Compare commits

...

12 Commits

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

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

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

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

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

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

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

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 10:27:58 -05:00
20 changed files with 1369 additions and 15 deletions

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -1,3 +1,2 @@
# Restart kiosk and redeclare capabilities when HDMI connect/disconnect changes DRM state. # Settle DRM for 2s before restarting Chromium, then redeclare capabilities.
SUBSYSTEM=="drm", KERNEL=="card?-HDMI-A-?", ACTION=="change", RUN+="/usr/bin/systemctl restart flowercore-signage-player-pi.service" SUBSYSTEM=="drm", KERNEL=="card?-HDMI-A-?", ACTION=="change", RUN+="/usr/bin/systemctl start flowercore-signage-player-pi-hdmi.service"
SUBSYSTEM=="drm", KERNEL=="card?-HDMI-A-?", ACTION=="change", RUN+="/usr/bin/systemctl start flowercore-signage-detect-display.service"

View File

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

View File

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

View File

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

View File

@@ -18,12 +18,12 @@
# simultaneous runner pods; single-replica constraint below). # simultaneous runner pods; single-replica constraint below).
# #
# Credentials: # Credentials:
# OnePasswordItem "GitHub Runner Registration Token" → Secret # OnePasswordItem "GitHub PAT (Runner Registration)" → Secret
# github-runner-token with field "credential" used as RUNNER_TOKEN. # github-runner-token with field "credential" used as RUNNER_TOKEN.
# Operator must create/rotate the 1P item manually; registration tokens # Operator must create/rotate the 1P item manually; registration tokens
# expire after 1h — use a fine-grained PAT with admin:org_hook scope # expire after 1h — use a fine-grained PAT with Administration:read/write
# or a re-registration script. See docs/infrastructure/ # scope on the target repos, or a re-registration script. See
# self-hosted-runner-fleet.md §Security. # docs/infrastructure/self-hosted-runner-fleet.md §Security.
# #
# Security model: # Security model:
# - No ClusterRole / ClusterRoleBinding — runner has no K8s API access. # - No ClusterRole / ClusterRoleBinding — runner has no K8s API access.
@@ -52,8 +52,10 @@ metadata:
--- ---
# 1Password secret sync — creates github-runner-token K8s Secret. # 1Password secret sync — creates github-runner-token K8s Secret.
# Fields expected in the 1Password item: # Fields expected in the 1Password item:
# credential — GitHub runner registration token (or PAT for re-reg script) # credential — GitHub fine-grained PAT (Administration:read/write on
# Item path: IAmWorkin vault > "GitHub Runner Registration Token" # target repos) used by the runner image to mint a fresh
# short-lived registration token at pod start.
# Item path: IAmWorkin vault > "GitHub PAT (Runner Registration)"
# Operator MUST create this item before the Deployment will start cleanly. # Operator MUST create this item before the Deployment will start cleanly.
apiVersion: onepassword.com/v1 apiVersion: onepassword.com/v1
kind: OnePasswordItem kind: OnePasswordItem
@@ -64,7 +66,7 @@ metadata:
app.kubernetes.io/component: credentials app.kubernetes.io/component: credentials
app.kubernetes.io/part-of: flowercore app.kubernetes.io/part-of: flowercore
spec: spec:
itemPath: vaults/IAmWorkin/items/GitHub Runner Registration Token itemPath: vaults/IAmWorkin/items/GitHub PAT (Runner Registration)
--- ---
apiVersion: v1 apiVersion: v1
kind: PersistentVolumeClaim kind: PersistentVolumeClaim
@@ -111,7 +113,11 @@ spec:
# one pod at a time. Each pod re-registers as an ephemeral runner after # one pod at a time. Each pod re-registers as an ephemeral runner after
# completing a job (EPHEMERAL=true restarts the container, not the pod, # completing a job (EPHEMERAL=true restarts the container, not the pod,
# so the PVC stays attached between jobs). # so the PVC stays attached between jobs).
replicas: 0 #
# 2026-05-16: bumped 0 -> 1 after operator provisioned the
# "GitHub PAT (Runner Registration)" 1P item with field=credential.
# Unblocks CI fleet-wide (was budget-exhausted on GH-hosted runners).
replicas: 1
selector: selector:
matchLabels: matchLabels:
app.kubernetes.io/name: github-runner app.kubernetes.io/name: github-runner
@@ -135,6 +141,32 @@ spec:
runAsUser: 1001 runAsUser: 1001
runAsGroup: 1001 runAsGroup: 1001
fsGroup: 1001 fsGroup: 1001
# Sprint 30 Cl-1 pod-env fix (2026-05-21): pre-create + chown
# /home/runner/.dotnet + /home/runner/.nuget so the non-root runner
# (UID 1001) can host setup-dotnet@v4 + dotnet restore writes without
# the per-workflow DOTNET_INSTALL_DIR patch ~25 flipped Linux repos
# have been carrying. Runs as root so chown succeeds; the main
# container then runs as 1001 against an emptyDir mounted at
# /home/runner. The PVC mount at /home/runner/.nuget/packages
# (Common runner) still wins at its nested path because Kubernetes
# honors the deeper mount.
initContainers:
- name: setup-runner-home
image: busybox:1.36
command:
- sh
- -c
- |
set -e
mkdir -p /home/runner/.dotnet /home/runner/.nuget/packages /home/runner/.nuget/NuGet
chown -R 1001:1001 /home/runner/.dotnet /home/runner/.nuget
chmod -R 755 /home/runner/.dotnet /home/runner/.nuget
securityContext:
runAsUser: 0
runAsNonRoot: false
volumeMounts:
- name: runner-home
mountPath: /home/runner
containers: containers:
- name: runner - name: runner
image: myoung34/github-runner:latest image: myoung34/github-runner:latest
@@ -157,12 +189,40 @@ spec:
# Labels used by workflow files: runs-on: [self-hosted, linux, fc-build-linux] # Labels used by workflow files: runs-on: [self-hosted, linux, fc-build-linux]
- name: LABELS - name: LABELS
value: "self-hosted,linux,fc-build-linux" value: "self-hosted,linux,fc-build-linux"
# Registration token injected from 1Password via OnePasswordItem CRD. # PAT (not pre-minted registration token) — myoung34/github-runner
- name: RUNNER_TOKEN # mints registration tokens itself via GitHub API when ACCESS_TOKEN
# is set. Switched from RUNNER_TOKEN -> ACCESS_TOKEN on 2026-05-16
# because the 1P "GitHub PAT (Runner Registration)" item stores a
# fine-grained PAT, not a short-lived registration token.
- name: ACCESS_TOKEN
valueFrom: valueFrom:
secretKeyRef: secretKeyRef:
name: github-runner-token name: github-runner-token
key: credential key: credential
# myoung34/github-runner default entrypoint expects root for some
# setup steps. With securityContext.runAsUser=1001 the entrypoint
# short-circuits with "RUN_AS_ROOT env var is set to true but the
# user has been overridden and is not running as root". Tell the
# entrypoint we're explicitly NOT root so it skips the root-only
# setup steps (cache prewarm + apt updates — both already baked).
- name: RUN_AS_ROOT
value: "false"
# Sprint 30 Cl-1 pod-env fix (2026-05-21): retire the per-workflow
# DOTNET_INSTALL_DIR patch by setting it (+ siblings) here so ALL
# flipped Linux repos pick it up automatically. setup-dotnet@v4
# default writes to /usr/share/dotnet (root-only) or HOME-relative
# ~/.dotnet without HOME guard; pin both explicitly to the chowned
# emptyDir at /home/runner.
- name: DOTNET_INSTALL_DIR
value: "/home/runner/.dotnet"
- name: DOTNET_CLI_TELEMETRY_OPTOUT
value: "1"
- name: NUGET_PACKAGES
value: "/home/runner/.nuget/packages"
- name: DOTNET_NOLOGO
value: "1"
- name: DOTNET_GENERATE_ASPNET_CERTIFICATE
value: "false"
resources: resources:
requests: requests:
cpu: "500m" cpu: "500m"
@@ -171,6 +231,14 @@ spec:
cpu: "2000m" cpu: "2000m"
memory: "4Gi" memory: "4Gi"
volumeMounts: volumeMounts:
# /home/runner emptyDir — owned by the non-root runner thanks
# to the setup-runner-home initContainer chown. Hosts .dotnet
# (setup-dotnet@v4 target) and provides a writable HOME without
# forcing a PVC. The PVC mount below at .nuget/packages wins
# at that nested path (deeper mount overrides), so the Common
# NuGet cache continues to persist across ephemeral pod restarts.
- name: runner-home
mountPath: /home/runner
- name: nuget-cache - name: nuget-cache
mountPath: /home/runner/.nuget/packages mountPath: /home/runner/.nuget/packages
- name: tmp - name: tmp
@@ -186,6 +254,8 @@ spec:
periodSeconds: 30 periodSeconds: 30
failureThreshold: 3 failureThreshold: 3
volumes: volumes:
- name: runner-home
emptyDir: {}
- name: nuget-cache - name: nuget-cache
persistentVolumeClaim: persistentVolumeClaim:
claimName: github-runner-nuget-cache claimName: github-runner-nuget-cache
@@ -194,3 +264,135 @@ spec:
# Restart policy: Always — the Deployment controller handles # Restart policy: Always — the Deployment controller handles
# re-registration after each ephemeral job completes. # re-registration after each ephemeral job completes.
restartPolicy: Always restartPolicy: Always
---
# Shared.Pos repo-scoped Linux runner. Added 2026-05-20 to unstick the
# FlowerCore.Shared.Pos "Build, Test & Publish" workflow, which had been
# queued indefinitely after the Sprint 26 Mac POS Phase 1/2 PRs merged
# (no fc-build-linux runner was registered to Shared.Pos — GitHub user
# accounts have only repo-scoped runners). First concrete instance of the
# Sprint 29 Cx-1 Linux-runner-fleet pattern; the full per-repo fleet is
# codified by that lane. emptyDir nuget cache (no RWO PVC) so it shares no
# volume with the Common runner and needs no node pin.
apiVersion: apps/v1
kind: Deployment
metadata:
name: github-runner-sharedpos
namespace: github-runner
labels:
app.kubernetes.io/name: github-runner-sharedpos
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/created-by: argocd
spec:
# UN-PARKED 2026-05-21: Shared.Pos #5 fixed the non-root setup-dotnet path
# (DOTNET_INSTALL_DIR step-scoped). Re-enabled to run the now-fixable build.
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: github-runner-sharedpos
strategy:
type: Recreate
template:
metadata:
labels:
app.kubernetes.io/name: github-runner-sharedpos
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
flowercore.io/created-by: argocd
spec:
serviceAccountName: github-runner
securityContext:
runAsNonRoot: true
runAsUser: 1001
runAsGroup: 1001
fsGroup: 1001
# Sprint 30 Cl-1 pod-env fix (2026-05-21): see github-runner Deployment
# above for full rationale. Mirrored on the Shared.Pos runner so the
# per-workflow DOTNET_INSTALL_DIR patch can be retired fleet-wide
# rather than re-applied per repo as flipped lanes land.
initContainers:
- name: setup-runner-home
image: busybox:1.36
command:
- sh
- -c
- |
set -e
mkdir -p /home/runner/.dotnet /home/runner/.nuget/packages /home/runner/.nuget/NuGet
chown -R 1001:1001 /home/runner/.dotnet /home/runner/.nuget
chmod -R 755 /home/runner/.dotnet /home/runner/.nuget
securityContext:
runAsUser: 0
runAsNonRoot: false
volumeMounts:
- name: runner-home
mountPath: /home/runner
containers:
- name: runner
image: myoung34/github-runner:latest
imagePullPolicy: Always
env:
- name: REPO_URL
value: "https://github.com/astoltz/FlowerCore.Shared.Pos"
- name: RUNNER_NAME_PREFIX
value: "rke2-linux-sharedpos"
- name: RUNNER_WORKDIR
value: "/tmp/runner/work"
- name: EPHEMERAL
value: "true"
- name: LABELS
value: "self-hosted,linux,fc-build-linux"
- name: ACCESS_TOKEN
valueFrom:
secretKeyRef:
name: github-runner-token
key: credential
- name: RUN_AS_ROOT
value: "false"
# Sprint 30 Cl-1 pod-env fix (2026-05-21): retire per-workflow patch.
- name: DOTNET_INSTALL_DIR
value: "/home/runner/.dotnet"
- name: DOTNET_CLI_TELEMETRY_OPTOUT
value: "1"
- name: NUGET_PACKAGES
value: "/home/runner/.nuget/packages"
- name: DOTNET_NOLOGO
value: "1"
- name: DOTNET_GENERATE_ASPNET_CERTIFICATE
value: "false"
resources:
requests:
cpu: "500m"
memory: "1Gi"
limits:
cpu: "2000m"
memory: "4Gi"
volumeMounts:
# Shared.Pos runner uses emptyDir for nuget cache (no node pin
# via RWO PVC). /home/runner emptyDir hosts .dotnet via the
# setup-runner-home initContainer chown; the .nuget/packages
# emptyDir mount still wins at its nested path.
- name: runner-home
mountPath: /home/runner
- name: nuget-cache
mountPath: /home/runner/.nuget/packages
- name: tmp
mountPath: /tmp
livenessProbe:
exec:
command:
- /bin/sh
- -c
- "pgrep -f Runner.Listener > /dev/null"
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
volumes:
- name: runner-home
emptyDir: {}
- name: nuget-cache
emptyDir: {}
- name: tmp
emptyDir: {}
restartPolicy: Always

View File

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

View File

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

View File

@@ -174,10 +174,13 @@ public sealed class PiSignagePlayerArtifactTests
public void HdmiRule_RestartsPlayerAndRunsCapabilityDetection() public void HdmiRule_RestartsPlayerAndRunsCapabilityDetection()
{ {
var rule = Read("systemd/99-flowercore-signage-hdmi.rules"); var rule = Read("systemd/99-flowercore-signage-hdmi.rules");
var responder = Read("scripts/flowercore-signage-hdmi-respond.sh");
rule.Should().Contain("KERNEL==\"card?-HDMI-A-?\""); rule.Should().Contain("KERNEL==\"card?-HDMI-A-?\"");
rule.Should().Contain("restart flowercore-signage-player-pi.service"); rule.Should().Contain("start flowercore-signage-player-pi-hdmi.service");
rule.Should().Contain("start flowercore-signage-detect-display.service"); responder.Should().Contain("sleep 2");
responder.Should().Contain("start flowercore-signage-detect-display.service");
responder.Should().Contain("restart flowercore-signage-player-pi.service");
} }
[Fact] [Fact]