,0 @@
[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

@@ -1,8 +0,0 @@
[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

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

View File

@@ -1,7 +0,0 @@
[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

@@ -1,30 +0,0 @@
[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

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

View File

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

View File

@@ -1,22 +0,0 @@
#!/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

@@ -1,64 +0,0 @@
#!/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

@@ -1,68 +0,0 @@
#!/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

@@ -30,7 +30,6 @@ import logging
import re import re
import shlex import shlex
import subprocess import subprocess
import unicodedata
from typing import Optional from typing import Optional
from fastapi import FastAPI, HTTPException from fastapi import FastAPI, HTTPException
@@ -61,189 +60,6 @@ class TtsRequest(BaseModel):
volume: int = 100 # 0-200 volume: int = 100 # 0-200
HEBREW_CHAR_RE = re.compile(r"[\u0590-\u05FF]")
HEBREW_WORD_RE = re.compile(r"[\u0590-\u05FF]+")
# eSpeak-NG's Hebrew voice can spell unpointed Hebrew as Unicode character
# names on some builds. For source-text study reads, prefer a stable
# scholarly transliteration so words sound like words even without niqqud.
HEBREW_WORD_TRANSLITERATIONS = {
"אב": "av",
"אבא": "abba",
"אברהם": "Avraham",
"אדמה": "adamah",
"אדני": "Adonai",
"אדם": "adam",
"אור": "or",
"אלהים": "Elohim",
"אלוהים": "Elohim",
"אמן": "amen",
"אם": "em",
"אמת": "emet",
"ארץ": "eretz",
"אש": "esh",
"את": "et",
"בית": "beit",
"בן": "ben",
"ברא": "bara",
"בראשית": "bereshit",
"ברית": "berit",
"ברוך": "barukh",
"בת": "bat",
"גוי": "goy",
"גוים": "goyim",
"גויים": "goyim",
"דבר": "davar",
"דברים": "devarim",
"דוד": "David",
"הלל": "hallel",
"הארץ": "ha-aretz",
"הברית": "ha-berit",
"החדשה": "ha-chadashah",
"השמים": "ha-shamayim",
"השמיים": "ha-shamayim",
"ויאמר": "vayomer",
"יהוה": "Adonai",
"יוסף": "Yosef",
"יוחנן": "Yochanan",
"ישראל": "Yisrael",
"ישוע": "Yeshua",
"יצחק": "Yitzchak",
"יעקב": "Yaakov",
"ירושלים": "Yerushalayim",
"כהן": "kohen",
"כהנים": "kohanim",
"מים": "mayim",
"מות": "mavet",
"מושיע": "moshia",
"מלך": "melekh",
"מלכות": "malkhut",
"מרים": "Miriam",
"משה": "Moshe",
"משיח": "Mashiach",
"נביא": "navi",
"נביאים": "neviim",
"עם": "am",
"עולם": "olam",
"צדק": "tzedek",
"קדוש": "qadosh",
"קדושים": "qedoshim",
"קול": "qol",
"רוח": "ruach",
"שאול": "Shaul",
"שמים": "shamayim",
"שמיים": "shamayim",
"שמעון": "Shimon",
"שלום": "Shalom",
"תורה": "torah",
"חכמה": "chokhmah",
"חסד": "chesed",
"חיים": "chayim",
"חושך": "choshekh",
}
HEBREW_LETTERS = {
"א": "a",
"ב": "b",
"ג": "g",
"ד": "d",
"ה": "h",
"ו": "v",
"ז": "z",
"ח": "kh",
"ט": "t",
"י": "y",
"כ": "kh",
"ך": "kh",
"ל": "l",
"מ": "m",
"ם": "m",
"נ": "n",
"ן": "n",
"ס": "s",
"ע": "a",
"פ": "p",
"ף": "f",
"צ": "ts",
"ץ": "ts",
"ק": "q",
"ר": "r",
"ש": "sh",
"ת": "t",
}
HEBREW_VOWELISH = {"a", "e", "i", "o", "u"}
def _strip_hebrew_marks(value: str) -> str:
decomposed = unicodedata.normalize("NFD", value)
return "".join(
ch for ch in decomposed
if unicodedata.category(ch) != "Mn" and ch not in {"׳", "״", "־"}
)
def _fallback_hebrew_transliteration(word: str) -> str:
tokens: list[str] = []
chars = list(word)
for index, ch in enumerate(chars):
token = HEBREW_LETTERS.get(ch)
if token is None:
continue
if ch == "ה" and index == len(chars) - 1:
token = "ah"
elif ch == "י" and index > 0:
token = "i"
elif ch == "ו" and index > 0:
token = "o"
tokens.append(token)
if not tokens:
return word
spoken: list[str] = []
for index, token in enumerate(tokens):
spoken.append(token)
next_token = tokens[index + 1] if index + 1 < len(tokens) else ""
if (
token[-1:] not in HEBREW_VOWELISH
and next_token
and next_token[:1] not in HEBREW_VOWELISH
):
spoken.append("a")
return "".join(spoken)
def _transliterate_hebrew_word(match: re.Match[str]) -> str:
original = match.group(0)
normalized = _strip_hebrew_marks(original)
if not normalized:
return original
direct = HEBREW_WORD_TRANSLITERATIONS.get(normalized)
if direct:
return direct
if normalized.startswith("ו") and len(normalized) > 1:
rest = HEBREW_WORD_TRANSLITERATIONS.get(normalized[1:])
if rest:
return f"ve-{rest}"
if normalized.startswith("ה") and len(normalized) > 1:
rest = HEBREW_WORD_TRANSLITERATIONS.get(normalized[1:])
if rest:
return f"ha-{rest}"
return _fallback_hebrew_transliteration(normalized)
def _prepare_synthesis_input(text: str, language: str, voice: str) -> tuple[str, str]:
if language.lower().startswith("he") and HEBREW_CHAR_RE.search(text):
spoken = HEBREW_WORD_RE.sub(_transliterate_hebrew_word, text)
return spoken, "en-us"
return text, voice
def _resolve_voice(req: TtsRequest) -> str: def _resolve_voice(req: TtsRequest) -> str:
if req.voice: if req.voice:
return req.voice.strip() return req.voice.strip()
@@ -299,15 +115,14 @@ def tts(req: TtsRequest) -> Response:
raise HTTPException(status_code=400, detail="text is required") raise HTTPException(status_code=400, detail="text is required")
voice = _resolve_voice(req) voice = _resolve_voice(req)
spoken_text, synth_voice = _prepare_synthesis_input(req.text, req.language, voice)
args = [ args = [
"--stdout", "--stdout",
"-v", synth_voice, "-v", voice,
"-s", str(max(80, min(450, req.rate))), "-s", str(max(80, min(450, req.rate))),
"-p", str(max(0, min(99, req.pitch))), "-p", str(max(0, min(99, req.pitch))),
"-a", str(max(0, min(200, req.volume))), "-a", str(max(0, min(200, req.volume))),
] ]
wav = _run_espeak(args, spoken_text.encode("utf-8")) wav = _run_espeak(args, req.text.encode("utf-8"))
if not wav: if not wav:
raise HTTPException(status_code=500, detail="espeak-ng returned empty stdout") raise HTTPException(status_code=500, detail="espeak-ng returned empty stdout")
return Response(content=wav, media_type="audio/wav") return Response(content=wav, media_type="audio/wav")
@@ -338,9 +153,9 @@ def tts(req: TtsRequest) -> Response:
PHONEME_DURATION_RE = re.compile(r"^\s*\S+\s+(\d+)\s+", re.MULTILINE) PHONEME_DURATION_RE = re.compile(r"^\s*\S+\s+(\d+)\s+", re.MULTILINE)
def _estimate_total_ms(req: TtsRequest, voice: str, spoken_text: str) -> int: def _estimate_total_ms(req: TtsRequest, voice: str) -> int:
args = ["--pho", "--quiet", "-v", voice, "-s", str(req.rate)] args = ["--pho", "--quiet", "-v", voice, "-s", str(req.rate)]
out = _run_espeak(args, spoken_text.encode("utf-8")) out = _run_espeak(args, req.text.encode("utf-8"))
text = out.decode("utf-8", errors="replace") text = out.decode("utf-8", errors="replace")
total = 0 total = 0
for match in PHONEME_DURATION_RE.finditer(text): for match in PHONEME_DURATION_RE.finditer(text):
@@ -360,8 +175,7 @@ def timings(req: TtsRequest):
if not req.text.strip(): if not req.text.strip():
raise HTTPException(status_code=400, detail="text is required") raise HTTPException(status_code=400, detail="text is required")
voice = _resolve_voice(req) voice = _resolve_voice(req)
spoken_text, synth_voice = _prepare_synthesis_input(req.text, req.language, voice) total_ms = _estimate_total_ms(req, voice)
total_ms = _estimate_total_ms(req, synth_voice, spoken_text)
# Distribute total_ms across whitespace-split words proportional to # Distribute total_ms across whitespace-split words proportional to
# character count. Punctuation-only tokens are folded into the previous # character count. Punctuation-only tokens are folded into the previous
@@ -390,7 +204,7 @@ def timings(req: TtsRequest):
{ {
"text": req.text, "text": req.text,
"language": req.language, "language": req.language,
"voice": synth_voice, "voice": voice,
"words": out_words, "words": out_words,
"durationMs": total_ms, "durationMs": total_ms,
} }

View File

@@ -359,7 +359,7 @@ spec:
runAsUser: 1654 runAsUser: 1654
containers: containers:
- name: biblical-tts - name: biblical-tts
image: localhost/fc-biblical-tts:v20260506-hebrew-translit image: localhost/fc-biblical-tts:v1
imagePullPolicy: Never imagePullPolicy: Never
ports: ports:
- containerPort: 10402 - containerPort: 10402
@@ -532,7 +532,7 @@ spec:
fsGroupChangePolicy: OnRootMismatch fsGroupChangePolicy: OnRootMismatch
containers: containers:
- name: web - name: web
image: localhost/fc-ttsreader-web:v20260603-s54cx14-pr29-live image: localhost/fc-ttsreader-web:v20260506-47a88ae
imagePullPolicy: Never imagePullPolicy: Never
ports: ports:
- containerPort: 5217 - containerPort: 5217
@@ -554,16 +554,10 @@ spec:
value: "/data/chapter-context.db" value: "/data/chapter-context.db"
- name: TtsReader__Jobs__Root - name: TtsReader__Jobs__Root
value: "/data/jobs" value: "/data/jobs"
- name: TtsReader__Export__LocalCasRoot
value: "/data/bundles/cas"
- name: TtsReader__Piper__Host - name: TtsReader__Piper__Host
value: "10.0.57.17" value: "ttsreader-piper.fc-ttsreader.svc.cluster.local."
- name: TtsReader__Piper__Port - name: TtsReader__Piper__Port
value: "8500" value: "10200"
- name: TtsReader__Piper__Transport
value: "http"
- name: TtsReader__Piper__HttpPath
value: "/tts"
- name: TtsReader__Kokoro__Enabled - name: TtsReader__Kokoro__Enabled
value: "true" value: "true"
- name: TtsReader__Kokoro__BaseUrl - name: TtsReader__Kokoro__BaseUrl
@@ -574,14 +568,6 @@ spec:
value: "http://ttsreader-kokoro.fc-ttsreader.svc.cluster.local.:8880" value: "http://ttsreader-kokoro.fc-ttsreader.svc.cluster.local.:8880"
- name: TtsReader__Kokoro__TimeoutSeconds - name: TtsReader__Kokoro__TimeoutSeconds
value: "120" value: "120"
- name: FlowerCore__Tts__BiblicalTts__Enabled
value: "true"
- name: FlowerCore__Tts__BiblicalTts__BaseUrl
value: "http://ttsreader-biblical.fc-ttsreader.svc.cluster.local.:10402"
- name: FlowerCore__Tts__BiblicalTts__TimeoutSeconds
value: "60"
- name: FlowerCore__Tts__BiblicalTts__DefaultLanguage
value: "grc"
- name: Speech__Alignment__Enabled - name: Speech__Alignment__Enabled
# Cluster-native faster-whisper (Lane F, 2026-04-25). The # Cluster-native faster-whisper (Lane F, 2026-04-25). The
# ttsreader-align deployment in this manifest wraps # ttsreader-align deployment in this manifest wraps
@@ -617,8 +603,6 @@ spec:
# the writable PVC mount. # the writable PVC mount.
- name: TtsReader__Preview__CacheDirectory - name: TtsReader__Preview__CacheDirectory
value: "/data/voice-previews" value: "/data/voice-previews"
- name: TtsReader__VoiceLibrary__ReferenceClip__Directory
value: "/data/voice-reference-clips"
# Sprint E XXL Phase 4γ — content-addressed CDN bundle dir for # Sprint E XXL Phase 4γ — content-addressed CDN bundle dir for
# POST /api/v1/render. Default "wwwroot/cdn" resolves under the # POST /api/v1/render. Default "wwwroot/cdn" resolves under the
# read-only app filesystem, so pin to the writable PVC mount # read-only app filesystem, so pin to the writable PVC mount

View File

@@ -1,47 +0,0 @@
# fc-updater — Update Center GitOps adoption
**Status:** adopted into `bluejay-infra` on 2026-05-06. The live ArgoCD
Application is `infra-fc-updater`, generated by the `bluejay-infra`
ApplicationSet with automated sync, `prune: true`, and `selfHeal: true`.
## Managed manifest set
`apps/fc-updater/fc-updater.yaml` manages:
- `Namespace/fc-updater`
- `PersistentVolumeClaim/updatecenter-data`
- `Deployment/updatecenter-web`
- `Service/updatecenter-web`
- `Certificate/updatecenter-web-tls`
- `Certificate/updatecenter-web-internal-tls`
- `IngressRoute/updatecenter-web`
- `IngressRoute/updatecenter-web-internal`
- `IngressRoute/updatecenter-web-public`
The Deployment intentionally sets `revisionHistoryLimit: 3` and
`strategy.type: Recreate`. The service is singleton + SQLite/local bundle
storage on `PersistentVolumeClaim/updatecenter-data`, pinned to
`rke2-server`.
## Runtime dependencies intentionally not stored here
These live Secrets are pre-existing runtime material and are not committed to
Git:
- `updater-bootstrap-auth`
- `updater-signing`
- `updater-webhooks`
- `cf-origin-flowercore-io`
Rotate the Cloudflare Origin Certificate through
`FlowerCore.Notes/docs/standards/code-signing-rotation-runbook.md`; the
shared origin cert must exist in every namespace that serves a
`*.flowercore.io` public IngressRoute.
## Verification
```powershell
kubectl.exe --kubeconfig C:\Users\AndrewStoltz\.kube\rke2.yaml -n argocd get application infra-fc-updater
kubectl.exe --kubeconfig C:\Users\AndrewStoltz\.kube\rke2.yaml -n fc-updater get deploy,svc,ingressroute,certificate,pvc
curl.exe -sk https://update.flowercore.io/api/v1/manifests/_schema
```

View File

@@ -1,271 +0,0 @@
# FlowerCore Update Center
# GitOps adoption of the live fc-updater namespace after PUB-1/PUB-3.
# Runtime credentials remain in existing K8s Secrets; do not store them here.
---
apiVersion: v1
kind: Namespace
metadata:
name: fc-updater
labels:
app.kubernetes.io/part-of: flowercore
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: updatecenter-data
namespace: fc-updater
labels:
app.kubernetes.io/name: updatecenter-web
app.kubernetes.io/part-of: flowercore
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
volumeMode: Filesystem
resources:
requests:
# Sized for fleet bundle storage (LocalFsBundleStore.MaxTotalBytes
# soft cap at 25 GiB per project_uc_remaining_4_apps_signed_2026_05_06).
# Mike Bundle alone is ~5.1 GiB; cluster live capacity is already
# 20 GiB after a manual expand. PVCs cannot shrink, so git must track
# at least the live size to avoid the OutOfSync loop.
storage: 25Gi
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: updatecenter-web
namespace: fc-updater
labels:
app: updatecenter-web
app.kubernetes.io/name: updatecenter-web
app.kubernetes.io/part-of: flowercore
spec:
replicas: 1
revisionHistoryLimit: 3
strategy:
# SQLite + local bundle storage live on a single RWO PVC. Recreate avoids
# two pods overlapping the same write path during future image bumps.
type: Recreate
selector:
matchLabels:
app: updatecenter-web
template:
metadata:
labels:
app: updatecenter-web
spec:
nodeName: rke2-server
containers:
- name: web
image: localhost/fc-updater-web:v202605310029-7974fc4
imagePullPolicy: Never
ports:
- containerPort: 8080
name: http
env:
- name: ASPNETCORE_URLS
value: http://+:8080
- name: FlowerCore__Updater__Database__Provider
value: sqlite
- name: FlowerCore__Updater__Database__ConnectionString
value: Data Source=/data/updatecenter.db
- name: FlowerCore__Updater__BundleStorage__LocalFs__RootDirectory
value: /data/bundles
- name: FlowerCore__Updater__PublicShares__RequirePublicVisibilityOnPublicHosts
value: "true"
- name: FlowerCore__Updater__PublicShares__Links__0__Code
value: 8f3c2a9e7d41
- name: FlowerCore__Updater__PublicShares__Links__0__AppId
value: flowercore.faith-ai-mike
- name: FlowerCore__Updater__PublicShares__Links__0__Channel
value: stable
- name: FlowerCore__Updater__PublicShares__Links__0__RuntimeId
value: win-x64
- name: FlowerCore__Updater__PublicShares__Links__0__DisplayName
value: Faith AI Mike Edition
- name: FlowerCore__Updater__PublicShares__Links__0__Headline
value: Faith AI Mike Edition
- name: FlowerCore__Updater__PublicShares__Links__0__Description
value: Private release link for Mike's Faith AI bundle.
- name: FlowerCore__Audit__Sinks__Loki__Enabled
value: "false"
- name: FlowerCore__Updater__Auth__Bootstrap__Enabled
value: "true"
- name: FlowerCore__Updater__Auth__Bootstrap__Username
valueFrom:
secretKeyRef:
name: updater-bootstrap-auth
key: username
- name: FlowerCore__Updater__Auth__Bootstrap__Password
valueFrom:
secretKeyRef:
name: updater-bootstrap-auth
key: password
- name: FlowerCore__Updater__Auth__Bootstrap__SigningKey
valueFrom:
secretKeyRef:
name: updater-bootstrap-auth
key: signing-key
- name: FlowerCore__Updater__Signing__AutoSignOnPublish
value: "true"
- name: FlowerCore__Updater__Signing__RequireSignatureOnPublish
value: "true"
- name: FlowerCore__Updater__Signing__PfxBase64
valueFrom:
secretKeyRef:
name: updater-signing
key: pfx-base64
- name: FlowerCore__Updater__Signing__PfxPassword
valueFrom:
secretKeyRef:
name: updater-signing
key: pfx-password
- name: FlowerCore__Updater__Signing__OpItemReference
value: op://FlowerCore/step-ca-codesign
- name: FlowerCore__Updater__Signing__TrustAnchorPath
value: /etc/flowercore-updater/signing/root-ca.pem
- name: FlowerCore__Updater__GitHub__Token
valueFrom:
secretKeyRef:
name: updater-webhooks
key: github-token
- name: FlowerCore__Updater__GitHub__WebhookSecret
valueFrom:
secretKeyRef:
name: updater-webhooks
key: github-webhook-secret
- name: FlowerCore__Updater__Gitea__Token
valueFrom:
secretKeyRef:
name: updater-webhooks
key: gitea-token
- name: FlowerCore__Updater__Gitea__WebhookSecret
valueFrom:
secretKeyRef:
name: updater-webhooks
key: gitea-webhook-secret
readinessProbe:
tcpSocket:
port: http
initialDelaySeconds: 10
periodSeconds: 15
livenessProbe:
tcpSocket:
port: http
initialDelaySeconds: 30
periodSeconds: 30
volumeMounts:
- name: data
mountPath: /data
- name: signing
mountPath: /etc/flowercore-updater/signing
readOnly: true
volumes:
- name: data
persistentVolumeClaim:
claimName: updatecenter-data
- name: signing
secret:
secretName: updater-signing
items:
- key: root-ca.pem
path: root-ca.pem
---
apiVersion: v1
kind: Service
metadata:
name: updatecenter-web
namespace: fc-updater
labels:
app: updatecenter-web
app.kubernetes.io/name: updatecenter-web
app.kubernetes.io/part-of: flowercore
spec:
type: ClusterIP
selector:
app: updatecenter-web
ports:
- name: http
port: 8080
targetPort: http
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: updatecenter-web-tls
namespace: fc-updater
spec:
secretName: updatecenter-web-tls
issuerRef:
name: step-ca-acme
kind: ClusterIssuer
dnsNames:
- updatecenter.iamworkin.lan
- updates.iamworkin.lan
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: updatecenter-web-internal-tls
namespace: fc-updater
spec:
secretName: updatecenter-web-internal-tls
issuerRef:
name: step-ca-acme
kind: ClusterIssuer
dnsNames:
- updatecenter-internal.iamworkin.lan
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: updatecenter-web
namespace: fc-updater
spec:
entryPoints:
- web
- websecure
routes:
- match: (Host(`updatecenter.iamworkin.lan`) || Host(`updates.iamworkin.lan`)) && (Method(`GET`) || Method(`HEAD`) || Method(`POST`) || Method(`OPTIONS`))
kind: Rule
services:
- name: updatecenter-web
port: 8080
tls:
secretName: updatecenter-web-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: updatecenter-web-internal
namespace: fc-updater
spec:
entryPoints:
- web
- websecure
routes:
- match: Host(`updatecenter-internal.iamworkin.lan`)
kind: Rule
services:
- name: updatecenter-web
port: 8080
tls:
secretName: updatecenter-web-internal-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: updatecenter-web-public
namespace: fc-updater
spec:
entryPoints:
- websecure
routes:
- match: (Host(`update.flowercore.io`) || Host(`updates.flowercore.io`)) && (Method(`GET`) || Method(`HEAD`) || Method(`POST`) || Method(`OPTIONS`))
kind: Rule
services:
- name: updatecenter-web
port: 8080
tls:
secretName: cf-origin-flowercore-io

View File

@@ -1,7 +0,0 @@
# ArgoCD's bluejay-infra ApplicationSet uses a directory generator and does
# not require kustomization.yaml. Keep this anyway as the manifest inventory
# and for local `kubectl kustomize apps/fc-updater` previews.
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
resources:
- fc-updater.yaml

View File

@@ -1,11 +1,6 @@
# FlowerCore Tenant — retired flowercore.io placeholder. # FlowerCore Tenant — flowercore.io (main brand)
# # Public-facing placeholder landing page served by nginx
# Public flowercore.io/www.flowercore.io routing is now owned by # ArgoCD managed - BlueJay Lab
# apps/fc-landing/fc-landing.yaml. This tenant placeholder remains available
# only as an in-cluster service; do not create a duplicate public
# IngressRoute here because it competes with fc-landing and requires a
# namespace-local cf-origin-flowercore-io Secret.
# ArgoCD managed - BlueJay Lab
--- ---
apiVersion: v1 apiVersion: v1
kind: Namespace kind: Namespace
@@ -15,9 +10,15 @@ metadata:
app.kubernetes.io/part-of: bluejay-infra app.kubernetes.io/part-of: bluejay-infra
flowercore.io/tenant: flowercore flowercore.io/tenant: flowercore
--- ---
# Landing page HTML # NOTE: The existing cf-origin-flowercore-io secret (covering *.flowercore.io)
apiVersion: v1 # must be copied into this namespace. It already exists in other namespaces.
kind: ConfigMap # Copy with: kubectl get secret cf-origin-flowercore-io -n fc-system -o yaml \
# | sed 's/namespace: .*/namespace: tenant-flowercore/' \
# | kubectl apply -f -
---
# Landing page HTML
apiVersion: v1
kind: ConfigMap
metadata: metadata:
name: flowercore-web-html name: flowercore-web-html
namespace: tenant-flowercore namespace: tenant-flowercore
@@ -307,6 +308,25 @@ spec:
selector: selector:
app: flowercore-web app: flowercore-web
ports: ports:
- port: 80 - port: 80
targetPort: 80 targetPort: 80
name: http name: http
---
# Traefik IngressRoute — public via Cloudflare
# Uses existing cf-origin-flowercore-io cert (must be copied to this namespace)
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: flowercore-web
namespace: tenant-flowercore
spec:
entryPoints:
- websecure
routes:
- match: Host(`flowercore.io`) || Host(`www.flowercore.io`)
kind: Rule
services:
- name: flowercore-web
port: 80
tls:
secretName: cf-origin-flowercore-io

View File

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

View File

@@ -1,54 +0,0 @@
FROM myoung34/github-runner:latest
ARG RUBY_VERSION=3.3.11
ARG RUBY_MINOR=3.3
ARG RUBY_BUILD_VERSION=v20260326
ARG RUNNER_UID=1001
ARG RUNNER_GID=1001
ENV RUNNER_TOOL_CACHE=/home/runner/_tool
ENV RUNNER_RUBY_TOOLCACHE=/opt/runner-toolcache
ENV PATH="/home/runner/_tool/Ruby/${RUBY_MINOR}/x64/bin:/opt/runner-toolcache/Ruby/${RUBY_MINOR}/x64/bin:${PATH}"
USER root
# Bake the IAmWorkin step-ca root CA into the system trust store. Without
# this, .NET HttpClient calls from CI tests against *.iamworkin.lan
# (e.g. https://selenium.iamworkin.lan/session) fail with `PartialChain`
# because the runner image's default Ubuntu trust bundle doesn't include
# our internal Root CA. update-ca-certificates regenerates
# /etc/ssl/certs/ca-certificates.crt, which OpenSSL + .NET on Linux read
# automatically — no SSL_CERT_FILE env var needed.
COPY step-ca-root.crt /usr/local/share/ca-certificates/iamworkin-step-ca-root.crt
RUN apt-get update \
&& DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
autoconf \
bison \
build-essential \
ca-certificates \
curl \
libdb-dev \
libffi-dev \
libgdbm-dev \
libgmp-dev \
libncurses-dev \
libreadline-dev \
libssl-dev \
libyaml-dev \
patch \
pkg-config \
uuid-dev \
zlib1g-dev \
&& update-ca-certificates \
&& curl -fsSL "https://github.com/rbenv/ruby-build/archive/refs/tags/${RUBY_BUILD_VERSION}.tar.gz" -o /tmp/ruby-build.tar.gz \
&& mkdir -p /tmp/ruby-build \
&& tar -xzf /tmp/ruby-build.tar.gz --strip-components=1 -C /tmp/ruby-build \
&& /tmp/ruby-build/install.sh \
&& rm -rf /tmp/ruby-build /tmp/ruby-build.tar.gz /var/lib/apt/lists/*
COPY install-ruby-toolcache.sh /usr/local/bin/install-ruby-toolcache.sh
RUN chmod +x /usr/local/bin/install-ruby-toolcache.sh \
&& RUBY_VERSION="${RUBY_VERSION}" RUBY_MINOR="${RUBY_MINOR}" TOOLCACHE_ROOT="${RUNNER_RUBY_TOOLCACHE}" RUNNER_UID="${RUNNER_UID}" RUNNER_GID="${RUNNER_GID}" /usr/local/bin/install-ruby-toolcache.sh \
&& ruby -v

View File

@@ -1,133 +0,0 @@
# GitHub Runner Fleet
ArgoCD owns `apps/github-runner/github-runner.yaml`. Do not patch live runner
Deployments with `kubectl`; update this manifest and let ArgoCD reconcile.
## Runner Shape
All repo-scoped Linux runners use:
- `localhost/fc-github-runner:v20260525-ruby3.3.11-stepca`, derived from
`myoung34/github-runner:latest`
- `ACCESS_TOKEN` from the `github-runner-token` Secret
- `RUN_AS_ROOT=false`
- `EPHEMERAL=true`
- `LABELS=self-hosted,linux,fc-build-linux`
- writable non-root paths under `/home/runner` for .NET, NuGet, XDG cache, and
Actions tool cache
- Ruby 3.3.11 seeded into `/home/runner/_tool/Ruby/3.3/x64` from the baked
`/opt/runner-toolcache` copy so `ruby/setup-ruby@v1` can discover it on
self-hosted `ubuntu-20.04-x64` runners
`github-runner` for `FlowerCore.Common` is single-replica because it retains the
original Longhorn ReadWriteOnce NuGet PVC. Every other repo-scoped runner uses
two replicas with per-pod `emptyDir` caches. That is the safe backlog-drain
strategy: no two pods share one RWO PVC.
Sprint 32 final long-tail wave adds 16 two-replica Deployments:
`FlowerCore.Knowledge`, `FlowerCore.LlmBridge`, `FlowerCore.Media`,
`FlowerCore.Presentations`, `FlowerCore.RemoteDesktop`, `FlowerCore.DNS`,
`FlowerCore.Distribution`, `FlowerCore.Scoreboard`,
`FlowerCore.SegmentDisplay`, `FlowerCore.Signage.Contracts`,
`FlowerCore.SignalControl`, `FlowerCore.Intranet.Web`,
`FlowerCore.Provisioning`, `FlowerCore.Redis`, `FlowerCore.MessageBoard`, and
`FlowerCore.MenuBoard`.
## Image Build
Ruby is baked with a pinned `ruby-build` release and Ruby patch version. The pod
still mounts an `emptyDir` over `/home/runner`, so the `setup-runner-home` init
container copies the baked toolcache from `/opt/runner-toolcache/Ruby` into
`/home/runner/_tool/Ruby` before the runner container starts.
The IAmWorkin step-ca root CA is also baked into the system trust store
(`/usr/local/share/ca-certificates/iamworkin-step-ca-root.crt`, registered by
`update-ca-certificates`). Without it, .NET HttpClient calls from CI tests
against `*.iamworkin.lan` (e.g. `https://selenium.iamworkin.lan/session`)
fail with `PartialChain`. To refresh the bundled cert when the root rotates,
re-extract from the cluster and overwrite `step-ca-root.crt`:
```bash
kubectl get secret -n cert-manager step-ca-root \
-o jsonpath='{.data.ca\.crt}' | base64 -d > step-ca-root.crt
```
```bash
cd apps/github-runner
podman build -t localhost/fc-github-runner:v20260525-ruby3.3.11-stepca .
podman run --rm localhost/fc-github-runner:v20260525-ruby3.3.11-stepca ruby -v
podman run --rm localhost/fc-github-runner:v20260525-ruby3.3.11-stepca \
test -f /opt/runner-toolcache/Ruby/3.3/x64.complete
podman save localhost/fc-github-runner:v20260525-ruby3.3.11-stepca \
-o fc-github-runner-v20260525-ruby3.3.11-stepca.tar
```
Import the saved image on every schedulable RKE2 node before ArgoCD rolls the
Deployments:
```bash
for node in rke2-server rke2-agent1 rke2-agent2; do
scp fc-github-runner-v20260525-ruby3.3.11-stepca.tar "$node:/tmp/"
ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images rm localhost/fc-github-runner:v20260525-ruby3.3.11-stepca || true'
ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images import /tmp/fc-github-runner-v20260525-ruby3.3.11-stepca.tar'
done
```
## Post-Merge Proof
After the PR is merged and ArgoCD syncs, verify the runner fleet:
```bash
kubectl -n github-runner get deploy,pods,pvc
```
Verify the Ruby toolcache in a fresh pod:
```bash
kubectl -n github-runner exec deploy/github-runner-puppet -c runner -- ruby -v
kubectl -n github-runner exec deploy/github-runner-puppet -c runner -- sh -c \
'echo "$RUNNER_TOOL_CACHE" && test -f "$RUNNER_TOOL_CACHE/Ruby/3.3/x64.complete"'
```
Verify GitHub registration for the repo-scoped runners:
```bash
for repo in FlowerCore.Common FlowerCore.Shared.Pos FlowerCore.Puppet FlowerCore.Signage \
FlowerCore.DMS FlowerCore.Telephony FlowerCore.Print.Web FlowerCore.Chat \
FlowerCore.MySQL FlowerCore.Kiosk.Linux FlowerCore.Marquee FlowerCore.TtsReader \
FlowerCore.Knowledge FlowerCore.LlmBridge FlowerCore.Media \
FlowerCore.Presentations FlowerCore.RemoteDesktop FlowerCore.DNS \
FlowerCore.Distribution FlowerCore.Scoreboard FlowerCore.SegmentDisplay \
FlowerCore.Signage.Contracts FlowerCore.SignalControl FlowerCore.Intranet.Web \
FlowerCore.Provisioning FlowerCore.Redis FlowerCore.MessageBoard \
FlowerCore.MenuBoard; do
echo "=== $repo ==="
gh api "/repos/astoltz/$repo/actions/runners" \
--jq '.runners[] | select(.labels[].name == "fc-build-linux") | {name,status,busy,labels:[.labels[].name]}'
done
```
Shared.Pos publish proof after the runner pod is online:
```bash
gh run list --repo astoltz/FlowerCore.Shared.Pos \
--workflow "Build, Test & Publish" --branch main --limit 5
```
If the latest run is still queued after runner registration, rerun the workflow
from GitHub Actions and verify it lands on an `rke2-linux-*` runner.
## Failure Notes
- `actions/setup-dotnet` permission error at `/usr/share/dotnet`: check that
`DOTNET_INSTALL_DIR=/home/runner/.dotnet` and related cache env vars are
present on the runner pod.
- `ruby/setup-ruby@v1` says self-hosted runners must install Ruby in
`$RUNNER_TOOL_CACHE`: check that the init container copied
`/opt/runner-toolcache/Ruby` into `/home/runner/_tool/Ruby` and that
`/home/runner/_tool/Ruby/3.3/x64.complete` exists.
- `404` during runner registration: the fine-grained PAT is valid but missing
repository access for that repo. Add the repo to the PAT access list; the PAT
value does not change.
- `Multi-Attach` volume error: only the Common runner uses a RWO PVC and it must
stay single-replica. New multi-replica runners use `emptyDir`.

File diff suppressed because it is too large Load Diff

View File

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

View File

@@ -1,12 +0,0 @@
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----

View File

@@ -466,11 +466,11 @@ spec:
itemPath: vaults/IAmWorkin/items/Guacamole JSON Auth itemPath: vaults/IAmWorkin/items/Guacamole JSON Auth
--- ---
--- ---
# 1Password-backed credentials for Mac mini VNC access (Phase 1 <EFBFBD> 2026-04-28) # 1Password-backed credentials for Mac mini VNC access (Phase 1 2026-04-28)
# The operator mints Secret 'macmini-vnc-creds' with keys: username, password, VNC Password # The operator mints Secret 'macmini-vnc-creds' with keys: username, password, VNC Password
# Note: '1Password' field label 'VNC Password' -> K8s Secret key 'VNC Password' (space retained) # Note: '1Password' field label 'VNC Password' -> K8s Secret key 'VNC Password' (space retained)
# Guacamole VNC connection password is sourced from the 'VNC Password' field. # Guacamole VNC connection password is sourced from the 'VNC Password' field.
# Actual IP is 10.0.56.115 (INFRA VLAN) <EFBFBD> the 1P item 'IP' field is kept as backup reference. # Actual IP is 10.0.56.115 (INFRA VLAN) the 1P item 'IP' field is kept as backup reference.
apiVersion: onepassword.com/v1 apiVersion: onepassword.com/v1
kind: OnePasswordItem kind: OnePasswordItem
metadata: metadata:
@@ -481,7 +481,6 @@ metadata:
app.kubernetes.io/part-of: flowercore app.kubernetes.io/part-of: flowercore
spec: spec:
itemPath: vaults/IAmWorkin/items/Mac Mini itemPath: vaults/IAmWorkin/items/Mac Mini
---
# Blue Jay Branding Extension (CSS + translations) # Blue Jay Branding Extension (CSS + translations)
apiVersion: v1 apiVersion: v1
kind: ConfigMap kind: ConfigMap

View File

@@ -46,7 +46,7 @@ spec:
spec: spec:
containers: containers:
- name: intranet-web - name: intranet-web
image: localhost/fc-intranet-web:v20260531-ttsreader-bridge image: localhost/fc-intranet-web:v20260505-1108
imagePullPolicy: Never imagePullPolicy: Never
ports: ports:
- containerPort: 5300 - containerPort: 5300

View File

@@ -241,12 +241,8 @@ spec:
kind: ClusterIssuer kind: ClusterIssuer
dnsNames: dnsNames:
- knowledge.iamworkin.lan - knowledge.iamworkin.lan
# step-ca ACME caps lifetime at 30d; requesting 90d silently capped duration: 2160h # 90d
# made renewBefore=cert-lifetime → perpetual renewal loop (10888+ CRs renewBefore: 720h # 30d
# in 18h on 2026-05-07). Match working 720h/240h pattern from other
# FC services.
duration: 720h # 30d (step-ca cap)
renewBefore: 240h # 10d
--- ---
apiVersion: traefik.io/v1alpha1 apiVersion: traefik.io/v1alpha1
kind: IngressRoute kind: IngressRoute

View File

@@ -1,93 +0,0 @@
# =============================================================================
# ci1 - Windows Server 2025 KubeVirt VM (GitHub Actions Self-Hosted Runner)
# =============================================================================
# Boots from the sysprepped containerDisk template built by the Windows VM
# sysprep pipeline. See docs/infrastructure/windows-vm-sysprep-pipeline.md.
# Path A/B/C install history is preserved in git log only.
# =============================================================================
apiVersion: v1
kind: Namespace
metadata:
name: kubevirt-vms
labels:
app.kubernetes.io/part-of: kubevirt-stack
pod-security.kubernetes.io/enforce: privileged
---
apiVersion: kubevirt.io/v1
kind: VirtualMachine
metadata:
name: ci1
namespace: kubevirt-vms
labels:
app: ci-runner
role: github-actions-runner
flowercore.io/managed-by: bluejay-infra
spec:
runStrategy: Halted
template:
metadata:
labels:
app: ci-runner
role: github-actions-runner
kubevirt.io/vm: ci1
spec:
domain:
cpu:
cores: 8
sockets: 1
threads: 1
memory:
guest: 16Gi
resources:
requests:
memory: 16Gi
limits:
memory: 16Gi
clock:
utc: {}
timer:
hpet:
present: false
pit:
tickPolicy: delay
rtc:
tickPolicy: catchup
hyperv: {}
features:
acpi: {}
apic: {}
hyperv:
relaxed: {}
vapic: {}
spinlocks:
spinlocks: 8191
smm: {}
firmware:
bootloader:
efi:
secureBoot: false
devices:
tpm: {}
disks:
- name: rootdisk
disk:
bus: virtio
interfaces:
# Pod-network fallback for CI runner outbound traffic. Switch to
# prod-vlan57 once the bridge/NAD lane is ready for L2 access.
- name: default
masquerade: {}
model: virtio
machine:
type: q35
networks:
- name: default
pod: {}
volumes:
- name: rootdisk
containerDisk:
image: localhost/fc-win-server-2025:v1
imagePullPolicy: Never
terminationGracePeriodSeconds: 3600

View File

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

View File

@@ -1,69 +0,0 @@
# =============================================================================
# NetworkAttachmentDefinition — PROD VLAN 57 bridge
# =============================================================================
# Purpose: makes KubeVirt VMs reachable on the PROD VLAN (10.0.57.0/24)
# alongside the existing pod network. Required for ci1 to bridge onto PROD
# (e.g. to provision/scrape edge1, edge2, kiosks, Pis on the same L2 segment).
#
# **DEPLOY GATE — Phase 1.5 host work required first**:
# On every RKE2 node (rke2-server, rke2-agent1, rke2-agent2):
# 1. Switch port (UniFi USL16LP) trunks VLAN 57 to the node — usually
# already true since BLUEJAY-WS reaches 10.0.57.x services. Verify
# with `ip link show enp86s0.57` after configuring sub-interface, OR
# `tcpdump -ni enp86s0 vlan 57` and ping a known PROD host.
# 2. Linux bridge `br-prod` enslaving `enp86s0.57` (VLAN sub-interface).
# NetworkManager profile examples in the runbook below.
# 3. Verify Multus DaemonSet `kube-multus-ds` is Ready on all nodes.
#
# Without those, applying this NAD has no effect except to register the CRD.
# A VM that requests this NAD with no bridge present will fail with:
# `error adding pod kubevirt-vms_ci1 to CNI network "prod-vlan57": failed to
# plumb VLAN: open /sys/class/net/br-prod/master: no such file or directory`
#
# Configuration notes:
# - cniVersion 0.3.1 to match Multus daemon-config.json
# - mtu 1500 (matches enp86s0 default; bump if jumbo frames configured)
# - bridge name `br-prod` is convention; if Puppet picks a different name
# (e.g. `br57`, `br-vlan57`), edit BOTH this NAD and the ci1.yaml
# interface block. Keep them in sync.
# - vlan: 0 because the host bridge already strips VLAN tag (br-prod sits
# on top of `enp86s0.57`). If we instead used a VLAN-aware bridge with
# trunk port, set vlan: 57 here. Current convention is VLAN-stripped at
# the sub-interface, so the bridge passes untagged frames.
#
# Apply:
# kubectl --kubeconfig $env:USERPROFILE\.kube\rke2.yaml apply -f apps/kubevirt-vms/prod-vlan57-nad.yaml
#
# Then update ci1.yaml networks: stanza to:
# - name: prod-net
# multus:
# networkName: kubevirt-vms/prod-vlan57
# and the interface block from `masquerade` to `bridge`.
# =============================================================================
---
# Namespace must exist already (created by ci1.yaml's first document).
# This file imports a NAD into that same namespace.
apiVersion: k8s.cni.cncf.io/v1
kind: NetworkAttachmentDefinition
metadata:
name: prod-vlan57
namespace: kubevirt-vms
annotations:
bluejay.iamworkin.lan/host-bridge: "br-prod (enslaves enp86s0.57)"
bluejay.iamworkin.lan/cidr: "10.0.57.0/24"
bluejay.iamworkin.lan/gateway: "10.0.57.1"
bluejay.iamworkin.lan/dns: "10.0.56.1 (pfSense Unbound)"
spec:
config: |
{
"cniVersion": "0.3.1",
"name": "prod-vlan57",
"type": "bridge",
"bridge": "br-prod",
"ipam": {},
"mtu": 1500,
"vlan": 0,
"promiscMode": true,
"preserveDefaultVlan": false
}

View File

@@ -1,99 +0,0 @@
# =============================================================================
# Windows Server 2025 ISO — Static NFS PV (Path B for SATA-CDROM timeout)
# =============================================================================
# Purpose: Mount the ISO from Synology NAS via NFS instead of from a Longhorn-
# backed Filesystem PVC.
#
# Why: SATA-CDROM emulation reading from a Longhorn-backed Filesystem PVC is
# too slow for OVMF's boot read window — the DVD-ROM enumeration times out
# before the bootloader can be read. Symptom on the serial console:
# BdsDxe: failed to start Boot0001 "UEFI QEMU DVD-ROM QM00001 " from ...
# BdsDxe: failed to start Boot0001 ... Time out
# BdsDxe: No bootable option or device was found
# Diagnosis confirmed the ISO content is a perfectly valid bootable ISO9660
# image — the bug is in the timing path between OVMF and Longhorn-backed
# storage, not in the ISO itself.
#
# Block-mode PVC was tried (`volumeMode: Block` via DataVolume) and would
# likely fix the timing, but CDI v1.65.0's upload-target pod cannot open the
# block device due to runAsUser:107 + capabilities.drop:[ALL] and we got:
# blockdev: cannot open /dev/cdi-block-volume: Permission denied
#
# NFS-mounted ISO bypasses both issues: no Longhorn slowness, no CDI upload
# pod permission concerns. The ISO is read directly from the NAS over a
# native NFSv4.1 mount that QEMU's SATA emulator can read at full LAN speed.
#
# Layout on Synology:
# /volume1/ISOs/ (existing export, RKE2 ACL)
# en-us_windows_server_2025_updated_march_2026_x64_dvd_8e06425a.iso
# win2025-iso-disk/ (new subdir, 2026-05-08)
# disk.img -> hardlink to ../en-us_windows_server_2025_..._8e06425a.iso
#
# KubeVirt's launcher pod expects a PVC mounted at
# /var/run/kubevirt-private/vmi-disks/<diskName>/disk.img — by mounting the
# `win2025-iso-disk/` subdir as the NFS PV root, `disk.img` lives at the PV's
# root and KubeVirt's CDROM emulator finds it without any path manipulation.
#
# A symlink would NOT work for sub-path NFS mounts (the relative target
# `../...iso` falls outside the sub-mount root). A hardlink works because it
# references the same inode regardless of mount point.
#
# Memory references:
# - feedback_synology_nfs_volume1_kubernetes_export_scoped (Synology export
# scoping pattern — but /volume1/ISOs export, unlike /volume1/kubernetes,
# does support sub-path mounts because Synology NFS is configured with
# pseudo-fs in NFSv4.1)
# - feedback_kubevirt_iso_first_install_bootorder_and_runstrategy (boot
# order / runStrategy gotchas, separate from the storage timing issue)
#
# Validation (2026-05-08, from rke2-server / rke2-agent1 / rke2-agent2):
# mount -t nfs -o nfsvers=4.1,ro 10.0.58.3:/volume1/ISOs/win2025-iso-disk /tmp/m
# file /tmp/m/disk.img
# -> ISO 9660 CD-ROM filesystem data 'SSS_X64FRE_EN-US_DV9' (bootable)
# All 3 RKE2 nodes can mount and read.
# =============================================================================
apiVersion: v1
kind: PersistentVolume
metadata:
name: windows-server-2025-iso-nfs
labels:
flowercore.io/iso: windows-server-2025
flowercore.io/managed-by: bluejay-infra
spec:
capacity:
storage: 8Gi
accessModes:
- ReadOnlyMany
volumeMode: Filesystem
persistentVolumeReclaimPolicy: Retain
storageClassName: "" # static, no provisioner
mountOptions:
- nfsvers=4.1
- ro
- hard
- timeo=600
- retrans=3
nfs:
server: 10.0.58.3 # BlueJayNAS Synology DS1621+ on HOME VLAN 58
path: /volume1/ISOs/win2025-iso-disk
readOnly: true
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: windows-server-2025-iso-nfs
namespace: kubevirt-vms
labels:
app: ci-runner
flowercore.io/managed-by: bluejay-infra
spec:
accessModes:
- ReadOnlyMany
volumeMode: Filesystem
resources:
requests:
storage: 8Gi
storageClassName: ""
volumeName: windows-server-2025-iso-nfs

View File

@@ -207,13 +207,20 @@ spec:
- port: 993 - port: 993
targetPort: 993 targetPort: 993
name: imaps name: imaps
# --- mail-tls Certificate REMOVED 2026-06-01 --- ---
# mail-tls is now managed OUTSIDE cert-manager: issued from step-ca's JWK 'admin' # TLS Certificate via cert-manager
# provisioner and auto-renewed by a systemd timer on noc1 (step ca renew), which apiVersion: cert-manager.io/v1
# writes the mail-tls secret directly. step-ca-acme only has an HTTP-01 (Traefik) kind: Certificate
# solver, but mail.iamworkin.lan must resolve to the dedicated MetalLB IP 10.0.56.202 metadata:
# (SMTP/IMAP), so HTTP-01 cannot validate. Do NOT re-add a cert-manager Certificate name: mail-tls
# here unless a DNS-01 solver is deployed for step-ca-acme. namespace: mail
spec:
secretName: mail-tls
issuerRef:
name: step-ca-acme
kind: ClusterIssuer
dnsNames:
- mail.iamworkin.lan
--- ---
# Traefik IngressRoute - Webmail placeholder # Traefik IngressRoute - Webmail placeholder
apiVersion: traefik.io/v1alpha1 apiVersion: traefik.io/v1alpha1

File diff suppressed because one or more lines are too long

View File

@@ -1,297 +0,0 @@
# =============================================================================
# Multus CNI — Meta-CNI for multi-network attachment to pods/VMs
# =============================================================================
# Purpose: enable KubeVirt VMs (and any future workload) to attach additional
# network interfaces beyond the default Calico-managed pod network. Required
# for ci1 (Windows Server 2025 KubeVirt VM) to bridge onto PROD VLAN 57.
#
# Source: upstream k8snetworkplumbingwg/multus-cni v4.2.2
# https://github.com/k8snetworkplumbingwg/multus-cni/blob/v4.2.2/deployments/multus-daemonset-thick.yml
#
# Inlined verbatim (with project header + version pin annotation) for
# reproducibility and air-gap safety. Bumping versions = edit this file +
# git push. ArgoCD picks up via the bluejay-infra ApplicationSet
# (apps/* directory generator on main).
#
# Why thick plugin (not thin):
# - Thick = daemon + thin shim binary; daemon handles NAD watch + CRD reads
# centrally so each pod's CNI ADD doesn't hit the K8s API server. Better
# for clusters with many NAD-using pods.
# - Thin = each CNI ADD process directly contacts K8s API. Simpler but
# scales worse and has more failure modes.
# - KubeVirt + multi-VM workload pattern fits thick perfectly.
#
# Cluster context (verified 2026-05-08):
# - RKE2 v1.34.5 on 3 nodes (rke2-server, rke2-agent1, rke2-agent2)
# - Calico CNI (Tigera-managed) at /etc/cni/net.d + /opt/cni/bin (default)
# - openSUSE Leap 16, kernel 6.12, containerd 2.1.5
# - host bridge for PROD VLAN 57 = `br-prod` (PUPPET HOST WORK — see Phase 1.5
# in docs/infrastructure/windows-server-build-runner-plan.md)
#
# Version pin: snapshot-thick → pinning to v4.2.2 release tag at deploy time
# would require a private mirror of the image. Upstream `snapshot-thick` tag
# is updated on every release, so for now we trust upstream + Calico's
# established pattern. Pin to a specific SHA256 once we mirror to Gitea OCI.
#
# Apply (once committed to bluejay-infra main, ApplicationSet auto-syncs):
# git add apps/multus/multus.yaml && git commit && git push origin main
# # ArgoCD `infra-multus` Application appears within 3 min via ApplicationSet
#
# Verify:
# kubectl -n kube-system get ds kube-multus-ds
# kubectl -n kube-system rollout status ds kube-multus-ds
# kubectl get crd network-attachment-definitions.k8s.cni.cncf.io
# =============================================================================
---
apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
name: network-attachment-definitions.k8s.cni.cncf.io
annotations:
bluejay.iamworkin.lan/source: "k8snetworkplumbingwg/multus-cni v4.2.2"
spec:
group: k8s.cni.cncf.io
scope: Namespaced
names:
plural: network-attachment-definitions
singular: network-attachment-definition
kind: NetworkAttachmentDefinition
shortNames:
- net-attach-def
versions:
- name: v1
served: true
storage: true
schema:
openAPIV3Schema:
description: 'NetworkAttachmentDefinition is a CRD schema specified by the Network Plumbing
Working Group to express the intent for attaching pods to one or more logical or physical
networks. More information available at: https://github.com/k8snetworkplumbingwg/multi-net-spec'
type: object
properties:
apiVersion:
type: string
kind:
type: string
metadata:
type: object
spec:
description: 'NetworkAttachmentDefinition spec defines the desired state of a network attachment'
type: object
properties:
config:
description: 'NetworkAttachmentDefinition config is a JSON-formatted CNI configuration'
type: string
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: multus
rules:
- apiGroups: ["k8s.cni.cncf.io"]
resources:
- '*'
verbs:
- '*'
- apiGroups:
- ""
resources:
- pods
- pods/status
verbs:
- get
- list
- update
- watch
- apiGroups:
- ""
- events.k8s.io
resources:
- events
verbs:
- create
- patch
- update
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: multus
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: multus
subjects:
- kind: ServiceAccount
name: multus
namespace: kube-system
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: multus
namespace: kube-system
---
kind: ConfigMap
apiVersion: v1
metadata:
name: multus-daemon-config
namespace: kube-system
labels:
tier: node
app: multus
data:
daemon-config.json: |
{
"chrootDir": "/hostroot",
"cniVersion": "0.3.1",
"logLevel": "verbose",
"logToStderr": true,
"cniConfigDir": "/host/etc/cni/net.d",
"multusAutoconfigDir": "/host/etc/cni/net.d",
"multusConfigFile": "auto",
"socketDir": "/host/run/multus/"
}
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: kube-multus-ds
namespace: kube-system
labels:
tier: node
app: multus
name: multus
spec:
selector:
matchLabels:
name: multus
updateStrategy:
type: RollingUpdate
template:
metadata:
labels:
tier: node
app: multus
name: multus
spec:
hostNetwork: true
hostPID: true
tolerations:
- operator: Exists
effect: NoSchedule
- operator: Exists
effect: NoExecute
serviceAccountName: multus
containers:
- name: kube-multus
image: ghcr.io/k8snetworkplumbingwg/multus-cni:snapshot-thick
command: [ "/usr/src/multus-cni/bin/multus-daemon" ]
# 2026-05-11: upstream default of 50Mi memory limit OOM-cascades when
# an operator-owned namespace accumulates >100 pending pods retrying
# CNI ADD. RemoteDesktop emitted 219 orphan rd-browser-only pods
# (missing OwnerReferences), kubelet's CNI ADD avalanche pushed multus
# over 50Mi, OOMKilled, restarted with even bigger backlog → loop.
# 21h cluster outage. See FlowerCore.Notes:
# feedback_multus_50mi_limit_oom_orphan_pod_avalanche.md
# 1Gi limit / 512Mi request comfortably handles a 200+ pod CNI
# catchup burst on 64GB nodes (nodes are <25% used in steady-state).
# Drop back toward 256Mi only after MultusMemoryPressure alert
# proves steady-state working set sits well below 200Mi.
resources:
requests:
cpu: "100m"
memory: "512Mi"
limits:
cpu: "100m"
memory: "1Gi"
securityContext:
privileged: true
terminationMessagePolicy: FallbackToLogsOnError
volumeMounts:
- name: cni
mountPath: /host/etc/cni/net.d
# multus-daemon expects that cnibin path must be identical between pod and container host.
# e.g. if the cni bin is in '/opt/cni/bin' on the container host side, then it should be mount to '/opt/cni/bin' in multus-daemon,
# not to any other directory, like '/opt/bin' or '/usr/bin'.
- name: cnibin
mountPath: /opt/cni/bin
- name: host-run
mountPath: /host/run
- name: host-var-lib-cni-multus
mountPath: /var/lib/cni/multus
- name: host-var-lib-kubelet
mountPath: /var/lib/kubelet
mountPropagation: HostToContainer
- name: host-run-k8s-cni-cncf-io
mountPath: /run/k8s.cni.cncf.io
- name: host-run-netns
mountPath: /run/netns
mountPropagation: HostToContainer
- name: multus-daemon-config
mountPath: /etc/cni/net.d/multus.d
readOnly: true
- name: hostroot
mountPath: /hostroot
mountPropagation: HostToContainer
- mountPath: /etc/cni/multus/net.d
name: multus-conf-dir
env:
- name: MULTUS_NODE_NAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
initContainers:
- name: install-multus-binary
image: ghcr.io/k8snetworkplumbingwg/multus-cni:snapshot-thick
command:
- "sh"
- "-c"
- "cp /usr/src/multus-cni/bin/multus-shim /host/opt/cni/bin/multus-shim && cp /usr/src/multus-cni/bin/passthru /host/opt/cni/bin/passthru"
resources:
requests:
cpu: "10m"
memory: "15Mi"
securityContext:
privileged: true
terminationMessagePolicy: FallbackToLogsOnError
volumeMounts:
- name: cnibin
mountPath: /host/opt/cni/bin
mountPropagation: Bidirectional
terminationGracePeriodSeconds: 10
volumes:
- name: cni
hostPath:
path: /etc/cni/net.d
- name: cnibin
hostPath:
path: /opt/cni/bin
- name: hostroot
hostPath:
path: /
- name: multus-daemon-config
configMap:
name: multus-daemon-config
items:
- key: daemon-config.json
path: daemon-config.json
- name: host-run
hostPath:
path: /run
- name: host-var-lib-cni-multus
hostPath:
path: /var/lib/cni/multus
- name: host-var-lib-kubelet
hostPath:
path: /var/lib/kubelet
- name: host-run-k8s-cni-cncf-io
hostPath:
path: /run/k8s.cni.cncf.io
- name: host-run-netns
hostPath:
path: /run/netns/
- name: multus-conf-dir
hostPath:
path: /etc/cni/multus/net.d

View File

@@ -1,226 +0,0 @@
# Selenium Grid NetworkPolicy.
#
# Captured into bluejay-infra 2026-05-07 during the regroup audit. This
# NetworkPolicy was previously applied via `kubectl apply` directly to
# the cluster with no source-of-truth anywhere — a fresh cluster rebuild
# would have lost all of it (including the Selenium Grid → Traefik VIP
# allow rule for AAT runs against `*.iamworkin.lan` services).
#
# The Selenium Grid Deployment + Services themselves are still managed
# outside ArgoCD (deployed via raw kubectl from the original Selenium
# Grid bring-up). Migrating those into bluejay-infra is a separate lane —
# this commit only restores GitOps repeatability for the NetworkPolicy.
#
# Rules captured from the live cluster's `kubectl get netpol -n selenium
# selenium-netpol -o yaml` on 2026-05-07. Originally applied 2026-03-15
# (from `metadata.creationTimestamp` before the field was stripped).
#
# Allows:
# - Egress: CoreDNS, intra-namespace pod-to-pod (4442/4443/4444/5555),
# Traefik VIP for `*.iamworkin.lan` AAT runs, all FC namespaces on
# standard FC service ports (5100/5200/5300/5400/8080), pod CIDR
# (10.42.0.0/16) + service CIDR (10.43.0.0/16) for the same ports,
# LAN gateway range (10.0.56.0/24) for HTTPS, edge2 CUPS print
# (10.0.57.16:5200), public internet 80/443 (excluding RFC1918), and
# fc-signage:5190 for the signage AAT lane.
# - Ingress: Traefik (4444 + 8089 ACME-solver-style), intra-pod,
# telephony / gitea / fc-system / fc-signage / github-runner namespaces
# on 4444.
#
# 2026-05-25: added github-runner ingress on 4444 so CI jobs running in
# self-hosted runner pods (e.g. FlowerCore.Print.Web `help-screenshots`)
# can reach the grid. Without this allow, the session POST to
# `selenium-hub.selenium.svc.cluster.local:4444` was DNAT'd to the hub
# pod IP and then dropped at the Calico ingress hook — Selenium UI showed
# 0/4 sessions while the .NET HTTP client timed out at 60s. Same family
# as `feedback_netpol_dnat_backend_port`, wrong-source-namespace flavor.
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: selenium-netpol
namespace: selenium
labels:
app.kubernetes.io/part-of: selenium
app.kubernetes.io/component: isolation
spec:
egress:
- ports:
- port: 53
protocol: UDP
- port: 53
protocol: TCP
to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: kube-system
- ports:
- port: 4442
protocol: TCP
- port: 4443
protocol: TCP
- port: 4444
protocol: TCP
- port: 5555
protocol: TCP
to:
- podSelector: {}
- ports:
- port: 443
protocol: TCP
- port: 80
protocol: TCP
to:
- ipBlock:
cidr: 10.0.56.200/32
- ports:
- port: 443
protocol: TCP
- port: 80
protocol: TCP
- port: 5200
protocol: TCP
- port: 5300
protocol: TCP
- port: 5400
protocol: TCP
- port: 5100
protocol: TCP
- port: 8080
protocol: TCP
to:
- namespaceSelector: {}
- ports:
- port: 443
protocol: TCP
- port: 80
protocol: TCP
- port: 8443
protocol: TCP
- port: 8080
protocol: TCP
- port: 5200
protocol: TCP
- port: 5300
protocol: TCP
- port: 5400
protocol: TCP
- port: 5100
protocol: TCP
to:
- ipBlock:
cidr: 10.43.0.0/16
- ports:
- port: 443
protocol: TCP
- port: 80
protocol: TCP
- port: 8443
protocol: TCP
- port: 8080
protocol: TCP
- port: 5200
protocol: TCP
- port: 5300
protocol: TCP
- port: 5400
protocol: TCP
- port: 5100
protocol: TCP
to:
- ipBlock:
cidr: 10.42.0.0/16
- ports:
- port: 443
protocol: TCP
- port: 80
protocol: TCP
- port: 8443
protocol: TCP
to:
- ipBlock:
cidr: 10.0.56.0/24
- ports:
- port: 5200
protocol: TCP
to:
- ipBlock:
cidr: 10.0.57.16/32
- ports:
- port: 80
protocol: TCP
- port: 443
protocol: TCP
to:
- ipBlock:
cidr: 0.0.0.0/0
except:
- 172.16.0.0/12
- 192.168.0.0/16
- ports:
- port: 5190
protocol: TCP
to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: fc-signage
ingress:
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: traefik-system
ports:
- port: 4444
protocol: TCP
- port: 8089
protocol: TCP
- from:
- podSelector: {}
ports:
- port: 4442
protocol: TCP
- port: 4443
protocol: TCP
- port: 4444
protocol: TCP
- port: 5555
protocol: TCP
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: telephony
ports:
- port: 4444
protocol: TCP
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: gitea
ports:
- port: 4444
protocol: TCP
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: fc-system
ports:
- port: 4444
protocol: TCP
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: fc-signage
ports:
- port: 4444
protocol: TCP
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: github-runner
ports:
- port: 4444
protocol: TCP
podSelector: {}
policyTypes:
- Ingress
- Egress

View File

@@ -1,427 +0,0 @@
# Selenium Grid 4 — RKE2 deployment
#
# Hub + chrome + firefox + edge browser nodes serving fleet-wide AAT runs from
# the GitHub Actions self-hosted runners. ArgoCD owns this namespace from
# 2026-05-25 (`infra-selenium` Application; previously these resources were
# orphan kubectl-applied since 2026-03-15).
#
# Endpoints:
# - Internal cluster: http://selenium-hub.selenium.svc.cluster.local:4444
# - LAN LoadBalancer (MetalLB): http://10.0.56.208:4444
# - Traefik public: https://selenium.iamworkin.lan
#
# Browser maxSessions:
# - chrome 2 (bumped from 1 on 2026-05-25 morning-routine — AAT-heavy
# Print.Web help-screenshots was the global bottleneck;
# see commit history for ops/runner-replica-rightsize)
# - firefox 1
# - edge 1
#
# Screenshots + video recording write to NFS via the chrome video sidecar.
# See: CLAUDE.md "Selenium Grid & Visual AAT Testing" + bluejay-infra ADR notes.
---
apiVersion: v1
kind: Service
metadata:
labels:
app: selenium-hub
app.kubernetes.io/name: selenium-hub
app.kubernetes.io/part-of: selenium-grid
name: selenium-hub
namespace: selenium
spec:
ports:
- name: web
port: 4444
targetPort: 4444
- name: publish
port: 4442
targetPort: 4442
- name: subscribe
port: 4443
targetPort: 4443
selector:
app: selenium-hub
type: ClusterIP
---
apiVersion: v1
kind: Service
metadata:
annotations:
metallb.io/ip-allocated-from-pool: bluejay-pool
metallb.universe.tf/loadBalancerIPs: 10.0.56.208
labels:
app: selenium-hub
component: external-access
name: selenium-hub-external
namespace: selenium
spec:
clusterIP: 10.43.90.147
clusterIPs:
- 10.43.90.147
externalTrafficPolicy: Local
healthCheckNodePort: 32213
ports:
- name: web
nodePort: 32411
port: 4444
targetPort: 4444
- name: publish
nodePort: 32068
port: 4442
targetPort: 4442
- name: subscribe
nodePort: 31000
port: 4443
targetPort: 4443
selector:
app: selenium-hub
type: LoadBalancer
---
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app: selenium-hub
app.kubernetes.io/name: selenium-hub
app.kubernetes.io/part-of: selenium-grid
name: selenium-hub
namespace: selenium
spec:
replicas: 1
selector:
matchLabels:
app: selenium-hub
template:
metadata:
labels:
app: selenium-hub
app.kubernetes.io/name: selenium-hub
app.kubernetes.io/part-of: selenium-grid
spec:
containers:
- env:
- name: SE_NODE_SESSION_TIMEOUT
value: '300'
- name: SE_SESSION_REQUEST_TIMEOUT
value: '300'
- name: SE_SESSION_RETRY_INTERVAL
value: '5'
- name: JAVA_OPTS
value: -Xmx512m
image: selenium/hub:4.27.0
livenessProbe:
httpGet:
path: /wd/hub/status
port: 4444
initialDelaySeconds: 30
periodSeconds: 15
timeoutSeconds: 5
name: selenium-hub
ports:
- containerPort: 4444
name: web
- containerPort: 4442
name: publish
- containerPort: 4443
name: subscribe
readinessProbe:
httpGet:
path: /wd/hub/status
port: 4444
initialDelaySeconds: 10
periodSeconds: 5
timeoutSeconds: 5
# Hub baseline working set ~766Mi on 2026-05-25 (75% of prior 1Gi
# limit). Bump to 1.5Gi / 1Gi to keep ~50% headroom; matches the
# stampede-buffer pattern documented for multus
# (feedback_k8s_cni_multus_sizing). CPU left alone — observed 54m
# against a 500m limit, no contention.
resources:
limits:
cpu: 500m
memory: 1536Mi
requests:
cpu: 250m
memory: 1Gi
---
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app: selenium-node-chrome
app.kubernetes.io/name: selenium-node-chrome
app.kubernetes.io/part-of: selenium-grid
name: selenium-node-chrome
namespace: selenium
spec:
replicas: 1
selector:
matchLabels:
app: selenium-node-chrome
template:
metadata:
labels:
app: selenium-node-chrome
app.kubernetes.io/name: selenium-node-chrome
app.kubernetes.io/part-of: selenium-grid
spec:
containers:
- env:
- name: SE_EVENT_BUS_HOST
value: selenium-hub
- name: SE_EVENT_BUS_PUBLISH_PORT
value: '4442'
- name: SE_EVENT_BUS_SUBSCRIBE_PORT
value: '4443'
- name: SE_NODE_MAX_SESSIONS
value: '2'
- name: SE_NODE_OVERRIDE_MAX_SESSIONS
value: 'false'
- name: SE_VNC_NO_PASSWORD
value: '1'
- name: SE_SCREEN_WIDTH
value: '1920'
- name: SE_SCREEN_HEIGHT
value: '1080'
- name: SE_NODE_SESSION_TIMEOUT
value: '300'
image: selenium/node-chrome:4.27.0
livenessProbe:
httpGet:
path: /status
port: 5555
initialDelaySeconds: 30
periodSeconds: 15
name: selenium-chrome
ports:
- containerPort: 5555
name: node
readinessProbe:
httpGet:
path: /status
port: 5555
initialDelaySeconds: 15
periodSeconds: 5
# Chromium-based browser node. Bumped from 1Gi -> 2Gi (req 512Mi
# -> 1Gi) on 2026-05-25 — Edge had 51 OOMKills in 5d on the
# original 1Gi cap (~1 OOM every 2.4h), and Chrome at maxSessions=2
# was running 684Mi idle on the same cap. Matches the Firefox node's
# tested-stable 2Gi limit. CPU unchanged.
resources:
limits:
cpu: '1'
memory: 2Gi
requests:
cpu: 500m
memory: 1Gi
volumeMounts:
- mountPath: /dev/shm
name: dshm
- env:
- name: DISPLAY_CONTAINER_NAME
value: localhost
- name: SE_SCREEN_WIDTH
value: '1920'
- name: SE_SCREEN_HEIGHT
value: '1080'
- name: SE_VIDEO_FILE_NAME
value: auto
- name: SE_VIDEO_UPLOAD_ENABLED
value: 'false'
image: selenium/video:ffmpeg-7.1-20250101
name: video
resources:
limits:
cpu: 500m
memory: 768Mi
requests:
cpu: 250m
memory: 384Mi
volumeMounts:
- mountPath: /videos
name: selenium-videos
volumes:
- emptyDir:
medium: Memory
sizeLimit: 2Gi
name: dshm
- emptyDir:
sizeLimit: 5Gi
name: selenium-videos
---
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app: selenium-node-firefox
app.kubernetes.io/name: selenium-node-firefox
app.kubernetes.io/part-of: selenium-grid
name: selenium-node-firefox
namespace: selenium
spec:
replicas: 1
selector:
matchLabels:
app: selenium-node-firefox
template:
metadata:
labels:
app: selenium-node-firefox
app.kubernetes.io/name: selenium-node-firefox
app.kubernetes.io/part-of: selenium-grid
spec:
containers:
- env:
- name: SE_EVENT_BUS_HOST
value: selenium-hub
- name: SE_EVENT_BUS_PUBLISH_PORT
value: '4442'
- name: SE_EVENT_BUS_SUBSCRIBE_PORT
value: '4443'
- name: SE_NODE_MAX_SESSIONS
value: '1'
- name: SE_NODE_OVERRIDE_MAX_SESSIONS
value: 'true'
- name: SE_VNC_NO_PASSWORD
value: '1'
- name: SE_START_VNC
value: 'false'
- name: SE_SCREEN_WIDTH
value: '1920'
- name: SE_SCREEN_HEIGHT
value: '1080'
- name: SE_NODE_SESSION_TIMEOUT
value: '300'
image: selenium/node-firefox:4.27.0
livenessProbe:
failureThreshold: 5
httpGet:
path: /status
port: 5555
initialDelaySeconds: 30
periodSeconds: 15
timeoutSeconds: 5
name: selenium-firefox
ports:
- containerPort: 5555
name: node
readinessProbe:
failureThreshold: 5
httpGet:
path: /status
port: 5555
initialDelaySeconds: 15
periodSeconds: 5
timeoutSeconds: 5
resources:
limits:
cpu: '1'
memory: 2Gi
requests:
cpu: 500m
memory: 1Gi
volumeMounts:
- mountPath: /dev/shm
name: dshm
volumes:
- emptyDir:
medium: Memory
sizeLimit: 2Gi
name: dshm
---
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app: selenium-node-edge
app.kubernetes.io/name: selenium-node-edge
app.kubernetes.io/part-of: selenium-grid
name: selenium-node-edge
namespace: selenium
spec:
replicas: 1
selector:
matchLabels:
app: selenium-node-edge
template:
metadata:
labels:
app: selenium-node-edge
app.kubernetes.io/name: selenium-node-edge
app.kubernetes.io/part-of: selenium-grid
spec:
containers:
- env:
- name: SE_EVENT_BUS_HOST
value: selenium-hub
- name: SE_EVENT_BUS_PUBLISH_PORT
value: '4442'
- name: SE_EVENT_BUS_SUBSCRIBE_PORT
value: '4443'
- name: SE_NODE_MAX_SESSIONS
value: '1'
- name: SE_NODE_OVERRIDE_MAX_SESSIONS
value: 'true'
- name: SE_VNC_NO_PASSWORD
value: '1'
- name: SE_SCREEN_WIDTH
value: '1920'
- name: SE_SCREEN_HEIGHT
value: '1080'
- name: SE_NODE_SESSION_TIMEOUT
value: '300'
image: selenium/node-edge:4.27.0
livenessProbe:
httpGet:
path: /status
port: 5555
initialDelaySeconds: 30
periodSeconds: 15
name: selenium-edge
ports:
- containerPort: 5555
name: node
readinessProbe:
httpGet:
path: /status
port: 5555
initialDelaySeconds: 15
periodSeconds: 5
# Chromium-based browser node. Bumped from 1Gi -> 2Gi (req 512Mi
# -> 1Gi) on 2026-05-25 — Edge had 51 OOMKills in 5d on the
# original 1Gi cap (~1 OOM every 2.4h), and Chrome at maxSessions=2
# was running 684Mi idle on the same cap. Matches the Firefox node's
# tested-stable 2Gi limit. CPU unchanged.
resources:
limits:
cpu: '1'
memory: 2Gi
requests:
cpu: 500m
memory: 1Gi
volumeMounts:
- mountPath: /dev/shm
name: dshm
volumes:
- emptyDir:
medium: Memory
sizeLimit: 2Gi
name: dshm
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: selenium-hub
namespace: selenium
spec:
entryPoints:
- websecure
routes:
- kind: Rule
match: Host(`selenium.iamworkin.lan`)
services:
- name: selenium-hub
port: 4444
tls:
secretName: selenium-tls

View File

@@ -127,13 +127,10 @@ spec:
initContainers: initContainers:
- name: fix-data-perms - name: fix-data-perms
image: busybox:latest image: busybox:latest
# Must run as root to chown the hostPath /tmp/tts-audio that may be # Also chown /shared-tts (hostPath /tmp/tts-audio) so the non-root
# root-owned after node reboot. Pod-level runAsNonRoot:true would # app user (uid 1654) can write Piper .sln16 files that Asterisk
# otherwise inherit and chown would fail with EPERM (see Notes memory # reads at /var/lib/asterisk/sounds/tts. World-readable (755) is
# feedback_hostpath_initcontainer_chown_perms). # fine — Asterisk runs as a different uid in the other pod.
securityContext:
runAsUser: 0
runAsNonRoot: false
command: ["sh", "-c", "chown -R 1654:1654 /data && chown 1654:1654 /shared-tts && chmod 0755 /shared-tts"] command: ["sh", "-c", "chown -R 1654:1654 /data && chown 1654:1654 /shared-tts && chmod 0755 /shared-tts"]
volumeMounts: volumeMounts:
- name: telephony-data - name: telephony-data

View File

@@ -1,68 +0,0 @@
# FlowerCore.WorldBuilder
ArgoCD-managed manifest for FlowerCore.WorldBuilder.Web — comic / storyboard
authoring service that drives ComfyUI for panel image generation and
QuestPDF for letter / A4 export.
Source: `D:\git\FlowerCore\FlowerCore.WorldBuilder` (master)
## Deployment order
1. **DNS preflight**`worldbuilder.iamworkin.lan -> 10.0.56.200` MUST exist
in pfSense Unbound before this manifest is applied, or cert-manager
HTTP-01 silently exponential-backs-off ~2h.
Memory: `feedback_pfsense_dns_required_for_acme`.
2. **Image import to ALL RKE2 nodes** — pod can schedule to any of
`rke2-server` (10.0.56.11), `rke2-agent1` (10.0.56.12),
`rke2-agent2` (10.0.56.13). Build with:
```bash
bash deploy/build.sh # in FlowerCore.WorldBuilder repo
podman save localhost/fc-worldbuilder:v<TAG> -o /tmp/fc-worldbuilder-v<TAG>.tar
for h in 10.0.56.11 10.0.56.12 10.0.56.13; do
scp /tmp/fc-worldbuilder-v<TAG>.tar fcadmin@$h:/tmp/
ssh fcadmin@$h \
"sudo /var/lib/rancher/rke2/bin/ctr -a /run/k3s/containerd/containerd.sock \
-n k8s.io images import /tmp/fc-worldbuilder-v<TAG>.tar"
done
```
Memory: `feedback_rke2_image_import_per_node_scp`.
3. **Bump image tag** in `worldbuilder.yaml` and git push.
ArgoCD ApplicationSet picks up within ~3 minutes.
4. **First production render** — open
`https://worldbuilder.iamworkin.lan/studio/c32e0000-0000-4000-8000-000000000004`
and confirm the Cyberpunk Blue Jay demo prompt loads with five seeded fake
generated images. This Sprint 32 visitor-safe profile uses
`ClientMode=fake`; switch the image-generation env vars back to ComfyUI only
for an operator-owned GPU render lane.
## Health probes
- `startupProbe` + `readinessProbe`: `httpGet /healthz` (registered explicitly
in Program.cs — anonymous, no DB or OpenAPI dependency).
- `livenessProbe`: `tcpSocket` as a cheap fallback.
Memory: `feedback_k8s_probes_must_not_hit_openapi`,
`feedback_k8s_probes_behind_auth_middleware`.
## Storage
- Longhorn RWO PVC `worldbuilder-data` (5Gi) mounted at `/data`. SQLite DB
lives at `/data/worldbuilder.db`, generated images under `/data/gallery/`,
PDF/PNG exports under `/data/exports/`.
- DataProtection keys persist to the same SQLite via
`AddFlowerCoreDataProtection<WorldBuilderDbContext>` — explicit migration
`20260429133417_Initial` already creates `fc_dp_keys`.
Memory: `feedback_dataprotection_keys_persist_to_app_dbcontext`,
`feedback_intranet_dataprotection_table_must_have_explicit_migration`.
## Image generation backend
Sprint 32 pins the Kubernetes profile to
`FlowerCore:WorldBuilder:ImageGeneration:ClientMode=fake` with
`BaseUrl=http://127.0.0.1:1`. That keeps the public/internal visitor demo
deterministic, avoids GPU exposure, and still exercises the studio/gallery
surface with persisted generated-image metadata.
The previous ComfyUI backend target was `http://10.0.56.20:8188` on
BLUEJAY-WS (R9700 / gfx1201 / ROCm 7.2.1). Re-enable it only in an
operator-owned follow-up that also verifies workstation reachability and image
import freshness.

View File

@@ -1,256 +0,0 @@
# FlowerCore.WorldBuilder — comic / storyboard authoring service.
#
# Deployment + Service + PVC + Certificate + IngressRoute. ArgoCD-managed
# end-to-end. See apps/worldbuilder/README.md for the per-deploy runbook.
#
# Image build (BLUEJAY-WS):
# bash deploy/build.sh # in FlowerCore.WorldBuilder repo
# podman save localhost/fc-worldbuilder:v<TAG> -o /tmp/fc-worldbuilder-v<TAG>.tar
# for h in 10.0.56.11 10.0.56.12 10.0.56.13; do
# scp /tmp/fc-worldbuilder-v<TAG>.tar fcadmin@$h:/tmp/
# ssh fcadmin@$h "sudo /var/lib/rancher/rke2/bin/ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images import /tmp/fc-worldbuilder-v<TAG>.tar"
# done
---
apiVersion: v1
kind: Namespace
metadata:
name: fc-worldbuilder
labels:
app.kubernetes.io/name: fc-worldbuilder
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
---
# SQLite DB + generated image gallery + PDF/PNG exports.
# Longhorn RWO — single replica with `Recreate` rollout strategy keeps it safe.
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: worldbuilder-data
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-data
app.kubernetes.io/component: storage
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
resources:
requests:
storage: 5Gi
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: worldbuilder-web
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-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: 1
revisionHistoryLimit: 3
strategy:
# RWO PVC + single replica. Recreate avoids multi-attach overlap.
type: Recreate
selector:
matchLabels:
app.kubernetes.io/name: worldbuilder-web
template:
metadata:
labels:
app.kubernetes.io/name: worldbuilder-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/prometheus"
flowercore.io/audit-trace-id: "worldbuilder-runtime-demo"
spec:
securityContext:
fsGroup: 1654
fsGroupChangePolicy: OnRootMismatch
containers:
- name: web
# Bump tag for each rebuild. Initial deploy: v202605062048
image: localhost/fc-worldbuilder:v202605062048
imagePullPolicy: Never
ports:
- containerPort: 8080
name: http
env:
- name: ASPNETCORE_URLS
value: "http://+:8080"
- name: ASPNETCORE_ENVIRONMENT
value: "Production"
- name: DOTNET_RUNNING_IN_CONTAINER
value: "true"
- name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
value: "false"
# SQLite path overrides (default appsettings uses relative paths).
- name: ConnectionStrings__DefaultConnection
value: "Data Source=/data/worldbuilder.db"
- name: FlowerCore__Database__Provider
value: "Sqlite"
- name: FlowerCore__Database__ConnectionStrings__Sqlite
value: "Data Source=/data/worldbuilder.db"
# Generated image gallery + exports persist on /data.
- name: FlowerCore__WorldBuilder__ImageStore__RootPath
value: "/data/gallery"
- name: FlowerCore__WorldBuilder__Export__RootPath
value: "/data/exports"
# Visitor-safe Sprint 32 profile: fake backend keeps public demo
# rendering deterministic and avoids exposing BLUEJAY-WS GPU.
- name: FlowerCore__WorldBuilder__ImageGeneration__BaseUrl
value: "http://127.0.0.1:1"
- name: FlowerCore__WorldBuilder__ImageGeneration__ClientMode
value: "fake"
- name: FlowerCore__WorldBuilder__ImageGeneration__BackendId
value: "fake"
resources:
# Cluster CPU-request budget runs hot (99% on all 3 nodes at deploy
# time) while actual CPU usage is well below capacity. Idle Blazor
# Server + SignalR + a single ComfyUI poller uses ~5m, so 25m is
# generous. Re-evaluate if active rendering/export workers ever
# push past the limit.
requests:
cpu: 25m
memory: 256Mi
limits:
cpu: 1000m
memory: 768Mi
# /healthz is registered explicitly in Program.cs (anonymous, no DB
# or OpenAPI dependency). Liveness uses tcpSocket as a cheap fallback
# in case future middleware changes accidentally gate /healthz.
# Memory: feedback_k8s_probes_must_not_hit_openapi,
# feedback_k8s_probes_behind_auth_middleware.
startupProbe:
httpGet:
path: /healthz
port: 8080
initialDelaySeconds: 5
periodSeconds: 5
failureThreshold: 30
readinessProbe:
httpGet:
path: /healthz
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: data
mountPath: /data
- name: tmp
mountPath: /tmp
- name: logs
mountPath: /app/logs
volumes:
- name: data
persistentVolumeClaim:
claimName: worldbuilder-data
- name: tmp
emptyDir: {}
- name: logs
emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
name: worldbuilder-web
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-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.kubernetes.io/name: worldbuilder-web
ports:
- name: http
port: 80
targetPort: 8080
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: worldbuilder-web-tls
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-web-tls
app.kubernetes.io/component: ingress
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
secretName: worldbuilder-web-tls
issuerRef:
name: step-ca-acme
kind: ClusterIssuer
dnsNames:
- worldbuilder.iamworkin.lan
# step-ca ACME provisioner caps lifetime at 30d. Requesting 90d
# silently capped to 30d, making renewBefore 720h (30d) equal to the
# actual cert lifetime — triggered a perpetual renewal loop that
# generated 2365+ CertificateRequest objects in 18h. Match the working
# 720h/240h pattern used by every other FC service cert.
duration: 720h # 30d (step-ca cap)
renewBefore: 240h # 10d
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: worldbuilder-web
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-web
app.kubernetes.io/component: ingress
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(`worldbuilder.iamworkin.lan`)
kind: Rule
services:
- name: worldbuilder-web
port: 80
tls:
secretName: worldbuilder-web-tls

View File

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

View File

@@ -1,84 +0,0 @@
# openvoxserver Quadlet Durability
This runbook documents the noc1 `openvoxserver` durability fix for the Puppet control-repo deploy path. The service is a noc1 host artifact, not an ArgoCD application, so discovery always starts on noc1 rather than in `apps/*`.
## Current State
As of the Sprint 32 Cx-12 apply on 2026-05-17:
- `/etc/containers/systemd/openvoxserver.container` has a `GIT_SSH_COMMAND` environment entry that points at the persisted serverdata deploy key.
- `/etc/systemd/system/openvoxserver-safeconfig.service` is enabled and active, and reapplies `git config --global --add safe.directory *` inside the running container.
- `/opt/puppet/r10k-deploy.sh` self-heals before each fetch by setting `safe.directory`, the repo-local `core.sshCommand`, and the persisted `known_hosts` file when needed.
- `puppet-deploy.service` exits `0/SUCCESS` after the apply and the control repo reports `HEAD == origin/master`.
- `systemctl cat openvoxserver` does not currently resolve to a generated unit on noc1. The container is running through Podman with `restart=always`, so destructive recreate smoke must not run until the generated unit is present.
## Discovery
Run every command through noc1 as `fcadmin`; do not assume BLUEJAY-WS can reach container-local surfaces directly.
```bash
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "hostname && sudo -n true"
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo find /etc/containers/systemd /usr/share/containers/systemd /etc/systemd/system -name 'openvoxserver*' 2>/dev/null"
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo sed -n '1,220p' /etc/containers/systemd/openvoxserver.container"
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo systemctl cat puppet-deploy.service"
```
If a future noc1 profile manages these files, update the Puppet control repo and let `puppet-deploy.service` apply the change. On 2026-05-17, host `puppet` was not installed, so Cx-12 used a direct noc1 host edit.
## Durable Fix Shape
The Quadlet keeps the deploy key as a path reference only:
```ini
Environment=GIT_SSH_COMMAND=ssh -i /opt/puppetlabs/server/data/puppetserver/.puppet-deploy-key -o StrictHostKeyChecking=yes -o IdentitiesOnly=yes -o UserKnownHostsFile=/opt/puppetlabs/server/data/puppetserver/.known_hosts
```
The safeconfig service is intentionally independent of `openvoxserver.service` until the generated unit exists. It waits for the `openvoxserver` container name and then runs:
```bash
/usr/bin/podman exec openvoxserver git config --global --add safe.directory *
```
The deploy script self-heals inside the container before it fetches the control repo:
```bash
git config --global --add safe.directory "*" 2>/dev/null || true
DEPLOY_KEY="/opt/puppetlabs/server/data/puppetserver/.puppet-deploy-key"
KNOWN_HOSTS="/opt/puppetlabs/server/data/puppetserver/.known_hosts"
REPO="/etc/puppetlabs/code/environments/production"
export GIT_SSH_COMMAND="ssh -i $DEPLOY_KEY -o StrictHostKeyChecking=yes -o IdentitiesOnly=yes -o UserKnownHostsFile=$KNOWN_HOSTS"
git -C "$REPO" config core.sshCommand "$GIT_SSH_COMMAND" 2>/dev/null || true
```
## Validation
Non-destructive validation:
```bash
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo grep -n 'GIT_SSH_COMMAND' /etc/containers/systemd/openvoxserver.container"
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo systemctl status openvoxserver-safeconfig.service --no-pager -l"
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo systemctl start puppet-deploy.service && sudo systemctl status puppet-deploy.service --no-pager -l"
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo podman exec openvoxserver git -C /etc/puppetlabs/code/environments/production config --get core.sshCommand"
```
Destructive recreate smoke is opt-in only:
```bash
scp scripts/monitoring/openvox-recreate-smoke.sh fcadmin@10.0.56.10:/tmp/openvox-recreate-smoke.sh
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "chmod +x /tmp/openvox-recreate-smoke.sh && sudo OPENVOX_RECREATE_SMOKE=1 /tmp/openvox-recreate-smoke.sh"
```
Do not run the smoke during normal sprint work. It stops and removes the production container before starting it again through systemd, and it now refuses to continue unless `systemctl cat openvoxserver` succeeds.
## Credential Rotation Note
When rotating the Puppet deploy key, update the persisted serverdata copy on noc1:
```bash
sudo install -m 0600 -o root -g root <new-deploy-key> /opt/puppet/serverdata/.puppet-deploy-key
sudo podman exec openvoxserver sh -c "ssh-keyscan github.com > /opt/puppetlabs/server/data/puppetserver/.known_hosts"
sudo systemctl start openvoxserver-safeconfig.service
sudo systemctl start puppet-deploy.service
```
Never commit the deploy key or print it in logs.

View File

@@ -1,48 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
if [ "${OPENVOX_RECREATE_SMOKE:-}" != "1" ]; then
echo "SKIP: set OPENVOX_RECREATE_SMOKE=1 to run the destructive openvoxserver recreate smoke." >&2
exit 64
fi
SUDO="${SUDO:-sudo}"
REPO="/etc/puppetlabs/code/environments/production"
CORE_SSH_COMMAND_FRAGMENT=".puppet-deploy-key"
if ! $SUDO systemctl cat openvoxserver >/dev/null 2>&1; then
echo "SKIP: systemctl cat openvoxserver failed; refusing to remove a container without a verified systemd recreate path." >&2
exit 65
fi
before="$($SUDO podman exec openvoxserver git -C "$REPO" rev-parse --short HEAD)"
echo "Before recreate: $before"
$SUDO systemctl stop openvoxserver
$SUDO podman rm openvoxserver 2>/dev/null || true
$SUDO systemctl start openvoxserver
sleep 50
$SUDO systemctl start puppet-deploy.service
sleep 5
$SUDO systemctl status puppet-deploy.service --no-pager -l
after="$($SUDO podman exec openvoxserver git -C "$REPO" rev-parse --short origin/master)"
echo "After recreate origin/master: $after"
$SUDO test -d /opt/puppet/code/environments/production/site-modules/profile/manifests
core_ssh="$($SUDO podman exec openvoxserver git -C "$REPO" config --get core.sshCommand)"
case "$core_ssh" in
*"$CORE_SSH_COMMAND_FRAGMENT"*) ;;
*)
echo "FAIL: core.sshCommand does not reference the persisted deploy key." >&2
exit 1
;;
esac
$SUDO podman exec openvoxserver git -C "$REPO" status --short --branch
echo "PASS: openvoxserver recreate smoke completed without git safety or deploy-key failure."

View File

@@ -13,7 +13,6 @@ public sealed class FleetManifestLintTests
private static readonly HashSet<string> PublicReadOnlyHosts = new(StringComparer.Ordinal) private static readonly HashSet<string> PublicReadOnlyHosts = new(StringComparer.Ordinal)
{ {
"brochure.flowercore.io",
"dist.flowercore.io", "dist.flowercore.io",
"dns.iamworkin.lan", "dns.iamworkin.lan",
}; };
@@ -23,16 +22,10 @@ public sealed class FleetManifestLintTests
// (bootstrap-JWT) so its allowlist is GET||HEAD||POST||OPTIONS — but // (bootstrap-JWT) so its allowlist is GET||HEAD||POST||OPTIONS — but
// PUT/PATCH/DELETE must still 404 at the route. Anything wider than this // PUT/PATCH/DELETE must still 404 at the route. Anything wider than this
// set should fail this lint. // set should fail this lint.
//
// PUB-1 (2026-05-06): update.flowercore.io / updates.flowercore.io were
// added for the Cloudflare-proxied public Update Center edge. They use the
// same bounded read-write allowlist as the LAN pair.
private static readonly HashSet<string> PublicReadWriteAllowlistHosts = new(StringComparer.Ordinal) private static readonly HashSet<string> PublicReadWriteAllowlistHosts = new(StringComparer.Ordinal)
{ {
"updatecenter.iamworkin.lan", "updatecenter.iamworkin.lan",
"updates.iamworkin.lan", "updates.iamworkin.lan",
"update.flowercore.io",
"updates.flowercore.io",
}; };
private static readonly HashSet<string> ApiKeyProtectedDeployments = new(StringComparer.Ordinal) private static readonly HashSet<string> ApiKeyProtectedDeployments = new(StringComparer.Ordinal)
@@ -55,45 +48,6 @@ public sealed class FleetManifestLintTests
"ttsreader-piper", "ttsreader-piper",
}; };
private static readonly IReadOnlyDictionary<string, string> LinuxRunnerRepos = new Dictionary<string, string>(StringComparer.Ordinal)
{
["github-runner"] = "https://github.com/astoltz/FlowerCore.Common",
["github-runner-sharedpos"] = "https://github.com/astoltz/FlowerCore.Shared.Pos",
["github-runner-puppet"] = "https://github.com/astoltz/FlowerCore.Puppet",
["github-runner-signage"] = "https://github.com/astoltz/FlowerCore.Signage",
["github-runner-dms"] = "https://github.com/astoltz/FlowerCore.DMS",
["github-runner-telephony"] = "https://github.com/astoltz/FlowerCore.Telephony",
["github-runner-print-web"] = "https://github.com/astoltz/FlowerCore.Print.Web",
["github-runner-chat"] = "https://github.com/astoltz/FlowerCore.Chat",
["github-runner-mysql"] = "https://github.com/astoltz/FlowerCore.MySQL",
["github-runner-kiosk-linux"] = "https://github.com/astoltz/FlowerCore.Kiosk.Linux",
["github-runner-updater"] = "https://github.com/astoltz/FlowerCore.Updater",
};
private static readonly HashSet<string> ScaledLinuxRunnerDeployments = new(StringComparer.Ordinal)
{
"github-runner-sharedpos",
"github-runner-puppet",
"github-runner-signage",
"github-runner-dms",
"github-runner-telephony",
"github-runner-print-web",
"github-runner-chat",
"github-runner-mysql",
"github-runner-kiosk-linux",
"github-runner-updater",
};
private static readonly IReadOnlyDictionary<string, string> WritableRunnerEnv = new Dictionary<string, string>(StringComparer.Ordinal)
{
["HOME"] = "/home/runner",
["DOTNET_INSTALL_DIR"] = "/home/runner/.dotnet",
["DOTNET_CLI_HOME"] = "/home/runner",
["NUGET_PACKAGES"] = "/home/runner/.nuget/packages",
["XDG_CACHE_HOME"] = "/home/runner/.cache",
["RUNNER_TOOL_CACHE"] = "/home/runner/_tool",
};
[Fact] [Fact]
public void IngressRoutes_MustKeepServiceReferencesInTheSameNamespace() public void IngressRoutes_MustKeepServiceReferencesInTheSameNamespace()
{ {
@@ -227,203 +181,6 @@ public sealed class FleetManifestLintTests
violations.Should().BeEmpty(); violations.Should().BeEmpty();
} }
[Fact]
public void GitHubRunnerFleet_MustRegisterRequiredReposAsRepoScopedDeployments()
{
var deployments = GitHubRunnerDeployments();
foreach (var expectedRunner in LinuxRunnerRepos)
{
deployments.Should().ContainKey(expectedRunner.Key);
var container = deployments[expectedRunner.Key].MainContainerMappings().Should().ContainSingle().Subject;
EnvValue(container, "REPO_URL").Should().Be(expectedRunner.Value);
EnvValue(container, "EPHEMERAL").Should().Be("true");
EnvValue(container, "LABELS").Should().Be("self-hosted,linux,fc-build-linux");
EnvValue(container, "RUN_AS_ROOT").Should().Be("false");
EnvValue(container, "ACCESS_TOKEN").Should().BeNull("ACCESS_TOKEN must come from github-runner-token Secret, not a literal");
EnvSecretName(container, "ACCESS_TOKEN").Should().Be("github-runner-token");
EnvSecretKey(container, "ACCESS_TOKEN").Should().Be("credential");
}
}
[Fact]
public void GitHubRunnerFleet_MustSetWritableNonRootDotnetAndCachePaths()
{
foreach (var deployment in GitHubRunnerDeployments().Values)
{
var container = deployment.MainContainerMappings().Should().ContainSingle().Subject;
foreach (var expectedEnv in WritableRunnerEnv)
{
EnvValue(container, expectedEnv.Key).Should().Be(expectedEnv.Value, $"{deployment.Name} must keep .NET paths writable for uid 1001");
}
var mounts = ManifestNodeExtensions.MappingSequence(container, "volumeMounts")
.ToDictionary(
mount => ManifestNodeExtensions.Scalar(mount, "name") ?? string.Empty,
mount => ManifestNodeExtensions.Scalar(mount, "mountPath") ?? string.Empty,
StringComparer.Ordinal);
mounts.Should().Contain("runner-home", "/home/runner");
mounts.Should().Contain("nuget-cache", "/home/runner/.nuget/packages");
mounts.Should().Contain("tmp", "/tmp");
}
}
[Fact]
public void GitHubRunnerFleet_MustAvoidRwoMultiAttachForScaledDeployments()
{
var deployments = GitHubRunnerDeployments();
foreach (var deploymentName in ScaledLinuxRunnerDeployments)
{
var deployment = deployments[deploymentName];
// Scaled runners must have >= 2 replicas (avoid single-pod bottleneck).
// Individual deployments may be tuned upward per CI activity — see
// "runners: right-size replica counts per 14d CI activity (#24)".
ReplicaCount(deployment).Should().BeGreaterOrEqualTo(2, $"{deploymentName} is in the scaled set and must run with at least 2 replicas");
var volumes = deployment.MappingSequence("spec", "template", "spec", "volumes");
var claimNames = volumes
.Select(volume => ManifestNodeExtensions.Scalar(volume, "persistentVolumeClaim", "claimName"))
.Where(value => !string.IsNullOrWhiteSpace(value))
.ToList();
claimNames.Should().BeEmpty($"{deploymentName} is scaled and must not share a RWO PVC");
volumes.Should().Contain(volume =>
string.Equals(ManifestNodeExtensions.Scalar(volume, "name"), "nuget-cache", StringComparison.Ordinal)
&& ManifestNodeExtensions.Mapping(volume, "emptyDir") != null);
}
var common = deployments["github-runner"];
ReplicaCount(common).Should().Be(1);
common.MappingSequence("spec", "template", "spec", "volumes")
.Select(volume => ManifestNodeExtensions.Scalar(volume, "persistentVolumeClaim", "claimName"))
.Where(value => !string.IsNullOrWhiteSpace(value))
.Should()
.ContainSingle()
.Which
.Should()
.Be("github-runner-nuget-cache");
}
[Fact]
public void Runners_MustNotPinToOperatorWorkstationHosts()
{
// CRITICAL SAFETY (operator directive 2026-05-26): BLUEJAY-WS is the
// operator's primary workstation — host of the 1Password Connect
// bearer token, fcadmin SSH keys to noc1, signing CA private keys,
// and source for every FC repo. A self-hosted GitHub Actions runner
// there would execute arbitrary PR code with that local access.
// Build-side analog of the Sprint 9 NEW safe-account exclusion gate
// (Puppet GPO/AppLocker/WDAC/audit-forwarder modules refuse to apply
// on BLUEJAY-WS). This lint asserts no GitHub-runner Deployment in
// apps/github-runner/ pins to a forbidden operator-workstation host
// via nodeName, nodeSelector, nodeAffinity, or tolerations.
// Existing legacy `bluejay-ws-sandbox-1` GitHub-registered runner is
// out of scope here (it's a runtime registration, not a K8s
// Deployment) — see CLAUDE.md "Common Mistakes" entry and
// feedback_bluejay_ws_never_public_runner.md.
var forbiddenHostPatterns = new[]
{
"bluejay-ws",
"BLUEJAY-WS",
"bluejay-ws.iamworkin.lan",
"iamworkin-ws",
};
bool ContainsForbidden(string? value) =>
!string.IsNullOrWhiteSpace(value)
&& forbiddenHostPatterns.Any(pattern => value!.Contains(pattern, StringComparison.OrdinalIgnoreCase));
var violations = GitHubRunnerDeployments().Values.SelectMany(deployment =>
{
var local = new List<string>();
var podSpec = ManifestNodeExtensions.Mapping(deployment.Root, "spec", "template", "spec");
if (podSpec is null)
{
return local;
}
// nodeName: pins the pod to a specific node by name.
var nodeName = ManifestNodeExtensions.Scalar(podSpec, "nodeName");
if (ContainsForbidden(nodeName))
{
local.Add($"{deployment.Name} sets nodeName='{nodeName}' which targets a forbidden operator-workstation host.");
}
// nodeSelector: dict of label → value pinning the pod to nodes
// carrying matching labels. Examples that would trip this:
// kubernetes.io/hostname: bluejay-ws
// flowercore.io/host: bluejay-ws.iamworkin.lan
var nodeSelector = ManifestNodeExtensions.Mapping(podSpec, "nodeSelector");
if (nodeSelector is not null)
{
foreach (var entry in nodeSelector.Children)
{
var key = entry.Key is YamlScalarNode keyScalar ? keyScalar.Value : null;
var value = entry.Value is YamlScalarNode valueScalar ? valueScalar.Value : null;
if (ContainsForbidden(value))
{
local.Add($"{deployment.Name} has nodeSelector entry '{key}: {value}' which targets a forbidden operator-workstation host.");
}
}
}
// nodeAffinity: matchExpressions over node labels.
foreach (var term in ManifestNodeExtensions.MappingSequence(podSpec, "affinity", "nodeAffinity", "requiredDuringSchedulingIgnoredDuringExecution", "nodeSelectorTerms"))
{
foreach (var expr in ManifestNodeExtensions.MappingSequence(term, "matchExpressions"))
{
var key = ManifestNodeExtensions.Scalar(expr, "key");
foreach (var valueNode in ManifestNodeExtensions.ScalarSequence(expr, "values"))
{
if (ContainsForbidden(valueNode))
{
local.Add($"{deployment.Name} has nodeAffinity matchExpression '{key}' value '{valueNode}' which targets a forbidden operator-workstation host.");
}
}
}
}
// tolerations: scheduling onto a tainted operator-workstation
// node would let the runner run there. Forbid any toleration
// value that names the workstation.
foreach (var toleration in ManifestNodeExtensions.MappingSequence(podSpec, "tolerations"))
{
var key = ManifestNodeExtensions.Scalar(toleration, "key");
var value = ManifestNodeExtensions.Scalar(toleration, "value");
if (ContainsForbidden(key))
{
local.Add($"{deployment.Name} has toleration key '{key}' which targets a forbidden operator-workstation host.");
}
if (ContainsForbidden(value))
{
local.Add($"{deployment.Name} has toleration value '{value}' which targets a forbidden operator-workstation host.");
}
}
return local;
}).ToList();
violations.Should().BeEmpty("BLUEJAY-WS / iamworkin-ws must never host a fleet GitHub Actions runner; see CLAUDE.md 'Registering BLUEJAY-WS as a fleet GitHub Actions runner' and feedback_bluejay_ws_never_public_runner.md");
}
[Fact]
public void Monitoring_MustAlertWhenLinuxRunnerDeploymentIsUnavailable()
{
var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
monitoring.Should().Contain("MacMiniRunnerOffline");
monitoring.Should().Contain("LinuxRunnerOffline");
monitoring.Should().Contain("kube_deployment_status_replicas_ready");
monitoring.Should().Contain("github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))");
monitoring.Should().Contain("folder: CI Alerts");
monitoring.Should().Contain("uid: linux-runner-offline");
monitoring.Should().Contain("alert_channel: irc");
}
[Fact] [Fact]
public void StatefulSets_WithVolumeClaimTemplates_MustDeclareFilesystemDefaults() public void StatefulSets_WithVolumeClaimTemplates_MustDeclareFilesystemDefaults()
{ {
@@ -528,184 +285,6 @@ 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,
@@ -729,51 +308,6 @@ 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 IReadOnlyDictionary<string, ManifestDocument> GitHubRunnerDeployments()
{
return Inventory.Documents
.Where(document => document.Kind == "Deployment")
.Where(document => document.Namespace == "github-runner")
.ToDictionary(document => document.Name, StringComparer.Ordinal);
}
private static int ReplicaCount(ManifestDocument document)
{
return int.TryParse(document.Scalar("spec", "replicas"), out var replicas) ? replicas : 1;
}
private static string? EnvValue(YamlMappingNode container, string name)
{
return EnvMapping(container, name) is { } env ? ManifestNodeExtensions.Scalar(env, "value") : null;
}
private static string? EnvSecretName(YamlMappingNode container, string name)
{
return EnvMapping(container, name) is { } env
? ManifestNodeExtensions.Scalar(env, "valueFrom", "secretKeyRef", "name")
: null;
}
private static string? EnvSecretKey(YamlMappingNode container, string name)
{
return EnvMapping(container, name) is { } env
? ManifestNodeExtensions.Scalar(env, "valueFrom", "secretKeyRef", "key")
: null;
}
private static YamlMappingNode? EnvMapping(YamlMappingNode container, string name)
{
return ManifestNodeExtensions.MappingSequence(container, "env")
.SingleOrDefault(env => string.Equals(ManifestNodeExtensions.Scalar(env, "name"), name, StringComparison.Ordinal));
}
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
@@ -997,22 +531,6 @@ internal sealed record ManifestDocument(
.ToList(); .ToList();
} }
// MainContainerMappings excludes initContainers. Use this when asserting
// properties of the primary container (env, image, volumeMounts) where an
// initContainer would be a false-positive match — e.g. the GitHub runner
// image's `setup-runner-home` initContainer should not count toward the
// single-container assertions on the runner deployments.
public IReadOnlyList<YamlMappingNode> MainContainerMappings()
{
var podSpec = PodSpec();
if (podSpec is null)
{
return Array.Empty<YamlMappingNode>();
}
return ManifestNodeExtensions.MappingSequence(podSpec, "containers").ToList();
}
public IReadOnlyList<ContainerSpec> ContainerSpecs() public IReadOnlyList<ContainerSpec> ContainerSpecs()
{ {
return ContainerMappings() return ContainerMappings()

View File

@@ -1,99 +0,0 @@
using FluentAssertions;
using Xunit;
namespace BluejayInfraLint.Tests;
[Trait("Category", "Unit")]
public sealed class OpenVoxServerDurabilityTests
{
private static readonly string Root = FindRepoRoot();
private static readonly string RunbookPath = Path.Combine(Root, "docs", "runbooks", "openvoxserver-quadlet-durability.md");
private static readonly string SmokePath = Path.Combine(Root, "scripts", "monitoring", "openvox-recreate-smoke.sh");
[Fact]
public void Runbook_DocumentsHostArtifactAndNonArgoPath()
{
var runbook = File.ReadAllText(RunbookPath);
runbook.Should().Contain("noc1 host artifact");
runbook.Should().Contain("not an ArgoCD application");
runbook.Should().Contain("systemctl cat openvoxserver");
runbook.Should().Contain("/etc/containers/systemd/openvoxserver.container");
}
[Fact]
public void Runbook_DocumentsCx12LiveApplyState()
{
var runbook = File.ReadAllText(RunbookPath);
runbook.Should().Contain("Sprint 32 Cx-12");
runbook.Should().Contain("openvoxserver-safeconfig.service");
runbook.Should().Contain("/opt/puppet/r10k-deploy.sh");
runbook.Should().Contain("HEAD == origin/master");
}
[Fact]
public void SmokeScript_IsExplicitlyOptIn()
{
var smoke = File.ReadAllText(SmokePath);
smoke.Should().Contain("OPENVOX_RECREATE_SMOKE");
smoke.Should().Contain("exit 64");
smoke.IndexOf("OPENVOX_RECREATE_SMOKE", StringComparison.Ordinal)
.Should().BeLessThan(smoke.IndexOf("systemctl stop openvoxserver", StringComparison.Ordinal));
}
[Fact]
public void SmokeScript_RequiresGeneratedSystemdUnitBeforeRemovingContainer()
{
var smoke = File.ReadAllText(SmokePath);
smoke.Should().Contain("systemctl cat openvoxserver");
smoke.Should().Contain("refusing to remove a container without a verified systemd recreate path");
smoke.IndexOf("systemctl cat openvoxserver", StringComparison.Ordinal)
.Should().BeLessThan(smoke.IndexOf("podman rm openvoxserver", StringComparison.Ordinal));
}
[Fact]
public void Artifacts_DoNotStoreSecretsOrPaidRunnerLabels()
{
var forbidden = new[]
{
"BEGIN OPENSSH PRIVATE KEY",
"BEGIN RSA PRIVATE KEY",
"ubuntu-latest",
"windows-latest",
"macos-latest",
};
var violations = new[] { RunbookPath, SmokePath }
.SelectMany(path =>
{
var text = File.ReadAllText(path);
return forbidden
.Where(token => text.Contains(token, StringComparison.OrdinalIgnoreCase))
.Select(token => $"{Path.GetRelativePath(Root, path)} contains forbidden token {token}");
})
.ToList();
violations.Should().BeEmpty();
}
private static string FindRepoRoot()
{
var current = new DirectoryInfo(AppContext.BaseDirectory);
while (current is not null)
{
if (Directory.Exists(Path.Combine(current.FullName, "apps"))
&& Directory.Exists(Path.Combine(current.FullName, "scripts"))
&& File.Exists(Path.Combine(current.FullName, "README.md")))
{
return current.FullName;
}
current = current.Parent;
}
throw new DirectoryNotFoundException("Could not find bluejay-infra root.");
}
}

View File

@@ -1,269 +0,0 @@
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.");
}
}

View File

@@ -1,6 +1,6 @@
package bluejayinfra.public_method_allowlist package bluejayinfra.public_method_allowlist
public_hosts := {"brochure.flowercore.io", "dist.flowercore.io", "dns.iamworkin.lan"} public_hosts := {"dist.flowercore.io", "dns.iamworkin.lan"}
deny[msg] { deny[msg] {
input.kind == "IngressRoute" input.kind == "IngressRoute"

View File

@@ -6,12 +6,7 @@ package bluejayinfra.public_readwrite_allowlist
# PUT/PATCH/DELETE must still 404 at the route. Any host in this set MUST # PUT/PATCH/DELETE must still 404 at the route. Any host in this set MUST
# include all four required methods AND MUST NOT include any forbidden # include all four required methods AND MUST NOT include any forbidden
# method. # method.
public_readwrite_hosts := { public_readwrite_hosts := {"updatecenter.iamworkin.lan", "updates.iamworkin.lan"}
"updatecenter.iamworkin.lan",
"updates.iamworkin.lan",
"update.flowercore.io",
"updates.flowercore.io",
}
required_methods := {"GET", "HEAD", "POST", "OPTIONS"} required_methods := {"GET", "HEAD", "POST", "OPTIONS"}