Compare commits

..

1 Commits

Author SHA1 Message Date
Andrew Stoltz
9a4a8264d9 github-runner: add DM and WorldBuilder runners 2026-05-18 17:44:29 -05:00
44 changed files with 583 additions and 3914 deletions

4
.gitattributes vendored
View File

@@ -1,4 +0,0 @@
/.gitattributes text eol=lf
*.yaml text eol=lf
*.yml text eol=lf
*.sh text eol=lf

View File

@@ -116,16 +116,6 @@ dotnet test tests/bluejay-infra-lint/BluejayInfraLint.Tests.csproj -c Release
That test project sweeps `bluejay-infra/apps/**` plus the canonical sibling `FlowerCore.*\\k8s` manifests that share the same workspace. Matching `conftest.dev` policy files live under `tests/bluejay-infra-lint/conftest.dev/` for environments that also have `conftest` or `opa`.
## Non-K8s Pi Artifacts
Some `apps/*` directories are deployment artifact bundles consumed by Puppet
instead of Kubernetes workloads. `apps/fc-signage-pi-player/` carries the
Chromium signage Pi player, `apps/fc-divoom-dm-pi-device/` carries the additive
edge2 Divoom-as-DeviceManagement-device profile/Hiera contract, and
`apps/fc-divoom-tv-pi/` carries the Divoom TV Pi HDMI systemd/Puppet shape.
These bundles intentionally avoid Deployment, IngressRoute, Certificate, and
OnePasswordItem resources.
## References
- OpenVox noc1 durability runbook: `docs/runbooks/openvoxserver-quadlet-durability.md`

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

27
apps/brochure/README.md Normal file
View File

@@ -0,0 +1,27 @@
# FlowerCore Brochure
`apps/brochure` hosts the public brochure split from `FlowerCore.Intranet.Web`.
ArgoCD's `apps/*` ApplicationSet will create `infra-brochure` after this
directory lands on `main`.
## Runtime
- Host: `https://brochure.flowercore.io`
- Namespace: `brochure`
- Deployment: `brochure-web`
- Image: `localhost/fc-brochure-web:v20260524-sprint32`
- Port: `8080`
- Public route method allowlist: `GET` and `HEAD`
## Operator Actions
1. Publish and import `localhost/fc-brochure-web:v20260524-sprint32` to every
RKE2 node before sync, using the same podman save + `ctr images import`
flow as the Intranet deployment.
2. Create the Cloudflare DNS record for `brochure.flowercore.io` pointing at
the FlowerCore public edge.
3. Verify `infra-brochure` appears in ArgoCD, the certificate becomes Ready,
and `GET https://brochure.flowercore.io/` returns `200`.
The route intentionally does not expose `/ops/*` or `/admin/*`; the Brochure
web app returns `404` for those paths and Traefik only forwards read methods.

131
apps/brochure/brochure.yaml Normal file
View File

@@ -0,0 +1,131 @@
# FlowerCore Brochure public host
#
# Thin Blazor host for public What's New, walkthrough, and gallery content
# carved out of FlowerCore.Intranet.Web. The ApplicationSet creates
# infra-brochure from this directory after merge.
---
apiVersion: v1
kind: Namespace
metadata:
name: brochure
labels:
app.kubernetes.io/part-of: flowercore
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: brochure-web
namespace: brochure
labels:
app: brochure-web
app.kubernetes.io/name: brochure-web
app.kubernetes.io/part-of: flowercore
spec:
replicas: 1
revisionHistoryLimit: 3
selector:
matchLabels:
app: brochure-web
template:
metadata:
labels:
app: brochure-web
app.kubernetes.io/name: brochure-web
app.kubernetes.io/part-of: flowercore
spec:
containers:
- name: brochure-web
image: localhost/fc-brochure-web:v20260524-sprint32
imagePullPolicy: Never
ports:
- containerPort: 8080
name: http
env:
- name: ASPNETCORE_ENVIRONMENT
value: Production
- name: ASPNETCORE_URLS
value: "http://+:8080"
resources:
requests:
cpu: "25m"
memory: "128Mi"
limits:
cpu: "500m"
memory: "512Mi"
readinessProbe:
httpGet:
path: /health
port: http
initialDelaySeconds: 10
periodSeconds: 10
livenessProbe:
httpGet:
path: /health
port: http
initialDelaySeconds: 30
periodSeconds: 30
securityContext:
runAsNonRoot: true
runAsUser: 1654
runAsGroup: 1654
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop:
- ALL
volumeMounts:
- name: tmp
mountPath: /tmp
volumes:
- name: tmp
emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
name: brochure-web
namespace: brochure
labels:
app: brochure-web
app.kubernetes.io/name: brochure-web
app.kubernetes.io/part-of: flowercore
spec:
type: ClusterIP
selector:
app: brochure-web
ports:
- name: http
port: 8080
targetPort: http
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: brochure-web-tls
namespace: brochure
spec:
secretName: brochure-web-tls
issuerRef:
name: step-ca-acme
kind: ClusterIssuer
dnsNames:
- brochure.flowercore.io
duration: 720h
renewBefore: 240h
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: brochure-web-public
namespace: brochure
spec:
entryPoints:
- websecure
routes:
- match: Host(`brochure.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
kind: Rule
services:
- name: brochure-web
port: 8080
tls:
secretName: brochure-web-tls

View File

@@ -1,169 +0,0 @@
# FlowerCore.AiStation.Web GitOps adoption manifest.
#
# Authored from the already-live fc-aistation resources on 2026-06-04.
# Keep the live image tag, Service ClusterIP, and PVC volumeName unchanged so
# ArgoCD adopts in place instead of replacing the workload or data volume.
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: aistation-web-data
namespace: fc-aistation
labels:
app.kubernetes.io/name: aistation-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-aistation
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 1Gi
storageClassName: longhorn
volumeMode: Filesystem
volumeName: pvc-27448d6f-6e66-42a7-a293-73dd8bbd6b3e
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: aistation-web
namespace: fc-aistation
labels:
app.kubernetes.io/name: aistation-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-aistation
spec:
progressDeadlineSeconds: 600
replicas: 1
revisionHistoryLimit: 3
selector:
matchLabels:
app.kubernetes.io/name: aistation-web
strategy:
type: Recreate
template:
metadata:
annotations:
prometheus.io/path: /metrics/prometheus
prometheus.io/port: "5000"
prometheus.io/scrape: "true"
labels:
app.kubernetes.io/name: aistation-web
app.kubernetes.io/part-of: flowercore
spec:
containers:
- envFrom:
- configMapRef:
name: aistation-web-config
image: localhost/fc-aistation-web:v20260602-aistation-owned-deploy-fix2
imagePullPolicy: Never
livenessProbe:
failureThreshold: 3
httpGet:
path: /healthz
port: 5000
scheme: HTTP
initialDelaySeconds: 30
periodSeconds: 30
successThreshold: 1
timeoutSeconds: 5
name: aistation-web
ports:
- containerPort: 5000
name: http
protocol: TCP
readinessProbe:
failureThreshold: 6
httpGet:
path: /healthz
port: 5000
scheme: HTTP
initialDelaySeconds: 10
periodSeconds: 10
successThreshold: 1
timeoutSeconds: 5
resources: {}
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /data
name: data
dnsPolicy: ClusterFirst
restartPolicy: Always
schedulerName: default-scheduler
securityContext: {}
terminationGracePeriodSeconds: 30
volumes:
- name: data
persistentVolumeClaim:
claimName: aistation-web-data
---
apiVersion: v1
kind: Service
metadata:
name: aistation-web
namespace: fc-aistation
labels:
app.kubernetes.io/name: aistation-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-aistation
spec:
clusterIP: 10.43.211.127
clusterIPs:
- 10.43.211.127
internalTrafficPolicy: Cluster
ipFamilies:
- IPv4
ipFamilyPolicy: SingleStack
ports:
- name: http
port: 80
protocol: TCP
targetPort: 5000
selector:
app.kubernetes.io/name: aistation-web
sessionAffinity: None
type: ClusterIP
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: aistation-web-tls
namespace: fc-aistation
labels:
app.kubernetes.io/name: aistation-web-tls
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-aistation
spec:
dnsNames:
- aistation.iamworkin.lan
issuerRef:
kind: ClusterIssuer
name: step-ca-acme
secretName: aistation-web-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: aistation-web
namespace: fc-aistation
labels:
app.kubernetes.io/name: aistation-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-aistation
spec:
entryPoints:
- websecure
routes:
- kind: Rule
match: Host(`aistation.iamworkin.lan`)
services:
- name: aistation-web
port: 80
tls:
secretName: aistation-web-tls

View File

@@ -1,206 +1,5 @@
# FlowerCore Chat
#
# ArgoCD-managed workload plus TLS/Ingress. The chat-web-secret remains an
# out-of-band Secret until the values are moved into a 1Password-backed item;
# the Deployment references it as optional so GitOps can own the workload
# without storing secret material in this repo.
---
apiVersion: v1
kind: Namespace
metadata:
name: fc-chat
labels:
app.kubernetes.io/part-of: flowercore
---
apiVersion: v1
kind: ConfigMap
metadata:
name: chat-web-config
namespace: fc-chat
labels:
app.kubernetes.io/name: chat-web
app.kubernetes.io/part-of: flowercore
data:
ASPNETCORE_ENVIRONMENT: Production
ASPNETCORE_URLS: "http://+:8080"
ASPNETCORE_FORWARDEDHEADERS_ENABLED: "true"
FlowerCore__Auth__Enabled: "false"
FlowerCore__Auth__Oidc__Enabled: "true"
FlowerCore__Auth__Oidc__Authority: "https://id.iamworkin.lan/application/o/chat/"
FlowerCore__Auth__Oidc__Audience: "chat"
FlowerCore__Auth__Oidc__ClientId: "chat"
FlowerCore__Database__ConnectionStrings__Sqlite: "Data Source=/data/chat.db"
# Ollama target. Switched 2026-04-25 from edge1 Pi5 (10.0.57.17) to BLUEJAY-WS
# workstation (10.0.56.20, RX 9070 XT 16GB, OLLAMA_HOST=0.0.0.0:11434, Vulkan
# backend per feedback_rdna4_vulkan_broken). The Pi5 was timing out every team-
# round speaker at the 300s per-turn cap (live-proven 2026-04-25 03:53 UTC,
# see feedback_chat_team_round_edge1_too_slow). Workstation has gemma3:4b for
# the Cheap tier, plus gemma3:27b/phi4:14b/qwen3:14b for Default/Balanced/Deep.
# Piper TTS stays on edge1 below (different service, Pi handles TTS fine).
FlowerCore__AI__OllamaBaseUrl: "http://10.0.56.20:11434"
FlowerCore__AI__DefaultModelName: "phi4:14b"
ChatOptions__BehaviorRuleEngine__OllamaBaseUrl: "http://10.0.56.20:11434"
ChatOptions__BehaviorRuleEngine__FallbackOllamaBaseUrl: "http://10.0.57.17:11434"
ChatOptions__BehaviorRuleEngine__ModelName: "gemma3:12b"
FlowerCore__AI__Memory__UseSharedIndexingAdapter: "true"
FlowerCore__AI__Memory__UseOllamaEmbeddings: "true"
FlowerCore__AI__Memory__EmbeddingModel: "nomic-embed-text"
FlowerCore__AI__Memory__EnableSharedIndexingBackfill: "true"
FlowerCore__AI__Memory__SharedIndexingDatabasePath: "/data/chat-memory-index.db"
FlowerCore__AI__Skills__Library__LibraryApiUrl: "http://library-web.fc-library.svc.cluster.local"
FlowerCore__AI__Skills__Retail__RetailApiUrl: "http://retail-web.fc-retail.svc.cluster.local"
FlowerCore__AI__Skills__Intranet__IntranetBaseUrl: "http://intranet-web.intranet.svc.cluster.local"
FlowerCore__AI__Skills__Print__PrintMcpBaseUrl: "http://10.0.57.16:5200"
FlowerCore__AI__IrcBridge__Enabled: "true"
FlowerCore__AI__IrcBridge__DefaultProfileSlug: "it-helpdesk"
FlowerCore__AI__IrcBridge__MentionProfileSlug: "it-helpdesk"
FlowerCore__AI__IrcBridge__MentionReactiveMode: "mentions-only"
FlowerCore__AI__IrcBridge__AllowActionExecution: "false"
FlowerCore__AI__Voice__Piper__Host: "10.0.57.17"
FlowerCore__AI__Voice__Piper__Port: "10400"
FlowerCore__AI__Voice__OutputRoot: "/data/audio"
FlowerCore__AI__Voice__RetentionDays: "30"
# LLM provider abstraction (ADR-088). Anthropic stays disabled here -- when
# an operator wants to enable Claude, they flip Enabled=true and mount
# FlowerCore__Anthropic__ApiKey from the onepassword-synced Secret (see
# docs/ai-agents/anthropic-integration.md).
FlowerCore__Anthropic__Enabled: "false"
FlowerCore__Anthropic__BaseUrl: "https://api.anthropic.com"
FlowerCore__Anthropic__DefaultModel: "claude-sonnet-4-6"
FlowerCore__Anthropic__CheapModel: "claude-haiku-4-5-20251001"
FlowerCore__Anthropic__DeepModel: "claude-opus-4-7"
FlowerCore__Budget__ResponseCacheEnabled: "true"
OTEL_SERVICE_NAME: FlowerCore.Chat
OTEL_EXPORTER_OTLP_ENDPOINT: "http://otel-collector.monitoring.svc.cluster.local:4317"
OTEL_EXPORTER_OTLP_PROTOCOL: grpc
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: chat-web-data
namespace: fc-chat
labels:
app.kubernetes.io/name: chat-web
app.kubernetes.io/part-of: flowercore
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
volumeMode: Filesystem
resources:
requests:
storage: 1Gi
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: chat-web
namespace: fc-chat
labels:
app.kubernetes.io/name: chat-web
app.kubernetes.io/part-of: flowercore
spec:
replicas: 1
strategy:
type: Recreate
selector:
matchLabels:
app.kubernetes.io/name: chat-web
template:
metadata:
labels:
app.kubernetes.io/name: chat-web
app.kubernetes.io/part-of: flowercore
annotations:
prometheus.io/scrape: "true"
prometheus.io/port: "8080"
prometheus.io/path: "/metrics/prometheus"
spec:
nodeSelector:
kubernetes.io/hostname: rke2-server
securityContext:
fsGroup: 1654
fsGroupChangePolicy: OnRootMismatch
containers:
- name: chat-web
image: localhost/fc-chat-web:v20260603-oidc-authentik
imagePullPolicy: Never
ports:
- name: http
containerPort: 8080
envFrom:
- configMapRef:
name: chat-web-config
- secretRef:
name: chat-web-secret
optional: true
env:
- name: FlowerCore__Auth__Oidc__Authority
valueFrom:
secretKeyRef:
name: chat-oidc-client
key: issuer_url
optional: true
- name: FlowerCore__Auth__Oidc__ClientId
valueFrom:
secretKeyRef:
name: chat-oidc-client
key: client_id
optional: true
- name: FlowerCore__Auth__Oidc__ClientSecret
valueFrom:
secretKeyRef:
name: chat-oidc-client
key: client_secret
optional: true
volumeMounts:
- name: data
mountPath: /data
resources:
requests:
memory: "128Mi"
cpu: "100m"
limits:
memory: "512Mi"
cpu: "500m"
readinessProbe:
httpGet:
path: /healthz
port: 8080
initialDelaySeconds: 10
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 6
livenessProbe:
httpGet:
path: /healthz
port: 8080
initialDelaySeconds: 30
periodSeconds: 30
timeoutSeconds: 5
failureThreshold: 3
volumes:
- name: data
persistentVolumeClaim:
claimName: chat-web-data
---
apiVersion: v1
kind: Service
metadata:
name: chat-web
namespace: fc-chat
labels:
app.kubernetes.io/name: chat-web
app.kubernetes.io/part-of: flowercore
spec:
type: ClusterIP
selector:
app.kubernetes.io/name: chat-web
ports:
- name: http
port: 80
targetPort: 8080
protocol: TCP
# FlowerCore Chat — TLS + Ingress
# Deployment and Service managed by deploy script (not ArgoCD)
---
apiVersion: cert-manager.io/v1
kind: Certificate

View File

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

View File

@@ -47,7 +47,7 @@ spec:
fsGroupChangePolicy: OnRootMismatch
containers:
- name: operator
image: localhost/fc-devicemgmt-operator:v20260519-sp34cl3-fix
image: localhost/fc-devicemgmt-operator:v20260512-cx5
imagePullPolicy: Never
ports:
- name: metrics

View File

@@ -4,22 +4,6 @@
# 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:
@@ -36,7 +20,7 @@ metadata:
annotations:
flowercore.io/traceability-standard: k8s-pod-ownership-and-traceability-standard
spec:
replicas: 0
replicas: 2
revisionHistoryLimit: 3
selector:
matchLabels:

View File

@@ -130,27 +130,6 @@ spec:
value: "Production"
- name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
value: "false"
# Authentik/OIDC enforcement (flipped ON 2026-06-04, no-live-proof per operator;
# public read/entitlement + Method() allowlist stay open — OIDC gates admin only).
# Auth__Enabled reverted to false 2026-06-04: enabling it gated the
# /healthz readiness probe (probe->302->NotReady->endpoints drop->down).
# Re-enable once /healthz is AllowAnonymous (falcon OIDC lane).
- name: FlowerCore__Auth__Enabled
value: "false"
- name: FlowerCore__Auth__Oidc__Enabled
value: "true"
- name: FlowerCore__Auth__Oidc__Authority
value: "https://id.iamworkin.lan/application/o/distribution/"
- name: FlowerCore__Auth__Oidc__Audience
value: "distribution"
- name: FlowerCore__Auth__Oidc__ClientId
value: "distribution"
- name: FlowerCore__Auth__Oidc__ClientSecret
valueFrom:
secretKeyRef:
name: distribution-oidc-client
key: client_secret
optional: true
# SQLite connection (catalog + data-protection keys via FlowerCoreDbContext).
# Read by Data/DatabaseProviderExtensions.cs in precedence order; Sqlite key wins.
- name: FlowerCore__Database__Provider

View File

@@ -1,45 +0,0 @@
# FlowerCore Divoom DM Pi Device
Source-controlled Puppet/Hiera deployment contract for registering the edge2
Divoom MiniToo panel as a FlowerCore DeviceManagement-managed Pi device.
This is not a Kubernetes application. The live panel remains the existing
edge2 `flowercore-divoom.service` managed by `FlowerCore.Puppet`
`profile::pi::service::divoom`, with the .NET payload deployed out of band
and `/opt/flowercore/divoom/data` plus the Bluetooth shell wrappers preserved.
Because edge2 is already Hiera-driven through `profile::pi::service::apps`,
the deploy home is additive `profile::pi::service` data/profile source, not
`profile::edge::service::apps` and not an ArgoCD/K8s app.
## Scope
- Stage DeviceManagement registration metadata for the edge2 Divoom MiniToo.
- Stage a separate, disabled-by-default DM Agent executor unit for privileged
Bluetooth operations once the DM-RPC lane lands.
- Keep `flowercore-divoom.service` and `flowercore-divoom-bt.service`
untouched: no service replacement, no restart subscription, no K8s surface.
- Preserve the current wrapper contract:
`/opt/flowercore/divoom/bt-link.sh`,
`/opt/flowercore/divoom/bt-reset.sh`, and
`/opt/flowercore/divoom/audio-link.sh`.
- Keep FM radio disabled and require visible render proof; device-info echo is
not render proof.
## Artifact Map
| Path | Use |
| --- | --- |
| `hiera/edge2-divoom-dm-device.overlay.yaml` | Additive Hiera overlay for edge2. Merge into the existing node YAML without removing `fc-pimanager` or `fc-divoom`. |
| `puppet/profile/pi/service/divoom_dm_device.pp` | Puppet profile shape to vendor into `FlowerCore.Puppet` after the DM-RPC executor binary exists. |
| `puppet/templates/divoom-device-registration.json.epp` | DM device registration metadata rendered on edge2. |
| `puppet/templates/flowercore-divoom-dm-agent.service.epp` | Separate DM Agent systemd unit. Defaults are stopped and disabled until a later cutover. |
## Rollout Notes
1. Land these artifacts in bluejay-infra as the deploy contract.
2. Vendor the Puppet profile and EPP templates into `FlowerCore.Puppet`.
3. Merge the Hiera overlay into `data/nodes/edge2.iamworkin.lan.yaml`.
4. Run Puppet in noop first, preferably with a node-local validation directory
under `~/.fcv` rather than `/tmp`.
5. Only enable the DM Agent service after the DeviceManagement BT executor has
landed and passed operator-eyeball render proof.

View File

@@ -1,32 +0,0 @@
---
# Merge into FlowerCore.Puppet data/nodes/edge2.iamworkin.lan.yaml.
# Additive overlay only: keep the existing fc-pimanager version/tarball entry,
# keep fc-divoom enabled, and do not move Divoom into Kubernetes.
profile::pi::service::apps:
fc-pimanager:
binary: 'FlowerCore.PiManager.Web'
install_dir: '/opt/fc-pimanager'
port: 5000
environment: 'edge2'
version: '2026.05.28.1646'
tarball_source: 'puppet:///modules/profile/pi/builds/fc-pimanager.tar.gz'
fc-divoom:
enabled: true
profile::pi::service::divoom_dm_device::ensure: 'present'
profile::pi::service::divoom_dm_device::service_enabled: false
profile::pi::service::divoom_dm_device::service_ensure: 'stopped'
profile::pi::service::divoom_dm_device::device_id: 'edge2-divoom-minitoo'
profile::pi::service::divoom_dm_device::display_name: 'edge2 Divoom MiniToo'
profile::pi::service::divoom_dm_device::host_fqdn: 'edge2.iamworkin.lan'
profile::pi::service::divoom_dm_device::dm_web_url: 'https://devicemgmt.iamworkin.lan'
profile::pi::service::divoom_dm_device::divoom_install_dir: '/opt/flowercore/divoom'
profile::pi::service::divoom_dm_device::agent_install_dir: '/opt/flowercore/devicemanagement-agent'
profile::pi::service::divoom_dm_device::bt_candidate_channels:
- '1'
- '10'
profile::pi::service::divoom_dm_device::default_bt_channel: '1'
profile::pi::service::divoom_dm_device::a2dp_default_state: 'off'
profile::pi::service::divoom_dm_device::fm_radio_enabled: false
profile::pi::service::divoom_dm_device::visible_render_proof_required: true

View File

@@ -1,140 +0,0 @@
# Drop into FlowerCore.Puppet site-modules/profile/manifests/pi/service/divoom_dm_device.pp.
# This profile is additive to profile::pi::service::divoom. It must not manage,
# restart, replace, or subscribe the existing flowercore-divoom.service.
class profile::pi::service::divoom_dm_device (
Enum['present', 'absent'] $ensure = 'present',
Boolean $service_enabled = false,
Enum['running', 'stopped'] $service_ensure = 'stopped',
String $service_name = 'flowercore-divoom-dm-agent',
String $device_id = 'edge2-divoom-minitoo',
String $display_name = 'edge2 Divoom MiniToo',
String $host_fqdn = 'edge2.iamworkin.lan',
String $dm_web_url = 'https://devicemgmt.iamworkin.lan',
String $divoom_install_dir = '/opt/flowercore/divoom',
String $agent_install_dir = '/opt/flowercore/devicemanagement-agent',
String $agent_binary = 'FlowerCore.DeviceManagement.Agent',
Array[String] $bt_candidate_channels = ['1', '10'],
String $default_bt_channel = '1',
Enum['on', 'off'] $a2dp_default_state = 'off',
Boolean $fm_radio_enabled = false,
Boolean $visible_render_proof_required = true,
) {
include profile::workstation::safe_account_exclusion
$safe_account = $profile::workstation::safe_account_exclusion::safe_account
$config_dir = '/etc/flowercore/device-management/devices'
$state_dir = '/var/lib/flowercore/divoom-dm-agent'
$log_dir = '/var/log/flowercore/divoom-dm-agent'
$registration_path = "${config_dir}/${device_id}.json"
$agent_binary_path = "${agent_install_dir}/${agent_binary}"
$bt_channels_json = inline_template('[<%= @bt_candidate_channels.map { |c| "\"#{c}\"" }.join(", ") %>]')
if $safe_account {
notify { 'fc-divoom-dm-device safe-account exclusion':
message => 'SAFE-ACCOUNT-EXCLUSION: Divoom DM Pi device profile refused to apply on operator workstation',
}
if $facts['os']['family'] != 'windows' {
ensure_resource('file', '/var/log/flowercore-audit', {
'ensure' => 'directory',
'owner' => 'root',
'group' => 'root',
'mode' => '0755',
})
file { '/var/log/flowercore-audit/safe-account-noop-fc-divoom-dm-device.log':
ensure => file,
owner => 'root',
group => 'root',
mode => '0644',
content => "noop: divoom dm pi device profile refused to apply on safe-account host\n",
require => File['/var/log/flowercore-audit'],
}
}
} elsif $ensure == 'absent' {
service { $service_name:
ensure => stopped,
enable => false,
}
file { [
"/etc/systemd/system/${service_name}.service",
$registration_path,
]:
ensure => absent,
}
exec { 'fc-divoom-dm-agent-systemd-reload':
command => '/usr/bin/systemctl daemon-reload',
refreshonly => true,
path => ['/usr/bin', '/bin'],
}
} else {
case $facts['os']['family'] {
'Debian': {}
default: { fail("profile::pi::service::divoom_dm_device only supports Debian-family OS, got ${facts['os']['family']}") }
}
file { [$config_dir, $state_dir, $log_dir]:
ensure => directory,
owner => 'root',
group => 'root',
mode => '0755',
}
file { $registration_path:
ensure => file,
owner => 'root',
group => 'root',
mode => '0644',
content => epp('profile/pi/fc_divoom_dm/divoom-device-registration.json.epp', {
'device_id' => $device_id,
'display_name' => $display_name,
'host_fqdn' => $host_fqdn,
'divoom_install_dir' => $divoom_install_dir,
'bt_channels_json' => $bt_channels_json,
'default_bt_channel' => $default_bt_channel,
'a2dp_default_state' => $a2dp_default_state,
'fm_radio_enabled' => $fm_radio_enabled,
'visible_render_proof_required' => $visible_render_proof_required,
}),
require => File[$config_dir],
}
file { "/etc/systemd/system/${service_name}.service":
ensure => file,
owner => 'root',
group => 'root',
mode => '0644',
content => epp('profile/pi/fc_divoom_dm/flowercore-divoom-dm-agent.service.epp', {
'service_name' => $service_name,
'device_id' => $device_id,
'dm_web_url' => $dm_web_url,
'registration_path' => $registration_path,
'divoom_install_dir' => $divoom_install_dir,
'agent_install_dir' => $agent_install_dir,
'agent_binary_path' => $agent_binary_path,
'state_dir' => $state_dir,
'log_dir' => $log_dir,
}),
notify => Exec['fc-divoom-dm-agent-systemd-reload'],
require => File[$registration_path],
}
exec { 'fc-divoom-dm-agent-systemd-reload':
command => '/usr/bin/systemctl daemon-reload',
refreshonly => true,
path => ['/usr/bin', '/bin'],
}
service { $service_name:
ensure => $service_ensure,
enable => $service_enabled,
require => [
File["/etc/systemd/system/${service_name}.service"],
File[$registration_path],
Exec['fc-divoom-dm-agent-systemd-reload'],
],
}
}
}

View File

@@ -1,34 +0,0 @@
{
"deviceId": "<%= $device_id %>",
"displayName": "<%= $display_name %>",
"hostFqdn": "<%= $host_fqdn %>",
"kind": "DivoomMiniToo",
"managedBy": "FlowerCore.DeviceManagement",
"executionMode": "Pi",
"transport": {
"kind": "BluetoothSerial",
"candidateChannels": <%= $bt_channels_json %>,
"defaultChannel": "<%= $default_bt_channel %>",
"deviceInfoIsRenderProof": false,
"visibleRenderProofRequired": <%= $visible_render_proof_required %>
},
"paths": {
"divoomInstallDir": "<%= $divoom_install_dir %>",
"btLink": "<%= $divoom_install_dir %>/bt-link.sh",
"btReset": "<%= $divoom_install_dir %>/bt-reset.sh",
"audioLink": "<%= $divoom_install_dir %>/audio-link.sh"
},
"capabilities": {
"supportsBluetoothSerial": true,
"supportsBtChannelRedetect": true,
"supportsBtHardReset": true,
"supportsBtAudioProfileSwitch": true,
"a2dpDefaultState": "<%= $a2dp_default_state %>",
"fmRadioEnabled": <%= $fm_radio_enabled %>
},
"safety": {
"preserveExistingService": "flowercore-divoom.service",
"preserveDataDirectory": "<%= $divoom_install_dir %>/data",
"doNotEnableFmRadio": true
}
}

View File

@@ -1,36 +0,0 @@
[Unit]
Description=FlowerCore Divoom DM Agent Bluetooth executor
Documentation=https://github.com/astoltz/FlowerCore.Notes/blob/master/docs/standards/divoom-tv-hdmi-multitarget-render-substrate.md
Wants=network-online.target
After=network-online.target bluetooth.service
Requires=bluetooth.service
ConditionPathExists=<%= $agent_binary_path %>
ConditionPathExists=<%= $registration_path %>
ConditionPathExists=<%= $divoom_install_dir %>/bt-link.sh
ConditionPathExists=<%= $divoom_install_dir %>/bt-reset.sh
ConditionPathExists=<%= $divoom_install_dir %>/audio-link.sh
[Service]
Type=simple
User=stoltz
Group=stoltz
WorkingDirectory=<%= $agent_install_dir %>
Environment=DOTNET_CLI_TELEMETRY_OPTOUT=1
Environment=FLOWERCORE_DM_DEVICE_REGISTRATION=<%= $registration_path %>
Environment=Divoom__Bluetooth__DeviceInfoIsRenderProof=false
Environment=Divoom__Bluetooth__VisibleRenderProofRequired=true
Environment=Divoom__Bluetooth__A2dpDefaultState=off
ExecStart=<%= $agent_binary_path %> --mode=Pi --device-id=<%= $device_id %> --dm-web-url=<%= $dm_web_url %> --registration=<%= $registration_path %>
Restart=on-failure
RestartSec=10s
StartLimitBurst=3
StartLimitIntervalSec=300s
SupplementaryGroups=bluetooth audio dialout
NoNewPrivileges=true
PrivateTmp=true
ProtectSystem=strict
ProtectHome=true
ReadWritePaths=<%= $state_dir %> <%= $log_dir %>
[Install]
WantedBy=multi-user.target

View File

@@ -1,44 +0,0 @@
# FlowerCore Divoom TV Pi HDMI
Source-controlled deploy shape for the native `FlowerCore.Divoom.Tv`
Avalonia HDMI renderer on a Raspberry Pi connected to a TV.
This is a Puppet/systemd appliance bundle, not a Kubernetes application. It
mirrors the existing `fc-signage-pi-player` pattern: bluejay-infra carries the
systemd units, scripts, Hiera shape, and Puppet profile source that
`FlowerCore.Puppet` vendors and installs.
## Scope
- Launch the future `FlowerCore.Divoom.Tv` linux-arm64 self-contained payload
from `/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv`.
- Prefer `cage` as the Wayland fullscreen compositor, with direct app launch as
a fallback for development images.
- Restart the app after HDMI hotplug with a 2 second DRM settle delay.
- Keep all runtime state local: `/var/lib/fc-divoom-tv` and
`/var/log/fc-divoom-tv`.
- Avoid CDN/runtime fetches; the app renders the in-house Divoom scene catalog
locally.
## Artifact Map
| Path | Use |
| --- | --- |
| `systemd/flowercore-divoom-tv.service` | Fullscreen Avalonia HDMI app service. |
| `systemd/flowercore-divoom-tv-hdmi.service` | HDMI hotplug responder service. |
| `systemd/99-flowercore-divoom-tv-hdmi.rules` | DRM udev hotplug rule. |
| `scripts/flowercore-divoom-tv-prelaunch.sh` | Preflight checks and local directory creation. |
| `scripts/flowercore-divoom-tv-launch.sh` | Cage-first fullscreen launcher. |
| `scripts/flowercore-divoom-tv-hdmi-respond.sh` | Hotplug settle and restart script. |
| `puppet/profile/pi/service/divoom_tv.pp` | Puppet profile shape to vendor into `FlowerCore.Puppet`. |
| `hiera/example-divoom-tv-pi.iamworkin.lan.yaml` | Example node Hiera for a Divoom TV Pi. |
## Rollout Notes
1. Build `FlowerCore.Divoom.Tv` with `dotnet.exe publish -c Release -r linux-arm64 --self-contained`.
2. Stage the payload to `/opt/flowercore/divoom-tv/` through the standard noc1
jump path and avoid `/tmp` for unprivileged Pi scratch.
3. Vendor the profile and static files into `FlowerCore.Puppet`.
4. Run Puppet noop, then apply on the target Pi.
5. Prove deployment with `systemctl is-active flowercore-divoom-tv.service`,
journal lines showing frames presented, and a visible HDMI display check.

View File

@@ -1,19 +0,0 @@
---
# Example node data for a dedicated Pi -> HDMI -> TV Divoom renderer.
# Copy into FlowerCore.Puppet data/nodes/<hostname>.iamworkin.lan.yaml only
# after the Pi has a static DHCP/DNS entry and the linux-arm64 payload exists.
facts:
role: pi_prototype
profile::motd::role: 'Divoom TV HDMI Renderer'
profile::pi::service::divoom_tv::ensure: 'present'
profile::pi::service::divoom_tv::service_enabled: true
profile::pi::service::divoom_tv::service_ensure: 'running'
profile::pi::service::divoom_tv::install_dir: '/opt/flowercore/divoom-tv'
profile::pi::service::divoom_tv::state_dir: '/var/lib/fc-divoom-tv'
profile::pi::service::divoom_tv::log_dir: '/var/log/fc-divoom-tv'
profile::pi::service::divoom_tv::presentation_mode: 'PillarboxSquare'
profile::pi::service::divoom_tv::startup_scene: 'bluejay-clock'
profile::pi::service::divoom_tv::reduced_motion: false

View File

@@ -1,149 +0,0 @@
# Drop into FlowerCore.Puppet site-modules/profile/manifests/pi/service/divoom_tv.pp.
# Static files come from profile/pi/fc_divoom_tv/ after this bluejay-infra
# bundle is vendored into the Puppet control repo.
class profile::pi::service::divoom_tv (
Enum['present', 'absent'] $ensure = 'present',
Boolean $service_enabled = false,
Enum['running', 'stopped'] $service_ensure = 'stopped',
String $service_name = 'flowercore-divoom-tv',
String $user = 'fc-divoom-tv',
String $group = 'fc-divoom-tv',
String $install_dir = '/opt/flowercore/divoom-tv',
String $state_dir = '/var/lib/fc-divoom-tv',
String $log_dir = '/var/log/fc-divoom-tv',
String $presentation_mode = 'PillarboxSquare',
String $startup_scene = 'bluejay-clock',
Boolean $reduced_motion = false,
) {
include profile::workstation::safe_account_exclusion
$safe_account = $profile::workstation::safe_account_exclusion::safe_account
if $safe_account {
notify { 'fc-divoom-tv safe-account exclusion':
message => 'SAFE-ACCOUNT-EXCLUSION: Divoom TV Pi profile refused to apply on operator workstation',
}
} elsif $ensure == 'absent' {
service { $service_name:
ensure => stopped,
enable => false,
}
file { [
"/etc/systemd/system/${service_name}.service",
"/etc/systemd/system/${service_name}-hdmi.service",
'/etc/udev/rules.d/99-flowercore-divoom-tv-hdmi.rules',
'/usr/local/bin/flowercore-divoom-tv-prelaunch.sh',
'/usr/local/bin/flowercore-divoom-tv-launch.sh',
'/usr/local/bin/flowercore-divoom-tv-hdmi-respond.sh',
'/etc/flowercore/divoom-tv.env',
]:
ensure => absent,
}
} else {
case $facts['os']['family'] {
'Debian': {}
default: { fail("profile::pi::service::divoom_tv only supports Debian-family OS, got ${facts['os']['family']}") }
}
package { ['cage', 'libgbm1', 'libdrm2', 'libxkbcommon0', 'fonts-dejavu-core']:
ensure => installed,
}
group { $group:
ensure => present,
system => true,
}
user { $user:
ensure => present,
system => true,
gid => $group,
home => $state_dir,
managehome => false,
shell => '/usr/sbin/nologin',
require => Group[$group],
}
file { [$install_dir, $state_dir, $log_dir, '/etc/flowercore']:
ensure => directory,
owner => $user,
group => $group,
mode => '0755',
}
file { '/etc/flowercore/divoom-tv.env':
ensure => file,
owner => 'root',
group => 'root',
mode => '0644',
content => "FC_DIVOOM_TV_PRESENTATION_MODE=${presentation_mode}\nFC_DIVOOM_TV_START_SCENE=${startup_scene}\nFC_DIVOOM_TV_REDUCED_MOTION=${reduced_motion}\n",
require => File['/etc/flowercore'],
}
$script_map = {
'/usr/local/bin/flowercore-divoom-tv-prelaunch.sh' => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv-prelaunch.sh',
'/usr/local/bin/flowercore-divoom-tv-launch.sh' => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv-launch.sh',
'/usr/local/bin/flowercore-divoom-tv-hdmi-respond.sh' => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv-hdmi-respond.sh',
}
$script_map.each |$dest, $src| {
file { $dest:
ensure => file,
owner => 'root',
group => 'root',
mode => '0755',
source => "puppet:///modules/${src}",
}
}
$unit_map = {
"/etc/systemd/system/${service_name}.service" => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv.service',
"/etc/systemd/system/${service_name}-hdmi.service" => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv-hdmi.service',
}
$unit_map.each |$dest, $src| {
file { $dest:
ensure => file,
owner => 'root',
group => 'root',
mode => '0644',
source => "puppet:///modules/${src}",
notify => Exec['fc-divoom-tv-systemd-reload'],
}
}
file { '/etc/udev/rules.d/99-flowercore-divoom-tv-hdmi.rules':
ensure => file,
owner => 'root',
group => 'root',
mode => '0644',
source => 'puppet:///modules/profile/pi/fc_divoom_tv/99-flowercore-divoom-tv-hdmi.rules',
notify => Exec['fc-divoom-tv-udev-reload'],
}
exec { 'fc-divoom-tv-systemd-reload':
command => '/usr/bin/systemctl daemon-reload',
refreshonly => true,
path => ['/usr/bin', '/bin'],
}
exec { 'fc-divoom-tv-udev-reload':
command => '/usr/bin/udevadm control --reload-rules',
refreshonly => true,
path => ['/usr/bin', '/bin'],
}
service { $service_name:
ensure => $service_ensure,
enable => $service_enabled,
require => [
File["/etc/systemd/system/${service_name}.service"],
File['/etc/flowercore/divoom-tv.env'],
File['/usr/local/bin/flowercore-divoom-tv-prelaunch.sh'],
File['/usr/local/bin/flowercore-divoom-tv-launch.sh'],
Exec['fc-divoom-tv-systemd-reload'],
],
}
}
}

View File

@@ -1,5 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
sleep 2
systemctl restart flowercore-divoom-tv.service

View File

@@ -1,25 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
APP_BIN="${FC_DIVOOM_TV_BIN:-/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv}"
STATE_DIR="${FC_DIVOOM_TV_STATE_DIR:-/var/lib/fc-divoom-tv}"
LOG_DIR="${FC_DIVOOM_TV_LOG_DIR:-/var/log/fc-divoom-tv}"
PRESENTATION_MODE="${FC_DIVOOM_TV_PRESENTATION_MODE:-PillarboxSquare}"
START_SCENE="${FC_DIVOOM_TV_START_SCENE:-bluejay-clock}"
REDUCED_MOTION="${FC_DIVOOM_TV_REDUCED_MOTION:-false}"
COMMON_ARGS=(
"--target=hdmi"
"--presentation-mode=${PRESENTATION_MODE}"
"--startup-scene=${START_SCENE}"
"--reduced-motion=${REDUCED_MOTION}"
"--state-dir=${STATE_DIR}"
"--log-dir=${LOG_DIR}"
)
if command -v cage >/dev/null 2>&1; then
exec cage -- "${APP_BIN}" "${COMMON_ARGS[@]}" "$@"
fi
echo "[$(date -Is)] cage not found; launching FlowerCore.Divoom.Tv directly" >&2
exec "${APP_BIN}" "${COMMON_ARGS[@]}" "$@"

View File

@@ -1,23 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
APP_BIN="${FC_DIVOOM_TV_BIN:-/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv}"
STATE_DIR="${FC_DIVOOM_TV_STATE_DIR:-/var/lib/fc-divoom-tv}"
LOG_DIR="${FC_DIVOOM_TV_LOG_DIR:-/var/log/fc-divoom-tv}"
mkdir -p "${STATE_DIR}" "${LOG_DIR}"
if [[ ! -x "${APP_BIN}" ]]; then
echo "[$(date -Is)] missing executable ${APP_BIN}" >&2
exit 1
fi
if [[ -d /sys/class/drm ]] && ! find /sys/class/drm -maxdepth 1 -name 'card*-HDMI-A-*' -print -quit | grep -q .; then
echo "[$(date -Is)] no HDMI connector visible yet; continuing so the app can wait for display" >&2
fi
if command -v cage >/dev/null 2>&1; then
echo "[$(date -Is)] cage available for fullscreen Wayland launch"
else
echo "[$(date -Is)] cage not installed; direct launch fallback will be used" >&2
fi

View File

@@ -1,2 +0,0 @@
# Settle DRM for 2s before restarting the fullscreen Avalonia renderer.
SUBSYSTEM=="drm", KERNEL=="card?-HDMI-A-?", ACTION=="change", RUN+="/usr/bin/systemctl start flowercore-divoom-tv-hdmi.service"

View File

@@ -1,7 +0,0 @@
[Unit]
Description=FlowerCore Divoom TV HDMI hotplug responder
DefaultDependencies=no
[Service]
Type=oneshot
ExecStart=/usr/local/bin/flowercore-divoom-tv-hdmi-respond.sh

View File

@@ -1,40 +0,0 @@
[Unit]
Description=FlowerCore Divoom TV HDMI Renderer (Avalonia fullscreen)
Documentation=https://github.com/astoltz/FlowerCore.Notes/blob/master/docs/standards/divoom-tv-hdmi-multitarget-render-substrate.md
Wants=network-online.target
After=network-online.target systemd-user-sessions.service
ConditionPathExists=/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv
[Service]
Type=simple
User=fc-divoom-tv
Group=fc-divoom-tv
WorkingDirectory=/opt/flowercore/divoom-tv
EnvironmentFile=-/etc/flowercore/divoom-tv.env
Environment=DOTNET_CLI_TELEMETRY_OPTOUT=1
Environment=XDG_RUNTIME_DIR=/run/fc-divoom-tv
RuntimeDirectory=fc-divoom-tv
RuntimeDirectoryMode=0700
ExecStartPre=/usr/local/bin/flowercore-divoom-tv-prelaunch.sh
ExecStart=/usr/local/bin/flowercore-divoom-tv-launch.sh
Restart=always
RestartSec=10s
StartLimitBurst=5
StartLimitIntervalSec=300s
MemoryMax=2G
MemoryHigh=1500M
PrivateTmp=true
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
ReadWritePaths=/var/lib/fc-divoom-tv /var/log/fc-divoom-tv /run/fc-divoom-tv
TTYPath=/dev/tty1
StandardInput=tty
StandardOutput=journal
StandardError=journal
TTYReset=yes
TTYVHangup=yes
TTYVTDisallocate=yes
[Install]
WantedBy=graphical.target

View File

@@ -1,169 +0,0 @@
# FlowerCore.Library.Web GitOps adoption manifest.
#
# Authored from the already-live fc-library resources on 2026-06-04.
# Keep the live image tag, Service ClusterIP, and PVC volumeName unchanged so
# ArgoCD adopts in place instead of replacing the workload or data volume.
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: library-web-data
namespace: fc-library
labels:
app.kubernetes.io/name: library-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-library
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 1Gi
storageClassName: longhorn
volumeMode: Filesystem
volumeName: pvc-2690bae2-4ee0-417a-b95f-50ec5c632b63
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: library-web
namespace: fc-library
labels:
app.kubernetes.io/name: library-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-library
spec:
progressDeadlineSeconds: 600
replicas: 1
revisionHistoryLimit: 3
selector:
matchLabels:
app.kubernetes.io/name: library-web
strategy:
type: Recreate
template:
metadata:
annotations:
prometheus.io/path: /metrics/prometheus
prometheus.io/port: "5000"
prometheus.io/scrape: "true"
labels:
app.kubernetes.io/name: library-web
app.kubernetes.io/part-of: flowercore
spec:
containers:
- envFrom:
- configMapRef:
name: library-web-config
image: localhost/fc-library-web:v20260602-library-owned-deploy-fix1
imagePullPolicy: Never
livenessProbe:
failureThreshold: 3
httpGet:
path: /health
port: 5000
scheme: HTTP
initialDelaySeconds: 30
periodSeconds: 30
successThreshold: 1
timeoutSeconds: 5
name: library-web
ports:
- containerPort: 5000
name: http
protocol: TCP
readinessProbe:
failureThreshold: 6
httpGet:
path: /health
port: 5000
scheme: HTTP
initialDelaySeconds: 10
periodSeconds: 10
successThreshold: 1
timeoutSeconds: 5
resources: {}
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /data
name: data
dnsPolicy: ClusterFirst
restartPolicy: Always
schedulerName: default-scheduler
securityContext: {}
terminationGracePeriodSeconds: 30
volumes:
- name: data
persistentVolumeClaim:
claimName: library-web-data
---
apiVersion: v1
kind: Service
metadata:
name: library-web
namespace: fc-library
labels:
app.kubernetes.io/name: library-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-library
spec:
clusterIP: 10.43.179.63
clusterIPs:
- 10.43.179.63
internalTrafficPolicy: Cluster
ipFamilies:
- IPv4
ipFamilyPolicy: SingleStack
ports:
- name: http
port: 80
protocol: TCP
targetPort: 5000
selector:
app.kubernetes.io/name: library-web
sessionAffinity: None
type: ClusterIP
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: library-web-tls
namespace: fc-library
labels:
app.kubernetes.io/name: library-web-tls
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-library
spec:
dnsNames:
- library.iamworkin.lan
issuerRef:
kind: ClusterIssuer
name: step-ca-acme
secretName: library-web-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: library-web
namespace: fc-library
labels:
app.kubernetes.io/name: library-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-library
spec:
entryPoints:
- websecure
routes:
- kind: Rule
match: Host(`library.iamworkin.lan`)
services:
- name: library-web
port: 80
tls:
secretName: library-web-tls

View File

@@ -1,170 +0,0 @@
# FlowerCore.Retail.Web GitOps adoption manifest.
#
# Authored from the already-live fc-retail resources on 2026-06-04.
# Keep the live image tag, Service ClusterIP, and PVC volumeName unchanged so
# ArgoCD adopts in place instead of replacing the workload or data volume.
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: retail-web-data
namespace: fc-retail
labels:
app.kubernetes.io/name: retail-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-retail
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 1Gi
storageClassName: longhorn
volumeMode: Filesystem
volumeName: pvc-3d40b336-eab4-41b3-812c-d5e9413ce0ab
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: retail-web
namespace: fc-retail
labels:
app.kubernetes.io/name: retail-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-retail
spec:
progressDeadlineSeconds: 600
replicas: 1
revisionHistoryLimit: 3
selector:
matchLabels:
app.kubernetes.io/name: retail-web
strategy:
type: Recreate
template:
metadata:
annotations:
kubectl.kubernetes.io/restartedAt: "2026-06-02T01:34:08-05:00"
prometheus.io/path: /metrics/prometheus
prometheus.io/port: "5000"
prometheus.io/scrape: "true"
labels:
app.kubernetes.io/name: retail-web
app.kubernetes.io/part-of: flowercore
spec:
containers:
- envFrom:
- configMapRef:
name: retail-web-config
image: localhost/fc-retail-web:v20260602-retail-owned-deploy-fix5
imagePullPolicy: Never
livenessProbe:
failureThreshold: 3
httpGet:
path: /health
port: 5000
scheme: HTTP
initialDelaySeconds: 30
periodSeconds: 30
successThreshold: 1
timeoutSeconds: 5
name: retail-web
ports:
- containerPort: 5000
name: http
protocol: TCP
readinessProbe:
failureThreshold: 6
httpGet:
path: /health
port: 5000
scheme: HTTP
initialDelaySeconds: 10
periodSeconds: 10
successThreshold: 1
timeoutSeconds: 5
resources: {}
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /data
name: data
dnsPolicy: ClusterFirst
restartPolicy: Always
schedulerName: default-scheduler
securityContext: {}
terminationGracePeriodSeconds: 30
volumes:
- name: data
persistentVolumeClaim:
claimName: retail-web-data
---
apiVersion: v1
kind: Service
metadata:
name: retail-web
namespace: fc-retail
labels:
app.kubernetes.io/name: retail-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-retail
spec:
clusterIP: 10.43.239.8
clusterIPs:
- 10.43.239.8
internalTrafficPolicy: Cluster
ipFamilies:
- IPv4
ipFamilyPolicy: SingleStack
ports:
- name: http
port: 80
protocol: TCP
targetPort: 5000
selector:
app.kubernetes.io/name: retail-web
sessionAffinity: None
type: ClusterIP
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: retail-web-tls
namespace: fc-retail
labels:
app.kubernetes.io/name: retail-web-tls
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-retail
spec:
dnsNames:
- retail.iamworkin.lan
issuerRef:
kind: ClusterIssuer
name: step-ca-acme
secretName: retail-web-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: retail-web
namespace: fc-retail
labels:
app.kubernetes.io/name: retail-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-retail
spec:
entryPoints:
- websecure
routes:
- kind: Rule
match: Host(`retail.iamworkin.lan`)
services:
- name: retail-web
port: 80
tls:
secretName: retail-web-tls

View File

@@ -532,7 +532,7 @@ spec:
fsGroupChangePolicy: OnRootMismatch
containers:
- name: web
image: localhost/fc-ttsreader-web:v20260603-s54cx14-pr29-schema
image: localhost/fc-ttsreader-web:v20260518-sprint36-demo-finish-b132cbf
imagePullPolicy: Never
ports:
- containerPort: 5217
@@ -554,8 +554,6 @@ spec:
value: "/data/chapter-context.db"
- name: TtsReader__Jobs__Root
value: "/data/jobs"
- name: TtsReader__Export__LocalCasRoot
value: "/data/bundles/cas"
- name: TtsReader__Piper__Host
value: "10.0.57.17"
- name: TtsReader__Piper__Port

View File

@@ -58,7 +58,7 @@ spec:
nodeName: rke2-server
containers:
- name: web
image: localhost/fc-updater-web:v202605310029-7974fc4
image: localhost/fc-updater-web:v20260509-4162dca-authgate
imagePullPolicy: Never
ports:
- containerPort: 8080
@@ -88,8 +88,6 @@ spec:
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

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

@@ -7,17 +7,12 @@ Deployments with `kubectl`; update this manifest and let ArgoCD reconcile.
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
@@ -33,45 +28,9 @@ Sprint 32 final long-tail wave adds 16 two-replica Deployments:
`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 "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images import /tmp/fc-github-runner-v20260525-ruby3.3.11-stepca.tar'
done
```
Sprint 37 Cx-2 closes the audited Linux runner gaps for
`FlowerCore.DeviceManagement` and `FlowerCore.WorldBuilder` with the same
two-replica `emptyDir` pattern.
## Post-Merge Proof
@@ -81,14 +40,6 @@ After the PR is merged and ArgoCD syncs, verify the runner fleet:
kubectl -n github-runner get deploy,pods,pvc
```
Verify the Ruby toolcache in a fresh pod:
```bash
kubectl -n github-runner exec deploy/github-runner-puppet -c runner -- ruby -v
kubectl -n github-runner exec deploy/github-runner-puppet -c runner -- sh -c \
'echo "$RUNNER_TOOL_CACHE" && test -f "$RUNNER_TOOL_CACHE/Ruby/3.3/x64.complete"'
```
Verify GitHub registration for the repo-scoped runners:
```bash
@@ -100,7 +51,7 @@ for repo in FlowerCore.Common FlowerCore.Shared.Pos FlowerCore.Puppet FlowerCore
FlowerCore.Distribution FlowerCore.Scoreboard FlowerCore.SegmentDisplay \
FlowerCore.Signage.Contracts FlowerCore.SignalControl FlowerCore.Intranet.Web \
FlowerCore.Provisioning FlowerCore.Redis FlowerCore.MessageBoard \
FlowerCore.MenuBoard; do
FlowerCore.MenuBoard FlowerCore.DeviceManagement FlowerCore.WorldBuilder; do
echo "=== $repo ==="
gh api "/repos/astoltz/$repo/actions/runners" \
--jq '.runners[] | select(.labels[].name == "fc-build-linux") | {name,status,busy,labels:[.labels[].name]}'
@@ -117,15 +68,25 @@ gh run list --repo astoltz/FlowerCore.Shared.Pos \
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.
## Sprint 37 Cx-2 Gap Audit
The 2026-05-18 GitHub workflow scan found these remaining repos with
`runs-on: [self-hosted, linux, fc-build-linux]` but no K8s runner Deployment:
`FlowerCore.AiStation.Linux`, `FlowerCore.PHP`, `FlowerCore.PiManager`,
`FlowerCore.Shared.Barcodes`, `FlowerCore.Shared.Lookup`,
`FlowerCore.Shared.Nodes`, `FlowerCore.Shared.PrintClient`,
`FlowerCore.Shared.Relay`, `FlowerCore.Shared.ShowRunner`, and
`FlowerCore.Shared.Storage`.
Mixed/platform repos also have Linux workflow legs but need owner review before
adding Linux runner Deployments: `FlowerCore.Library.Mac`,
`FlowerCore.Signage.Agent.AppleTv`, and `FlowerCore.Signage.Player.Wpf`.
## 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.

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

@@ -46,7 +46,7 @@ spec:
spec:
containers:
- name: intranet-web
image: localhost/fc-intranet-web:v20260531-ttsreader-bridge
image: localhost/fc-intranet-web:v20260508-brochure-w1
imagePullPolicy: Never
ports:
- containerPort: 5300

View File

@@ -93,7 +93,6 @@ spec:
prometheus.io/scrape: "true"
prometheus.io/port: "8080"
prometheus.io/path: "/metrics"
flowercore.io/healthz-auth-policy: "allow-anonymous"
spec:
securityContext:
runAsNonRoot: true
@@ -103,7 +102,7 @@ spec:
- name: web
# Placeholder tag — bump to the image you built + imported to ALL
# RKE2 nodes via scripts/deploy-knowledge.sh before applying.
image: localhost/fc-knowledge-web:v20260603-oidc-authentik-auditfix
image: localhost/fc-knowledge-web:v20260429232635
imagePullPolicy: Never
command:
- /bin/sh
@@ -124,25 +123,6 @@ spec:
value: "Production"
- name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
value: "false"
# AuthentiK/OIDC is enforced. /healthz stays anonymous by contract;
# see flowercore.io/healthz-auth-policy above and the Sprint 58
# OIDC readiness probe audit.
- name: FlowerCore__Auth__Enabled
value: "true"
- name: FlowerCore__Auth__Oidc__Enabled
value: "true"
- name: FlowerCore__Auth__Oidc__Authority
value: "https://id.iamworkin.lan/application/o/knowledge/"
- name: FlowerCore__Auth__Oidc__Audience
value: "knowledge"
- name: FlowerCore__Auth__Oidc__ClientId
value: "knowledge"
- name: FlowerCore__Auth__Oidc__ClientSecret
valueFrom:
secretKeyRef:
name: knowledge-oidc-client
key: client_secret
optional: true
# Vector-store directory + embedding model + edition profile dir.
# Profile JSON is baked into the image at /home/app/editions via the
# csproj Content-link from FlowerCore.Common/editions/.
@@ -154,8 +134,6 @@ spec:
value: "5"
- name: Knowledge__MaxLimit
value: "50"
- name: Knowledge__Federation__DatabasePath
value: "/data/vector-stores/knowledge-federation.db"
- name: FlowerCore__Editions__ProfileDirectory
value: "/home/app/editions"
# Embed via edge1 Pi 5 + AI HAT+ (10.0.57.17:11434). Cluster

View File

@@ -25,7 +25,7 @@ metadata:
role: github-actions-runner
flowercore.io/managed-by: bluejay-infra
spec:
runStrategy: Halted
runStrategy: Always
template:
metadata:
labels:

View File

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

View File

@@ -223,7 +223,7 @@ data:
service: "pimanager"
vlan: "home"
device: "pi4-ezconnect"
- targets: ["10.0.58.113:5200"]
- targets: ["10.0.58.113:5100"]
labels:
instance: "pirelay"
service: "pimanager"
@@ -280,14 +280,13 @@ data:
printer_model: "NuPrint 210"
# Print.Web health (Blazor app on edge2:5200)
# Target `/health` (anonymous) — root path requires API key auth and returns 401.
- job_name: "probe-printweb"
metrics_path: /probe
params:
module: [http_2xx]
scrape_interval: 30s
static_configs:
- targets: ["http://10.0.57.16:5200/health"]
- targets: ["http://10.0.57.16:5200/"]
labels:
instance: "print-web"
service: "print-web"
@@ -479,27 +478,24 @@ data:
- "https://gitea.iamworkin.lan/"
- "https://argocd.iamworkin.lan/"
- "https://intranet.iamworkin.lan/"
- "https://signage.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
- "https://signage.iamworkin.lan/"
- "https://kiosk.iamworkin.lan/"
- "https://media.iamworkin.lan/" # OIDC lane must add /healthz before flipping auth; live /healthz 404 on 2026-06-04
- "https://mysql.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
- "https://php.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
- "https://media.iamworkin.lan/"
- "https://mysql.iamworkin.lan/"
- "https://php.iamworkin.lan/"
- "https://zabbix.iamworkin.lan/"
- "https://desktop.iamworkin.lan/"
- "https://print.iamworkin.lan/healthz" # root 401 behind API key auth; /healthz anonymous 200
- "https://dns.iamworkin.lan/" # OIDC lane must add /healthz before flipping auth; live /healthz 404 on 2026-06-04
- "https://chat.iamworkin.lan/healthz" # OIDC staged; keep blackbox off root before enforcement flips
- "https://dist.iamworkin.lan/healthz" # distribution OIDC flip outage was /healthz gating; probe the anonymous health route
- "https://dms.iamworkin.lan/healthz" # future OIDC posture; health route is already anonymous/live
- "https://print.iamworkin.lan/"
- "https://dns.iamworkin.lan/"
- "https://chat.iamworkin.lan/"
- "https://dist.iamworkin.lan/"
- "https://dms.iamworkin.lan/"
- "https://menuboard.iamworkin.lan/"
- "https://messageboard.iamworkin.lan/"
- "https://presentations.iamworkin.lan/"
- "https://retail.iamworkin.lan/"
- "https://ttsreader.iamworkin.lan/"
# Explicit healthcheck paths
- "https://library.iamworkin.lan/health"
- "https://aistation.iamworkin.lan/healthz"
- "https://knowledge.iamworkin.lan/healthz"
- "https://fc-llm-bridge.iamworkin.lan/healthz"
- "https://acme.iamworkin.lan/health"
# NOTE: services intentionally NOT in this probe surface
@@ -733,7 +729,7 @@ data:
expr: |
kube_deployment_status_replicas_ready{
namespace="github-runner",
deployment=~"github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"
deployment=~"github-runner(|-.+)"
} == 0
for: 5m
labels:
@@ -1023,12 +1019,7 @@ data:
- name: kubernetes-state
rules:
- alert: KubeContainerRestartingFrequently
# Exclude github-runner: ephemeral runners register, run one job,
# exit cleanly, and restart by design. Also require kube_pod_info so
# deleted rollout pods do not keep firing from retained restart series.
expr: |
increase(kube_pod_container_status_restarts_total{namespace!="github-runner"}[1h]) > 5
and on(namespace, pod) kube_pod_info
expr: increase(kube_pod_container_status_restarts_total[1h]) > 5
for: 15m
labels:
severity: warning
@@ -1037,12 +1028,7 @@ data:
description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has restarted {{ $value | printf \"%.0f\" }} times in the last hour. Check 'kubectl describe pod' + last-state termination reason."
- alert: KubeContainerCrashLooping
# Same github-runner/delete-retention exclusions as the hourly
# restart rule above; real runner failures are covered by the
# dedicated LinuxRunnerOffline/MacMiniRunnerOffline alerts.
expr: |
increase(kube_pod_container_status_restarts_total{namespace!="github-runner"}[15m]) > 3
and on(namespace, pod) kube_pod_info
expr: increase(kube_pod_container_status_restarts_total[15m]) > 3
for: 5m
labels:
severity: critical
@@ -1070,10 +1056,7 @@ data:
description: "Pod can't pull image. Check the image ref (often a stale tag or unreachable registry) and clean up if it's an orphan."
- alert: KubeDeploymentReplicasMismatch
# github-runner has explicit runner-offline alerts; the generic
# replica-mismatch rule should not page on intentionally ephemeral
# 0/1 runner churn between CI jobs.
expr: kube_deployment_spec_replicas{namespace!="github-runner"} != kube_deployment_status_replicas_available{namespace!="github-runner"}
expr: kube_deployment_spec_replicas != kube_deployment_status_replicas_available
for: 15m
labels:
severity: warning
@@ -1290,55 +1273,24 @@ metadata:
data:
notify.py: |
#!/usr/bin/env python3
"""HTTP->IRC alert relay with thermal-printer DIGEST forwarding.
Listens on :9119, posts to #alerts on UnrealIRCd, forwards to Print.Web
/api/print/alert. Thermal printing is BATCHED into hourly digests by
default so the printer no longer spam-fires per Grafana webhook.
Routing (per Grafana webhook alert):
- IRC: always per-event (operator likes the stream)
- Thermal printer:
* severity in {critical,disaster,page} OR
label alert_channel=thermal_print_immediate -> print NOW
* label alert_channel=thermal_print -> enqueue into hourly digest
* everything else -> IRC only
- RESOLVED webhooks remove the alert from the digest buffer
Env vars (defaults preserve old behavior on first deploy):
THERMAL_PRINT_ENABLED default "true" - master kill switch
BATCH_INTERVAL_MIN default "60" - minutes between digest prints
BATCH_MAX_PENDING default "50" - force-flush threshold
HTTP surface:
POST / - Grafana webhook entry
POST /flush - manual digest flush (idempotent)
GET / - status + config + buffer depth + stats
"""HTTP->IRC alert relay with thermal printer forwarding for Grafana webhooks.
Listens on :9119, posts to #alerts on UnrealIRCd via raw IRC protocol.
Alerts tagged alert_channel=thermal_print also POST to Print.Web /api/print/alert.
"""
import json, os, socket, sys, threading, time
from collections import defaultdict
from datetime import datetime, timezone
import json, socket, sys, time
from http.server import HTTPServer, BaseHTTPRequestHandler
from urllib.request import Request, urlopen
from urllib.error import URLError
THERMAL_PRINT_ENABLED = os.environ.get("THERMAL_PRINT_ENABLED", "true").lower() == "true"
BATCH_INTERVAL_MIN = int(os.environ.get("BATCH_INTERVAL_MIN", "60"))
BATCH_MAX_PENDING = int(os.environ.get("BATCH_MAX_PENDING", "50"))
IRC_HOST = os.environ.get("IRC_HOST", "unrealircd.irc.svc")
IRC_PORT = int(os.environ.get("IRC_PORT", "6667"))
IRC_NICK = os.environ.get("IRC_NICK", "grafana-bot")
IRC_CHANNEL = os.environ.get("IRC_CHANNEL", "#alerts")
PRINT_WEB_URL = os.environ.get("PRINT_WEB_URL", "http://10.0.57.16:5200/api/print/alert")
_buffer_lock = threading.Lock()
_buffer = {} # fingerprint -> {"alert": dict, "first_seen": float, "last_seen": float}
_last_flush_time = time.time()
_stats = {"webhooks_received": 0, "irc_sent": 0, "print_immediate": 0,
"digest_flushed": 0, "buffer_dedup": 0, "buffer_added": 0,
"buffer_resolved": 0, "started_at": time.time()}
IRC_HOST = "unrealircd.irc.svc" # short name: CoreDNS ndots:5 + iamworkin.lan template hijacks full .cluster.local (see memory)
IRC_PORT = 6667
IRC_NICK = "grafana-bot"
IRC_CHANNEL = "#alerts"
PRINT_WEB_URL = "http://10.0.57.16:5200/api/print/alert"
PRINT_ENABLED = True
def send_irc(message):
"""Connect, handle PING, join, send, quit."""
try:
sock = socket.create_connection((IRC_HOST, IRC_PORT), timeout=15)
sock.sendall(f"NICK {IRC_NICK}\r\n".encode())
@@ -1371,137 +1323,52 @@ data:
time.sleep(0.5)
sock.sendall(b"QUIT :alert delivered\r\n")
sock.close()
_stats["irc_sent"] += 1
return True
except Exception as e:
print(f"[irc-notify] IRC send failed: {e}", file=sys.stderr)
return False
def post_thermal(payload, kind):
if not THERMAL_PRINT_ENABLED:
print(f"[irc-notify] thermal disabled; skip {kind} ({payload.get('title','?')[:40]})", file=sys.stderr)
return False
def send_thermal_print(alert):
if not PRINT_ENABLED: return
labels = alert.get("labels", {})
annotations = alert.get("annotations", {})
status = alert.get("status", "firing").upper()
summary = annotations.get("summary", "")
description = annotations.get("description", "")
runbook = annotations.get("runbook", "")
# Build a useful message: summary + description + runbook steps
parts = []
if summary: parts.append(summary)
if description and description != summary: parts.append(description)
if runbook: parts.append("STEPS: " + runbook)
message = " | ".join(parts) if parts else labels.get("alertname", "Unknown alert")
payload = {
"title": labels.get("alertname", "Unknown"),
"severity": labels.get("severity", "warning").capitalize(),
"host": labels.get("instance", labels.get("host", "unknown")),
"message": message,
"eventId": alert.get("fingerprint", ""),
"source": "Grafana",
"status": "RESOLVED" if status == "RESOLVED" else "PROBLEM",
"acknowledged": False
}
try:
req = Request(PRINT_WEB_URL, data=json.dumps(payload).encode("utf-8"),
headers={"Content-Type": "application/json"}, method="POST")
resp = urlopen(req, timeout=10)
if kind == "immediate": _stats["print_immediate"] += 1
print(f"[irc-notify] thermal {kind} sent: {payload.get('title','?')[:50]}", file=sys.stderr)
return True
print(f"[irc-notify] Thermal print sent: {resp.read().decode()}", file=sys.stderr)
except Exception as e:
print(f"[irc-notify] thermal {kind} failed: {e}", file=sys.stderr)
return False
print(f"[irc-notify] Thermal print failed: {e}", file=sys.stderr)
def fingerprint_of(alert):
fp = alert.get("fingerprint", "")
if fp: return fp
def should_print(alert):
labels = alert.get("labels", {})
target = labels.get("pod") or labels.get("instance") or labels.get("deployment") or labels.get("statefulset") or labels.get("namespace") or ""
return f"{labels.get('alertname','?')}/{labels.get('namespace','')}/{target}"
def is_critical(alert):
return alert.get("labels", {}).get("severity", "").lower() in ("critical", "disaster", "page")
def is_immediate_label(alert):
return alert.get("labels", {}).get("alert_channel") == "thermal_print_immediate"
def is_batched_label(alert):
return alert.get("labels", {}).get("alert_channel") == "thermal_print"
def add_to_digest(alert):
"""Add an alert to the digest buffer. Returns True if the buffer GREW
(new fingerprint), False if it was a dedup, resolution, or no-op.
"""
if not THERMAL_PRINT_ENABLED: return False
fp = fingerprint_of(alert)
status = alert.get("status", "firing").lower()
with _buffer_lock:
if status == "resolved":
if fp in _buffer:
del _buffer[fp]
_stats["buffer_resolved"] += 1
return False
if fp in _buffer:
_buffer[fp]["last_seen"] = time.time()
_buffer[fp]["alert"] = alert
_stats["buffer_dedup"] += 1
return False
_buffer[fp] = {"alert": alert, "first_seen": time.time(), "last_seen": time.time()}
_stats["buffer_added"] += 1
return True
def build_digest_payload():
with _buffer_lock:
items = list(_buffer.values())
if not items: return None
by_name = defaultdict(list)
for item in items:
labels = item["alert"].get("labels", {})
by_name[labels.get("alertname", "Unknown")].append(item)
lines = []
for name, group in sorted(by_name.items()):
targets = []
for it in group[:5]:
labels = it["alert"].get("labels", {})
t = (labels.get("pod") or labels.get("instance") or labels.get("deployment")
or labels.get("statefulset") or labels.get("namespace") or "?")
targets.append(t)
more = f" (+{len(group)-5})" if len(group) > 5 else ""
sevs = sorted({it["alert"].get("labels", {}).get("severity", "warning") for it in group})
lines.append(f"[{'/'.join(sevs)}] {name} x{len(group)}: {', '.join(targets)}{more}")
now = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M UTC")
title = f"Alert digest: {len(items)} firing"
body = "\n".join([
f"=== {title} ===",
f"as of {now}",
"",
*lines,
"",
"Stream: #alerts (IRC) | Triage: grafana-noc1.iamworkin.lan",
"Force-flush: POST irc-notify.monitoring.svc:9119/flush",
])
return {"title": title, "severity": "Warning", "host": "monitoring",
"message": body, "eventId": f"digest-{int(time.time())}",
"source": "Grafana digest", "status": "PROBLEM", "acknowledged": False}
def flush_digest():
payload = build_digest_payload()
if payload is None:
print("[irc-notify] flush: buffer empty, no digest sent", file=sys.stderr)
return False
sent = post_thermal(payload, "digest")
with _buffer_lock:
_buffer.clear()
if sent: _stats["digest_flushed"] += 1
return sent
def digest_loop():
global _last_flush_time
while True:
try:
now = time.time()
elapsed = now - _last_flush_time
if elapsed >= BATCH_INTERVAL_MIN * 60:
print(f"[irc-notify] digest tick: interval reached ({BATCH_INTERVAL_MIN}m); buffer={len(_buffer)}", file=sys.stderr)
flush_digest()
_last_flush_time = now
elif len(_buffer) >= BATCH_MAX_PENDING:
print(f"[irc-notify] digest tick: buffer full ({len(_buffer)}); force flush", file=sys.stderr)
flush_digest()
_last_flush_time = now
time.sleep(15)
except Exception as e:
print(f"[irc-notify] digest loop error: {e}", file=sys.stderr)
time.sleep(60)
if labels.get("alert_channel") == "thermal_print": return True
if labels.get("severity", "").lower() in ("critical", "disaster"): return True
if alert.get("status", "").upper() == "RESOLVED": return False
return False
class Handler(BaseHTTPRequestHandler):
def do_POST(self):
if self.path == "/flush":
ok = flush_digest()
self.send_response(200); self.send_header("Content-Type", "application/json"); self.end_headers()
self.wfile.write(json.dumps({"flushed": ok, "buffer_after": len(_buffer)}).encode())
return
_stats["webhooks_received"] += 1
length = int(self.headers.get("Content-Length", 0))
body = json.loads(self.rfile.read(length)) if length else {}
for alert in body.get("alerts", []):
@@ -1516,56 +1383,22 @@ data:
msg = f"{icon}{sev_tag} {name}: {summary}"
if desc: msg += f"\n {desc}"
send_irc(msg)
# Thermal routing — EVERYTHING (including criticals) goes into
# the hourly digest. Only the explicit `alert_channel=thermal_print_immediate`
# label bypasses, and even that flushes-the-current-digest rather
# than printing a standalone job, so the same fingerprint can't
# spam the printer per webhook cycle.
if status == "RESOLVED":
add_to_digest(alert) # removes from buffer
continue
if is_immediate_label(alert):
# Explicit opt-in for "paper this NOW" — first arrival of a
# new fingerprint triggers an immediate digest flush; repeat
# webhooks for the same fingerprint dedupe in the buffer
# until the next interval or until the alert resolves.
new_in_buffer = add_to_digest(alert)
if new_in_buffer:
global _last_flush_time
flush_digest()
_last_flush_time = time.time()
elif is_critical(alert) or is_batched_label(alert):
add_to_digest(alert)
# else: IRC-only (warnings without thermal_print label)
self.send_response(200); self.send_header("Content-Type", "application/json"); self.end_headers()
if should_print(alert): send_thermal_print(alert)
self.send_response(200)
self.send_header("Content-Type", "application/json")
self.end_headers()
self.wfile.write(b'{"status":"ok"}')
def do_GET(self):
self.send_response(200); self.send_header("Content-Type", "application/json"); self.end_headers()
with _buffer_lock:
alertnames = sorted({it["alert"].get("labels", {}).get("alertname", "?") for it in _buffer.values()})
depth = len(_buffer)
info = {
"service": "irc-notify",
"config": {"thermal_print_enabled": THERMAL_PRINT_ENABLED,
"batch_interval_min": BATCH_INTERVAL_MIN,
"batch_max_pending": BATCH_MAX_PENDING,
"irc_target": f"{IRC_HOST}:{IRC_PORT} {IRC_CHANNEL}",
"print_web_url": PRINT_WEB_URL},
"buffer": {"depth": depth, "alertnames": alertnames,
"seconds_since_last_flush": int(time.time() - _last_flush_time),
"seconds_until_next_flush": max(0, int(BATCH_INTERVAL_MIN*60 - (time.time() - _last_flush_time)))},
"stats": _stats,
}
self.wfile.write(json.dumps(info, indent=2).encode())
self.send_response(200)
self.send_header("Content-Type", "application/json")
self.end_headers()
self.wfile.write(json.dumps({"service":"irc-notify","thermal_print":PRINT_ENABLED}).encode())
def log_message(self, format, *args):
print(f"[irc-notify] {args[0]}", file=sys.stderr)
if __name__ == "__main__":
threading.Thread(target=digest_loop, daemon=True).start()
server = HTTPServer(("0.0.0.0", 9119), Handler)
print(f"[irc-notify] :9119 -> IRC {IRC_HOST}:{IRC_PORT} {IRC_CHANNEL} | thermal={'ON' if THERMAL_PRINT_ENABLED else 'OFF'} | digest={BATCH_INTERVAL_MIN}m max={BATCH_MAX_PENDING}", file=sys.stderr)
print(f"IRC alert relay :9119 -> {IRC_HOST}:{IRC_PORT} {IRC_CHANNEL} (thermal: {PRINT_ENABLED})")
server.serve_forever()
# =============================================================================
@@ -3676,7 +3509,7 @@ data:
- refId: A
relativeTimeRange: {from: 300, to: 0}
datasourceUid: prometheus
model: {expr: 'kube_deployment_status_replicas_ready{namespace="github-runner",deployment=~"github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"} == 0', instant: true, refId: A}
model: {expr: 'kube_deployment_status_replicas_ready{namespace="github-runner",deployment=~"github-runner(|-.+)"} == 0', instant: true, refId: A}
- refId: B
relativeTimeRange: {from: 300, to: 0}
datasourceUid: __expr__

View File

@@ -24,16 +24,7 @@
# (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.
# telephony / gitea / fc-system / fc-signage namespaces on 4444.
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
@@ -212,13 +203,6 @@ spec:
ports:
- port: 4444
protocol: TCP
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: github-runner
ports:
- port: 4444
protocol: TCP
podSelector: {}
policyTypes:
- Ingress

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

@@ -1,206 +0,0 @@
using FluentAssertions;
using Xunit;
namespace BluejayInfraLint.Tests;
[Trait("Category", "Unit")]
public sealed class DivoomPiDeployArtifactTests
{
private static readonly string Root = FindRepoRoot();
private static readonly string DmRoot = Path.Combine(Root, "apps", "fc-divoom-dm-pi-device");
private static readonly string TvRoot = Path.Combine(Root, "apps", "fc-divoom-tv-pi");
public static TheoryData<string> DmRequiredArtifacts => new()
{
"README.md",
"hiera/edge2-divoom-dm-device.overlay.yaml",
"puppet/profile/pi/service/divoom_dm_device.pp",
"puppet/templates/divoom-device-registration.json.epp",
"puppet/templates/flowercore-divoom-dm-agent.service.epp",
};
public static TheoryData<string> TvRequiredArtifacts => new()
{
"README.md",
"hiera/example-divoom-tv-pi.iamworkin.lan.yaml",
"puppet/profile/pi/service/divoom_tv.pp",
"systemd/flowercore-divoom-tv.service",
"systemd/flowercore-divoom-tv-hdmi.service",
"systemd/99-flowercore-divoom-tv-hdmi.rules",
"scripts/flowercore-divoom-tv-prelaunch.sh",
"scripts/flowercore-divoom-tv-launch.sh",
"scripts/flowercore-divoom-tv-hdmi-respond.sh",
};
[Theory]
[MemberData(nameof(DmRequiredArtifacts))]
public void DmDeviceArtifacts_ArePresent(string relativePath)
{
File.Exists(Path.Combine(DmRoot, relativePath.Replace('/', Path.DirectorySeparatorChar))).Should().BeTrue(relativePath);
}
[Theory]
[MemberData(nameof(TvRequiredArtifacts))]
public void TvPiArtifacts_ArePresent(string relativePath)
{
File.Exists(Path.Combine(TvRoot, relativePath.Replace('/', Path.DirectorySeparatorChar))).Should().BeTrue(relativePath);
}
[Fact]
public void DmDeviceReadme_DeclaresPuppetSystemdNotKubernetes()
{
var readme = ReadDm("README.md");
readme.Should().Contain("not a Kubernetes application");
readme.Should().Contain("profile::pi::service::divoom");
readme.Should().Contain("no K8s surface");
}
[Fact]
public void DmHieraOverlay_PreservesExistingEdge2DivoomService()
{
var hiera = ReadDm("hiera/edge2-divoom-dm-device.overlay.yaml");
hiera.Should().Contain("fc-pimanager:");
hiera.Should().Contain("fc-divoom:");
hiera.Should().Contain("enabled: true");
hiera.Should().Contain("profile::pi::service::divoom_dm_device::service_enabled: false");
hiera.Should().Contain("profile::pi::service::divoom_dm_device::service_ensure: 'stopped'");
}
[Fact]
public void DmPuppetProfile_DefaultsToStoppedDisabledService()
{
var profile = ReadDm("puppet/profile/pi/service/divoom_dm_device.pp");
profile.Should().Contain("Boolean $service_enabled = false");
profile.Should().Contain("Enum['running', 'stopped'] $service_ensure = 'stopped'");
profile.Should().Contain("service { $service_name:");
profile.Should().Contain("ensure => $service_ensure");
profile.Should().Contain("enable => $service_enabled");
}
[Fact]
public void DmPuppetProfile_DoesNotManageLiveDivoomWebUnit()
{
var profile = ReadDm("puppet/profile/pi/service/divoom_dm_device.pp");
profile.Should().NotContain("Service['flowercore-divoom.service']");
profile.Should().NotContain("service { 'flowercore-divoom.service'");
profile.Should().NotContain("notify => Service");
}
[Fact]
public void DmAgentUnit_IsSeparateAndGatedByExistingWrappers()
{
var unit = ReadDm("puppet/templates/flowercore-divoom-dm-agent.service.epp");
unit.Should().Contain("ConditionPathExists=<%= $divoom_install_dir %>/bt-link.sh");
unit.Should().Contain("ConditionPathExists=<%= $divoom_install_dir %>/bt-reset.sh");
unit.Should().Contain("ConditionPathExists=<%= $divoom_install_dir %>/audio-link.sh");
unit.Should().Contain("ExecStart=<%= $agent_binary_path %> --mode=Pi");
unit.Should().NotContain("flowercore-divoom.service");
}
[Fact]
public void DmRegistration_CarriesRenderProofAndSafetyPolicy()
{
var registration = ReadDm("puppet/templates/divoom-device-registration.json.epp");
registration.Should().Contain("\"candidateChannels\": <%= $bt_channels_json %>");
registration.Should().Contain("\"deviceInfoIsRenderProof\": false");
registration.Should().Contain("\"visibleRenderProofRequired\": <%= $visible_render_proof_required %>");
registration.Should().Contain("\"preserveExistingService\": \"flowercore-divoom.service\"");
registration.Should().Contain("\"doNotEnableFmRadio\": true");
}
[Fact]
public void TvService_UsesAvaloniaHdmiSafetyGates()
{
var unit = ReadTv("systemd/flowercore-divoom-tv.service");
unit.Should().Contain("ConditionPathExists=/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv");
unit.Should().Contain("Environment=XDG_RUNTIME_DIR=/run/fc-divoom-tv");
unit.Should().Contain("RuntimeDirectoryMode=0700");
unit.Should().Contain("ExecStartPre=/usr/local/bin/flowercore-divoom-tv-prelaunch.sh");
unit.Should().Contain("ExecStart=/usr/local/bin/flowercore-divoom-tv-launch.sh");
unit.Should().Contain("MemoryMax=2G");
unit.Should().Contain("PrivateTmp=true");
unit.Should().NotContain("/tmp");
}
[Fact]
public void TvLauncher_PrefersCageAndFallsBackToDirectLaunch()
{
var script = ReadTv("scripts/flowercore-divoom-tv-launch.sh");
script.Should().Contain("command -v cage");
script.Should().Contain("exec cage --");
script.Should().Contain("launching FlowerCore.Divoom.Tv directly");
script.Should().Contain("--target=hdmi");
script.Should().Contain("--presentation-mode=${PRESENTATION_MODE}");
}
[Fact]
public void TvHotplugRule_SettlesAndRestartsRenderer()
{
var rule = ReadTv("systemd/99-flowercore-divoom-tv-hdmi.rules");
var responder = ReadTv("scripts/flowercore-divoom-tv-hdmi-respond.sh");
rule.Should().Contain("KERNEL==\"card?-HDMI-A-?\"");
rule.Should().Contain("start flowercore-divoom-tv-hdmi.service");
responder.Should().Contain("sleep 2");
responder.Should().Contain("systemctl restart flowercore-divoom-tv.service");
}
[Fact]
public void TvPuppetProfile_InstallsCageAndStaticArtifacts()
{
var profile = ReadTv("puppet/profile/pi/service/divoom_tv.pp");
profile.Should().Contain("package { ['cage', 'libgbm1', 'libdrm2', 'libxkbcommon0', 'fonts-dejavu-core']");
profile.Should().Contain("'profile/pi/fc_divoom_tv/flowercore-divoom-tv.service'");
profile.Should().Contain("'profile/pi/fc_divoom_tv/flowercore-divoom-tv-launch.sh'");
profile.Should().Contain("profile/pi/fc_divoom_tv/99-flowercore-divoom-tv-hdmi.rules");
profile.Should().Contain("Boolean $service_enabled = false");
}
[Fact]
public void DivoomArtifacts_DoNotAddKubernetesWorkloads()
{
var allText = Directory.GetFiles(DmRoot, "*", SearchOption.AllDirectories)
.Concat(Directory.GetFiles(TvRoot, "*", SearchOption.AllDirectories))
.Select(File.ReadAllText);
foreach (var text in allText)
{
text.Should().NotContain("kind: Deployment");
text.Should().NotContain("kind: IngressRoute");
text.Should().NotContain("kind: Certificate");
text.Should().NotContain("kind: OnePasswordItem");
}
}
private static string ReadDm(string relativePath)
=> File.ReadAllText(Path.Combine(DmRoot, relativePath.Replace('/', Path.DirectorySeparatorChar)));
private static string ReadTv(string relativePath)
=> File.ReadAllText(Path.Combine(TvRoot, 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

@@ -67,7 +67,8 @@ public sealed class FleetManifestLintTests
["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",
["github-runner-devicemgmt"] = "https://github.com/astoltz/FlowerCore.DeviceManagement",
["github-runner-worldbuilder"] = "https://github.com/astoltz/FlowerCore.WorldBuilder",
};
private static readonly HashSet<string> ScaledLinuxRunnerDeployments = new(StringComparer.Ordinal)
@@ -81,7 +82,8 @@ public sealed class FleetManifestLintTests
"github-runner-chat",
"github-runner-mysql",
"github-runner-kiosk-linux",
"github-runner-updater",
"github-runner-devicemgmt",
"github-runner-worldbuilder",
};
private static readonly IReadOnlyDictionary<string, string> WritableRunnerEnv = new Dictionary<string, string>(StringComparer.Ordinal)
@@ -236,7 +238,7 @@ public sealed class FleetManifestLintTests
{
deployments.Should().ContainKey(expectedRunner.Key);
var container = deployments[expectedRunner.Key].MainContainerMappings().Should().ContainSingle().Subject;
var container = RunnerContainer(deployments[expectedRunner.Key]);
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");
@@ -252,7 +254,7 @@ public sealed class FleetManifestLintTests
{
foreach (var deployment in GitHubRunnerDeployments().Values)
{
var container = deployment.MainContainerMappings().Should().ContainSingle().Subject;
var container = RunnerContainer(deployment);
foreach (var expectedEnv in WritableRunnerEnv)
{
@@ -279,10 +281,7 @@ public sealed class FleetManifestLintTests
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");
ReplicaCount(deployment).Should().Be(2);
var volumes = deployment.MappingSequence("spec", "template", "spec", "volumes");
var claimNames = volumes
@@ -308,108 +307,6 @@ public sealed class FleetManifestLintTests
.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()
{
@@ -418,88 +315,12 @@ public sealed class FleetManifestLintTests
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("github-runner(|-.+)");
monitoring.Should().Contain("folder: CI Alerts");
monitoring.Should().Contain("uid: linux-runner-offline");
monitoring.Should().Contain("alert_channel: irc");
}
[Fact]
public void Monitoring_GenericKubernetesAlerts_MustExcludeEphemeralGithubRunnerNamespace()
{
var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
monitoring.Should().Contain("kube_pod_container_status_restarts_total{namespace!=\"github-runner\"}");
monitoring.Should().Contain("and on(namespace, pod) kube_pod_info");
monitoring.Should().Contain("kube_deployment_spec_replicas{namespace!=\"github-runner\"} != kube_deployment_status_replicas_available{namespace!=\"github-runner\"}");
monitoring.Should().Contain("dedicated LinuxRunnerOffline/MacMiniRunnerOffline alerts");
}
[Fact]
public void Monitoring_BlackboxTargetsForOidcSensitiveServices_MustUseAnonymousHealthRoutesWhenAvailable()
{
var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
monitoring.Should().Contain("https://chat.iamworkin.lan/healthz");
monitoring.Should().Contain("https://dist.iamworkin.lan/healthz");
monitoring.Should().Contain("https://dms.iamworkin.lan/healthz");
monitoring.Should().Contain("https://print.iamworkin.lan/healthz");
monitoring.Should().Contain("https://knowledge.iamworkin.lan/healthz");
monitoring.Should().Contain("https://library.iamworkin.lan/health");
monitoring.Should().Contain("https://aistation.iamworkin.lan/healthz");
monitoring.Should().NotContain("https://print.iamworkin.lan/\"");
}
[Fact]
public void OidcEnforcedDeployments_WithHttpHealthzProbes_MustDeclareAnonymousHealthzContract()
{
var violations = Inventory.Documents
.Where(document => document.Kind == "Deployment")
.SelectMany(document => document.MainContainerMappings()
.Where(container => string.Equals(EnvValue(container, "FlowerCore__Auth__Enabled"), "true", StringComparison.OrdinalIgnoreCase))
.Where(container => string.Equals(EnvValue(container, "FlowerCore__Auth__Oidc__Enabled"), "true", StringComparison.OrdinalIgnoreCase))
.Where(container => ProbeHttpGetPath(container, "readinessProbe") == "/healthz"
|| ProbeHttpGetPath(container, "startupProbe") == "/healthz")
.Where(_ => !string.Equals(
PodAnnotation(document, "flowercore.io/healthz-auth-policy"),
"allow-anonymous",
StringComparison.Ordinal))
.Select(container =>
{
var containerName = ManifestNodeExtensions.Scalar(container, "name") ?? "<unnamed>";
return $"{document.Descriptor} container '{containerName}' enforces OIDC while probing /healthz but lacks flowercore.io/healthz-auth-policy: allow-anonymous.";
}))
.ToList();
violations.Should().BeEmpty();
}
[Fact]
public void Knowledge_OidcEnforcement_MustKeepHealthzAnonymousContractVisibleInManifest()
{
var knowledge = Inventory.Documents
.Single(document => document.Kind == "Deployment" && document.Namespace == "knowledge" && document.Name == "knowledge-web");
var container = knowledge.MainContainerMappings().Should().ContainSingle().Subject;
EnvValue(container, "FlowerCore__Auth__Enabled").Should().Be("true");
EnvValue(container, "FlowerCore__Auth__Oidc__Enabled").Should().Be("true");
ProbeHttpGetPath(container, "readinessProbe").Should().Be("/healthz");
PodAnnotation(knowledge, "flowercore.io/healthz-auth-policy").Should().Be("allow-anonymous");
}
[Fact]
public void Distribution_OidcEnforcement_MustStayOffUntilHealthzAllowAnonymousProofLands()
{
var distribution = Inventory.Documents
.Single(document => document.Kind == "Deployment" && document.Namespace == "fc-distribution" && document.Name == "fc-distribution");
var container = distribution.MainContainerMappings().Should().ContainSingle().Subject;
EnvValue(container, "FlowerCore__Auth__Oidc__Enabled").Should().Be("true");
EnvValue(container, "FlowerCore__Auth__Enabled").Should().Be("false");
ProbeHttpGetPath(container, "readinessProbe").Should().Be("/healthz");
PodAnnotation(distribution, "flowercore.io/healthz-auth-policy").Should().NotBe("allow-anonymous");
}
[Fact]
public void StatefulSets_WithVolumeClaimTemplates_MustDeclareFilesystemDefaults()
{
@@ -824,6 +645,15 @@ public sealed class FleetManifestLintTests
return EnvMapping(container, name) is { } env ? ManifestNodeExtensions.Scalar(env, "value") : null;
}
private static YamlMappingNode RunnerContainer(ManifestDocument deployment)
{
return deployment.ContainerMappings()
.Where(container => string.Equals(ManifestNodeExtensions.Scalar(container, "name"), "runner", StringComparison.Ordinal))
.Should()
.ContainSingle($"{deployment.Name} must keep exactly one main runner container")
.Subject;
}
private static string? EnvSecretName(YamlMappingNode container, string name)
{
return EnvMapping(container, name) is { } env
@@ -844,19 +674,6 @@ public sealed class FleetManifestLintTests
.SingleOrDefault(env => string.Equals(ManifestNodeExtensions.Scalar(env, "name"), name, StringComparison.Ordinal));
}
private static string? PodAnnotation(ManifestDocument document, string name)
{
return document.Scalar("spec", "template", "metadata", "annotations", name);
}
private static string? ProbeHttpGetPath(YamlMappingNode container, string probeKey)
{
return ManifestNodeExtensions.TryGetMapping(container, probeKey, out var probe)
&& ManifestNodeExtensions.TryGetMapping(probe, "httpGet", out var httpGet)
? ManifestNodeExtensions.Scalar(httpGet, "path")
: null;
}
private static IReadOnlyList<ManifestDocument> FcDeviceManagementDocuments()
{
return Inventory.Documents
@@ -1086,22 +903,6 @@ internal sealed record ManifestDocument(
.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()
{
return ContainerMappings()