Compare commits

..

1 Commits

Author SHA1 Message Date
Codex
266b9cb8be feat(github-runner): add top Linux repo runners 2026-05-17 13:55:55 -05:00
29 changed files with 362 additions and 4904 deletions

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -1,109 +0,0 @@
# FlowerCore.DeviceManagement Operator.
#
# KubeOps controller for devices.flowercore.io resources. Operator-created
# children must set OwnerReferences + traceability labels/annotations per
# k8s-pod-ownership-and-traceability-standard.md. RBAC below grants
# apps/deployments/get so the process can resolve its own Deployment UID.
apiVersion: apps/v1
kind: Deployment
metadata:
name: fc-devicemgmt-operator
namespace: fc-devicemgmt
labels:
app: fc-devicemgmt-operator
app.kubernetes.io/name: fc-devicemgmt-operator
app.kubernetes.io/component: operator
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
flowercore.io/traceability-standard: k8s-pod-ownership-and-traceability-standard
spec:
replicas: 1
revisionHistoryLimit: 3
selector:
matchLabels:
app: fc-devicemgmt-operator
template:
metadata:
labels:
app: fc-devicemgmt-operator
app.kubernetes.io/name: fc-devicemgmt-operator
app.kubernetes.io/component: operator
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
prometheus.io/scrape: "true"
prometheus.io/port: "8080"
prometheus.io/path: "/metrics"
flowercore.io/audit-trace-id: "runtime-activity-trace"
spec:
serviceAccountName: fc-devicemgmt-operator
securityContext:
fsGroup: 1654
fsGroupChangePolicy: OnRootMismatch
containers:
- name: operator
image: localhost/fc-devicemgmt-operator:v20260519-sp34cl3-fix
imagePullPolicy: Never
ports:
- name: metrics
containerPort: 8080
env:
- name: ASPNETCORE_ENVIRONMENT
value: "Production"
- name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
value: "false"
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
- name: FLOWERCORE_KUBERNETES_OWNER_DEPLOYMENT
value: "fc-devicemgmt-operator"
- name: FlowerCore__Service__Name
value: "FlowerCore.DeviceManagement.Operator"
- name: FlowerCore__DeviceManagement__DefaultTenantId
value: "system"
resources:
requests:
cpu: 50m
memory: 128Mi
limits:
cpu: 500m
memory: 512Mi
readinessProbe:
tcpSocket:
port: 8080
initialDelaySeconds: 5
periodSeconds: 10
livenessProbe:
tcpSocket:
port: 8080
initialDelaySeconds: 20
periodSeconds: 30
securityContext:
runAsNonRoot: true
runAsUser: 1654
runAsGroup: 1654
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop:
- ALL
volumeMounts:
- name: tmp
mountPath: /tmp
- name: logs
mountPath: /app/logs
volumes:
- name: tmp
emptyDir: {}
- name: logs
emptyDir: {}

View File

@@ -1,151 +0,0 @@
# FlowerCore.DeviceManagement Web.
#
# Source repo is expected to ship FlowerCore.DeviceManagement.Web in a later
# Sprint 9+ lane. This manifest is static-valid without requiring the image to
# exist yet; import localhost/fc-devicemgmt-web:<tag> to all schedulable RKE2
# nodes before letting ArgoCD sync a live rollout.
#
# SCALED TO 0 — 2026-05-19 morning-routine cleanup.
# The Web pod cannot start until TWO upstream gaps close:
# 1. MySQL DB instance `flowercore_devicemgmt` (user `fc_devicemgmt`) is
# provisioned via fc-mysql Manager. The cluster currently has ZERO
# MySqlInstanceCrds and no `mysql.fc-mysql.svc:3306` Service, so the
# deployment-web container env `FlowerCore__Database__Host=mysql.fc-mysql.svc`
# points at nothing. Provision via the fc-mysql Manager UI/REST/MCP.
# 2. 1Password vault item `IAmWorkin/FlowerCore DeviceManagement Runtime`
# with 5 fields (DB-Password, mtls-ca.pem, mtls-client.crt, mtls-client.key,
# mtls-chain.pem) — see apps/fc-devicemgmt/1password-item.yaml. Mint mTLS
# from step-ca-agent ClusterIssuer per ADR-126; DB-Password must match the
# password configured for the MySQL user.
# Re-enable: change replicas back to 2 after both gaps close. The image tag
# in this file (v20260512-cx5) MAY also need a refresh — it predates the
# Sprint 34 Cl-3 operator fix; Web may have an analogous bug.
apiVersion: apps/v1
kind: Deployment
metadata:
name: fc-devicemgmt-web
namespace: fc-devicemgmt
labels:
app: fc-devicemgmt-web
app.kubernetes.io/name: fc-devicemgmt-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
flowercore.io/traceability-standard: k8s-pod-ownership-and-traceability-standard
spec:
replicas: 0
revisionHistoryLimit: 3
selector:
matchLabels:
app: fc-devicemgmt-web
template:
metadata:
labels:
app: fc-devicemgmt-web
app.kubernetes.io/name: fc-devicemgmt-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
prometheus.io/scrape: "true"
prometheus.io/port: "8080"
prometheus.io/path: "/metrics"
flowercore.io/audit-trace-id: "runtime-activity-trace"
spec:
securityContext:
fsGroup: 1654
fsGroupChangePolicy: OnRootMismatch
containers:
- name: web
image: localhost/fc-devicemgmt-web:v20260512-cx5
imagePullPolicy: Never
ports:
- name: http
containerPort: 8080
env:
- name: ASPNETCORE_URLS
value: "http://+:8080"
- name: ASPNETCORE_ENVIRONMENT
value: "Production"
- name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
value: "false"
- name: FlowerCore__Service__Name
value: "FlowerCore.DeviceManagement.Web"
- name: FlowerCore__DeviceManagement__DefaultTenantId
value: "system"
- name: FlowerCore__Database__Provider
value: "MySql"
- name: FlowerCore__Database__Host
value: "mysql.fc-mysql.svc"
- name: FlowerCore__Database__Database
value: "flowercore_devicemgmt"
- name: FlowerCore__Database__User
value: "fc_devicemgmt"
- name: FlowerCore__Database__Password
valueFrom:
secretKeyRef:
name: fc-devicemgmt-runtime
key: DB-Password
- name: FlowerCore__DeviceManagement__AgentMtls__CaPath
value: "/secrets/devicemgmt-mtls/mtls-ca.pem"
- name: FlowerCore__DeviceManagement__AgentMtls__ClientCertificatePath
value: "/secrets/devicemgmt-mtls/mtls-client.crt"
- name: FlowerCore__DeviceManagement__AgentMtls__ClientKeyPath
value: "/secrets/devicemgmt-mtls/mtls-client.key"
- name: FlowerCore__EventBus__Redis__Configuration
value: "redis.fc-redis.svc:6379"
resources:
requests:
cpu: 100m
memory: 256Mi
limits:
cpu: 1000m
memory: 768Mi
startupProbe:
tcpSocket:
port: 8080
initialDelaySeconds: 5
periodSeconds: 5
failureThreshold: 30
readinessProbe:
tcpSocket:
port: 8080
periodSeconds: 10
failureThreshold: 3
livenessProbe:
tcpSocket:
port: 8080
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
securityContext:
runAsNonRoot: true
runAsUser: 1654
runAsGroup: 1654
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop:
- ALL
volumeMounts:
- name: tmp
mountPath: /tmp
- name: logs
mountPath: /app/logs
- name: devicemgmt-mtls
mountPath: /secrets/devicemgmt-mtls
readOnly: true
volumes:
- name: tmp
emptyDir: {}
- name: logs
emptyDir: {}
- name: devicemgmt-mtls
secret:
secretName: fc-devicemgmt-runtime
defaultMode: 0400

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -532,7 +532,7 @@ spec:
fsGroupChangePolicy: OnRootMismatch fsGroupChangePolicy: OnRootMismatch
containers: containers:
- name: web - name: web
image: localhost/fc-ttsreader-web:v20260518-sprint36-demo-finish-b132cbf image: localhost/fc-ttsreader-web:v20260506-phase6
imagePullPolicy: Never imagePullPolicy: Never
ports: ports:
- containerPort: 5217 - containerPort: 5217
@@ -555,13 +555,9 @@ spec:
- name: TtsReader__Jobs__Root - name: TtsReader__Jobs__Root
value: "/data/jobs" value: "/data/jobs"
- name: TtsReader__Piper__Host - name: TtsReader__Piper__Host
value: "10.0.57.17" value: "ttsreader-piper.fc-ttsreader.svc.cluster.local."
- name: TtsReader__Piper__Port - name: TtsReader__Piper__Port
value: "8500" value: "10200"
- name: TtsReader__Piper__Transport
value: "http"
- name: TtsReader__Piper__HttpPath
value: "/tts"
- name: TtsReader__Kokoro__Enabled - name: TtsReader__Kokoro__Enabled
value: "true" value: "true"
- name: TtsReader__Kokoro__BaseUrl - name: TtsReader__Kokoro__BaseUrl

View File

@@ -1,76 +1,38 @@
# GitHub Runner Fleet # github-runner
ArgoCD owns `apps/github-runner/github-runner.yaml`. Do not patch live runner ArgoCD-managed repo-scoped Linux GitHub Actions runners for FlowerCore.
Deployments with `kubectl`; update this manifest and let ArgoCD reconcile.
## Runner Shape `astoltz` is a GitHub user account, not an organization, so each repository
needs its own runner registration. The existing Common runner remains
`Deployment/github-runner`; Sprint 29 adds one single-replica Deployment for
each top Linux-cost repo:
All repo-scoped Linux runners use: - `FlowerCore.Puppet`
- `FlowerCore.Signage`
- `FlowerCore.DMS`
- `FlowerCore.Telephony`
- `FlowerCore.Print.Web`
- `FlowerCore.Chat`
- `FlowerCore.MySQL`
- `FlowerCore.Kiosk.Linux`
- `ACCESS_TOKEN` from the `github-runner-token` Secret Each runner uses `myoung34/github-runner:latest`, `EPHEMERAL=true`, and labels
- `RUN_AS_ROOT=false` `self-hosted,linux,fc-build-linux`. The shared `github-runner-token` Secret is
- `EPHEMERAL=true` synced from the existing 1Password item `GitHub PAT (Runner Registration)` and
- `LABELS=self-hosted,linux,fc-build-linux` is consumed as `ACCESS_TOKEN`.
- writable non-root paths under `/home/runner` for .NET, NuGet, XDG cache, and
Actions tool cache
`github-runner` for `FlowerCore.Common` is single-replica because it retains the Do not `kubectl apply` this app over ArgoCD. Merge to `main`, let
original Longhorn ReadWriteOnce NuGet PVC. Every other repo-scoped runner uses `infra-github-runner` sync, then verify from `noc1`:
two replicas with per-pod `emptyDir` caches. That is the safe backlog-drain
strategy: no two pods share one RWO PVC.
Sprint 32 final long-tail wave adds 16 two-replica Deployments:
`FlowerCore.Knowledge`, `FlowerCore.LlmBridge`, `FlowerCore.Media`,
`FlowerCore.Presentations`, `FlowerCore.RemoteDesktop`, `FlowerCore.DNS`,
`FlowerCore.Distribution`, `FlowerCore.Scoreboard`,
`FlowerCore.SegmentDisplay`, `FlowerCore.Signage.Contracts`,
`FlowerCore.SignalControl`, `FlowerCore.Intranet.Web`,
`FlowerCore.Provisioning`, `FlowerCore.Redis`, `FlowerCore.MessageBoard`, and
`FlowerCore.MenuBoard`.
## Post-Merge Proof
After the PR is merged and ArgoCD syncs, verify the runner fleet:
```bash ```bash
kubectl -n github-runner get deploy,pods,pvc kubectl -n github-runner get deploy,pods,pvc
```
Verify GitHub registration for the repo-scoped runners: for repo in FlowerCore.Puppet FlowerCore.Signage FlowerCore.DMS FlowerCore.Telephony FlowerCore.Print.Web FlowerCore.Chat FlowerCore.MySQL FlowerCore.Kiosk.Linux; do
```bash
for repo in FlowerCore.Common FlowerCore.Shared.Pos FlowerCore.Puppet FlowerCore.Signage \
FlowerCore.DMS FlowerCore.Telephony FlowerCore.Print.Web FlowerCore.Chat \
FlowerCore.MySQL FlowerCore.Kiosk.Linux FlowerCore.Marquee FlowerCore.TtsReader \
FlowerCore.Knowledge FlowerCore.LlmBridge FlowerCore.Media \
FlowerCore.Presentations FlowerCore.RemoteDesktop FlowerCore.DNS \
FlowerCore.Distribution FlowerCore.Scoreboard FlowerCore.SegmentDisplay \
FlowerCore.Signage.Contracts FlowerCore.SignalControl FlowerCore.Intranet.Web \
FlowerCore.Provisioning FlowerCore.Redis FlowerCore.MessageBoard \
FlowerCore.MenuBoard; do
echo "=== $repo ==="
gh api "/repos/astoltz/$repo/actions/runners" \ gh api "/repos/astoltz/$repo/actions/runners" \
--jq '.runners[] | select(.labels[].name == "fc-build-linux") | {name,status,busy,labels:[.labels[].name]}' --jq '.runners[] | select((.labels[].name == "fc-build-linux") and (.status == "online")) | {name,status,busy,labels:[.labels[].name]}'
done done
``` ```
Shared.Pos publish proof after the runner pod is online: `LinuxRunnerOffline` is declared in `apps/monitoring/noc-monitoring.yaml` and
fires when any Common or top-8 Linux runner deployment has no available replica
```bash for 10 minutes.
gh run list --repo astoltz/FlowerCore.Shared.Pos \
--workflow "Build, Test & Publish" --branch main --limit 5
```
If the latest run is still queued after runner registration, rerun the workflow
from GitHub Actions and verify it lands on an `rke2-linux-*` runner.
## Failure Notes
- `actions/setup-dotnet` permission error at `/usr/share/dotnet`: check that
`DOTNET_INSTALL_DIR=/home/runner/.dotnet` and related cache env vars are
present on the runner pod.
- `404` during runner registration: the fine-grained PAT is valid but missing
repository access for that repo. Add the repo to the PAT access list; the PAT
value does not change.
- `Multi-Attach` volume error: only the Common runner uses a RWO PVC and it must
stay single-replica. New multi-replica runners use `emptyDir`.

File diff suppressed because it is too large Load Diff

View File

@@ -75,20 +75,6 @@ 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:
@@ -711,36 +697,6 @@ 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: linux-runners
rules:
- alert: LinuxRunnerOffline
expr: |
kube_deployment_status_replicas_ready{
namespace="github-runner",
deployment=~"github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"
} == 0
for: 5m
labels:
severity: warning
alert_channel: irc
service: github-runner
team: ci
annotations:
summary: "Linux CI runner offline: {{ $labels.deployment }}"
description: "Deployment {{ $labels.deployment }} in namespace github-runner has 0 ready replicas for more than 5 minutes. CI jobs targeting this repo will queue until the runner pod restarts and re-registers with GitHub. Check pods with: kubectl -n github-runner get pods -l app.kubernetes.io/name={{ $labels.deployment }}. Check logs with: kubectl -n github-runner logs -l app.kubernetes.io/name={{ $labels.deployment }} --tail=50. Common causes: PAT missing repo access, runner CrashLoopBackOff, or node/resource pressure."
- name: remote-desktop - name: remote-desktop
rules: rules:
- alert: RemoteDesktopWebDown - alert: RemoteDesktopWebDown
@@ -966,52 +922,6 @@ data:
annotations: annotations:
summary: "Disk usage high on {{ $labels.instance }} ({{ $value | printf \"%.1f\" }}%)" summary: "Disk usage high on {{ $labels.instance }} ({{ $value | printf \"%.1f\" }}%)"
# Puppet agent + service alerts.
# Mirror of FlowerCore.Notes/scripts/monitoring/alerts.yml `puppet` group
# so a future migration to in-cluster Prometheus inherits the ruleset.
# Source-of-truth for the live Podman Prometheus on noc1 is the Notes file.
# See feedback_monitoring_k8s_target_vs_live_podman.
- name: puppet
rules:
- alert: PuppetAgentReportStale
expr: puppet_last_run_age_seconds > 7200
for: 30m
labels:
severity: warning
alert_channel: irc
annotations:
summary: "Puppet agent {{ $labels.instance }} hasn't reported in over 2h"
description: "Last run age: {{ $value | humanizeDuration }}. The puppet agent on {{ $labels.instance }} may be stopped, the node may be powered off, or noc1 may be unreachable from this node."
runbook: "1. SSH to node (via noc1 jumpbox if needed) 2. sudo systemctl status puppet 3. sudo puppet agent -t --noop to force a run 4. Check r10k: ssh fcadmin@10.0.56.10 'sudo podman logs openvoxserver --tail 50' 5. Verify noc1 reachability: ping puppet.iamworkin.lan"
- alert: PuppetAgentReportCritical
expr: puppet_last_run_age_seconds > 86400
for: 1h
labels:
severity: critical
alert_channel: irc
annotations:
summary: "Puppet agent {{ $labels.instance }} silent for over 24h — node is unmanaged"
description: "Last run age: {{ $value | humanizeDuration }}. Node {{ $labels.instance }} has not submitted a Puppet report in over 24 hours. Config drift is accumulating — investigate immediately. If intentional (maintenance), add to the exclusion filter or silence in Grafana."
runbook: "URGENT: 1. Check node power state 2. SSH via noc1 jumpbox: ssh fcadmin@10.0.56.10 then ssh <node> 3. sudo systemctl status puppet 4. sudo systemctl start puppet + sudo puppet agent -t 5. Check for network partitions (VLAN connectivity to 10.0.56.10) 6. If node was recently reimaged: sudo puppet agent -t to re-register with new SSL cert"
# Sprint 33 Cx-7 Phase B (2026-05-25 postmortem follow-up):
# Detects puppet.service in failed state — distinct from PuppetAgentReportStale
# which catches "agent hasn't run." This catches "systemd gave up restarting it"
# (CA-verify loop or other fatal exit). Requires node-exporter systemd collector
# enabled with --collector.systemd. If `node_systemd_unit_state` has no series
# for a node, the collector is disabled there — flag in postmortem follow-up.
- alert: PuppetServiceFailed
expr: node_systemd_unit_state{name="puppet.service",state="failed"} == 1
for: 5m
labels:
severity: warning
alert_channel: irc
annotations:
summary: "Puppet service failed on {{ $labels.instance }}"
description: "puppet.service on {{ $labels.instance }} has been in failed state for 5+ minutes. systemd has stopped auto-restarting (CA-verify-loop or other exit). Manual `systemctl status puppet` confirms. Run `sudo systemctl start puppet` to recover; investigate journal for root cause."
runbook_url: "https://github.com/astoltz/FlowerCore.Notes/blob/master/memory/feedback_puppet_service_dead_after_ca_loop_alert_misreads.md"
# K8s pod-state alerts. Require kube-state-metrics scrape (added # K8s pod-state alerts. Require kube-state-metrics scrape (added
# 2026-04-26 — see scrape_configs above). Would have surfaced the # 2026-04-26 — see scrape_configs above). Would have surfaced the
# agent-zero ollama-proxy 172x crash-loop instead of letting it # agent-zero ollama-proxy 172x crash-loop instead of letting it
@@ -1064,6 +974,19 @@ data:
summary: "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} replica mismatch" summary: "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} replica mismatch"
description: "Spec wants {{ $labels.spec_replicas }} but only {{ $value }} available. Likely a rollout stuck on probe failure, scheduling, or PVC." description: "Spec wants {{ $labels.spec_replicas }} but only {{ $value }} available. Likely a rollout stuck on probe failure, scheduling, or PVC."
- alert: LinuxRunnerOffline
expr: |
kube_deployment_status_replicas_available{namespace="github-runner",deployment=~"github-runner(|-(puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"} < 1
for: 10m
labels:
severity: warning
service: github-runner
alert_channel: thermal_print
annotations:
summary: "Linux GitHub Actions runner offline: {{ $labels.deployment }}"
description: "{{ $labels.deployment }} has no available runner pod for 10 minutes. GitHub jobs using [self-hosted, linux, fc-build-linux] for its repo will queue at $0 until the runner returns."
runbook_url: "https://gitea.iamworkin.lan/bluejay/FlowerCore.Notes/src/branch/master/docs/infrastructure/self-hosted-runner-fleet.md"
# Q-MR-3 (2026-05-11): multus memory pressure — catches the next OOM # Q-MR-3 (2026-05-11): multus memory pressure — catches the next OOM
# cascade BEFORE multus is OOM-killed cluster-wide. The 2026-05-10 # cascade BEFORE multus is OOM-killed cluster-wide. The 2026-05-10
# outage (21h) hit because no alert fired on the rising multus working # outage (21h) hit because no alert fired on the rising multus working
@@ -1273,55 +1196,24 @@ metadata:
data: data:
notify.py: | notify.py: |
#!/usr/bin/env python3 #!/usr/bin/env python3
"""HTTP->IRC alert relay with thermal-printer DIGEST forwarding. """HTTP->IRC alert relay with thermal printer forwarding for Grafana webhooks.
Listens on :9119, posts to #alerts on UnrealIRCd via raw IRC protocol.
Listens on :9119, posts to #alerts on UnrealIRCd, forwards to Print.Web Alerts tagged alert_channel=thermal_print also POST to Print.Web /api/print/alert.
/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
""" """
import json, os, socket, sys, threading, time import json, socket, sys, time
from collections import defaultdict
from datetime import datetime, timezone
from http.server import HTTPServer, BaseHTTPRequestHandler from http.server import HTTPServer, BaseHTTPRequestHandler
from urllib.request import Request, urlopen from urllib.request import Request, urlopen
from urllib.error import URLError
THERMAL_PRINT_ENABLED = os.environ.get("THERMAL_PRINT_ENABLED", "true").lower() == "true" IRC_HOST = "unrealircd.irc.svc" # short name: CoreDNS ndots:5 + iamworkin.lan template hijacks full .cluster.local (see memory)
BATCH_INTERVAL_MIN = int(os.environ.get("BATCH_INTERVAL_MIN", "60")) IRC_PORT = 6667
BATCH_MAX_PENDING = int(os.environ.get("BATCH_MAX_PENDING", "50")) IRC_NICK = "grafana-bot"
IRC_CHANNEL = "#alerts"
IRC_HOST = os.environ.get("IRC_HOST", "unrealircd.irc.svc") PRINT_WEB_URL = "http://10.0.57.16:5200/api/print/alert"
IRC_PORT = int(os.environ.get("IRC_PORT", "6667")) PRINT_ENABLED = True
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()}
def send_irc(message): def send_irc(message):
"""Connect, handle PING, join, send, quit."""
try: try:
sock = socket.create_connection((IRC_HOST, IRC_PORT), timeout=15) sock = socket.create_connection((IRC_HOST, IRC_PORT), timeout=15)
sock.sendall(f"NICK {IRC_NICK}\r\n".encode()) sock.sendall(f"NICK {IRC_NICK}\r\n".encode())
@@ -1354,137 +1246,52 @@ data:
time.sleep(0.5) time.sleep(0.5)
sock.sendall(b"QUIT :alert delivered\r\n") sock.sendall(b"QUIT :alert delivered\r\n")
sock.close() sock.close()
_stats["irc_sent"] += 1
return True return True
except Exception as e: except Exception as e:
print(f"[irc-notify] IRC send failed: {e}", file=sys.stderr) print(f"[irc-notify] IRC send failed: {e}", file=sys.stderr)
return False return False
def post_thermal(payload, kind): def send_thermal_print(alert):
if not THERMAL_PRINT_ENABLED: if not PRINT_ENABLED: return
print(f"[irc-notify] thermal disabled; skip {kind} ({payload.get('title','?')[:40]})", file=sys.stderr) labels = alert.get("labels", {})
return False 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: try:
req = Request(PRINT_WEB_URL, data=json.dumps(payload).encode("utf-8"), req = Request(PRINT_WEB_URL, data=json.dumps(payload).encode("utf-8"),
headers={"Content-Type": "application/json"}, method="POST") headers={"Content-Type": "application/json"}, method="POST")
resp = urlopen(req, timeout=10) resp = urlopen(req, timeout=10)
if kind == "immediate": _stats["print_immediate"] += 1 print(f"[irc-notify] Thermal print sent: {resp.read().decode()}", file=sys.stderr)
print(f"[irc-notify] thermal {kind} sent: {payload.get('title','?')[:50]}", file=sys.stderr)
return True
except Exception as e: except Exception as e:
print(f"[irc-notify] thermal {kind} failed: {e}", file=sys.stderr) print(f"[irc-notify] Thermal print failed: {e}", file=sys.stderr)
return False
def fingerprint_of(alert): def should_print(alert):
fp = alert.get("fingerprint", "")
if fp: return fp
labels = alert.get("labels", {}) 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 "" if labels.get("alert_channel") == "thermal_print": return True
return f"{labels.get('alertname','?')}/{labels.get('namespace','')}/{target}" if labels.get("severity", "").lower() in ("critical", "disaster"): return True
if alert.get("status", "").upper() == "RESOLVED": return False
def is_critical(alert): return False
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)
class Handler(BaseHTTPRequestHandler): class Handler(BaseHTTPRequestHandler):
def do_POST(self): 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)) length = int(self.headers.get("Content-Length", 0))
body = json.loads(self.rfile.read(length)) if length else {} body = json.loads(self.rfile.read(length)) if length else {}
for alert in body.get("alerts", []): for alert in body.get("alerts", []):
@@ -1499,56 +1306,22 @@ data:
msg = f"{icon}{sev_tag} {name}: {summary}" msg = f"{icon}{sev_tag} {name}: {summary}"
if desc: msg += f"\n {desc}" if desc: msg += f"\n {desc}"
send_irc(msg) send_irc(msg)
# Thermal routing — EVERYTHING (including criticals) goes into if should_print(alert): send_thermal_print(alert)
# the hourly digest. Only the explicit `alert_channel=thermal_print_immediate` self.send_response(200)
# label bypasses, and even that flushes-the-current-digest rather self.send_header("Content-Type", "application/json")
# than printing a standalone job, so the same fingerprint can't self.end_headers()
# 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()
self.wfile.write(b'{"status":"ok"}') self.wfile.write(b'{"status":"ok"}')
def do_GET(self): def do_GET(self):
self.send_response(200); self.send_header("Content-Type", "application/json"); self.end_headers() self.send_response(200)
with _buffer_lock: self.send_header("Content-Type", "application/json")
alertnames = sorted({it["alert"].get("labels", {}).get("alertname", "?") for it in _buffer.values()}) self.end_headers()
depth = len(_buffer) self.wfile.write(json.dumps({"service":"irc-notify","thermal_print":PRINT_ENABLED}).encode())
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())
def log_message(self, format, *args): def log_message(self, format, *args):
print(f"[irc-notify] {args[0]}", file=sys.stderr) print(f"[irc-notify] {args[0]}", file=sys.stderr)
if __name__ == "__main__": if __name__ == "__main__":
threading.Thread(target=digest_loop, daemon=True).start()
server = HTTPServer(("0.0.0.0", 9119), Handler) 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() server.serve_forever()
# ============================================================================= # =============================================================================
@@ -3635,39 +3408,6 @@ data:
relativeTimeRange: {from: 120, to: 0} relativeTimeRange: {from: 120, to: 0}
datasourceUid: __expr__ datasourceUid: __expr__
model: {type: threshold, expression: B, conditions: [{evaluator: {params: [600], type: gt}}], refId: C} model: {type: threshold, expression: B, conditions: [{evaluator: {params: [600], type: gt}}], refId: C}
- orgId: 1
name: CI Runners
folder: CI Alerts
interval: 1m
rules:
- uid: linux-runner-offline
title: LinuxRunnerOffline
condition: C
for: 5m
noDataState: OK
execErrState: Error
annotations:
summary: "Linux CI runner offline: {{ $labels.deployment }}"
description: "A github-runner namespace Deployment has 0 ready replicas for more than 5 minutes. CI jobs targeting that repo will queue until the runner pod restarts and re-registers."
runbook: "1. kubectl -n github-runner get pods -l app.kubernetes.io/name={{ $labels.deployment }} 2. kubectl -n github-runner logs -l app.kubernetes.io/name={{ $labels.deployment }} --tail=50 3. Verify PAT repo access if registration returns 404 4. Verify no RWO PVC is shared by scaled runners"
labels:
severity: warning
service: github-runner
alert_channel: irc
team: ci
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}
- refId: B
relativeTimeRange: {from: 300, to: 0}
datasourceUid: __expr__
model: {type: reduce, expression: A, reducer: last, refId: B}
- refId: C
relativeTimeRange: {from: 300, to: 0}
datasourceUid: __expr__
model: {type: threshold, expression: B, conditions: [{evaluator: {params: [0], type: gt}}], refId: C}
- orgId: 1 - orgId: 1
name: Infrastructure name: Infrastructure
folder: AI Stack Alerts folder: AI Stack Alerts
@@ -3700,24 +3440,25 @@ 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 - uid: linux-runner-offline
title: MacMiniRunnerOffline title: LinuxRunnerOffline
condition: C condition: C
for: 10m for: 10m
noDataState: Alerting noDataState: Alerting
execErrState: OK execErrState: OK
annotations: annotations:
summary: Mac mini GitHub runner offline summary: Linux GitHub Actions 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." description: "A repo-scoped fc-build-linux runner deployment has no available pod. Jobs will queue at $0 until ArgoCD/K8s returns the runner."
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" runbook_url: "https://gitea.iamworkin.lan/bluejay/FlowerCore.Notes/src/branch/master/docs/infrastructure/self-hosted-runner-fleet.md"
labels: labels:
severity: warning severity: warning
service: github-runner service: github-runner
alert_channel: thermal_print
data: data:
- refId: A - refId: A
relativeTimeRange: {from: 600, to: 0} relativeTimeRange: {from: 600, to: 0}
datasourceUid: prometheus datasourceUid: prometheus
model: {expr: 'min(flowercore_github_runner_online{runner=~"macmini-.*"} or vector(0))', instant: true, refId: A} model: {expr: 'min by(deployment) (kube_deployment_status_replicas_available{namespace="github-runner",deployment=~"github-runner(|-(puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"})', instant: true, refId: A}
- refId: B - refId: B
relativeTimeRange: {from: 600, to: 0} relativeTimeRange: {from: 600, to: 0}
datasourceUid: __expr__ datasourceUid: __expr__

View File

@@ -28,12 +28,9 @@ Source: `D:\git\FlowerCore\FlowerCore.WorldBuilder` (master)
Memory: `feedback_rke2_image_import_per_node_scp`. Memory: `feedback_rke2_image_import_per_node_scp`.
3. **Bump image tag** in `worldbuilder.yaml` and git push. 3. **Bump image tag** in `worldbuilder.yaml` and git push.
ArgoCD ApplicationSet picks up within ~3 minutes. ArgoCD ApplicationSet picks up within ~3 minutes.
4. **First production render** — open 4. **First production render** — open `https://worldbuilder.iamworkin.lan`,
`https://worldbuilder.iamworkin.lan/studio/c32e0000-0000-4000-8000-000000000004` create World → Character → Storyboard → ExportJob, confirm artifact
and confirm the Cyberpunk Blue Jay demo prompt loads with five seeded fake downloads. ComfyUI lives on BLUEJAY-WS at `http://10.0.56.20:8188`.
generated images. This Sprint 32 visitor-safe profile uses
`ClientMode=fake`; switch the image-generation env vars back to ComfyUI only
for an operator-owned GPU render lane.
## Health probes ## Health probes
@@ -56,13 +53,8 @@ Source: `D:\git\FlowerCore\FlowerCore.WorldBuilder` (master)
## Image generation backend ## Image generation backend
Sprint 32 pins the Kubernetes profile to `FlowerCore:WorldBuilder:ImageGeneration:BaseUrl=http://10.0.56.20:8188` —
`FlowerCore:WorldBuilder:ImageGeneration:ClientMode=fake` with ComfyUI runs on BLUEJAY-WS Windows (R9700 / gfx1201 / ROCm 7.2.1). Pod reaches
`BaseUrl=http://127.0.0.1:1`. That keeps the public/internal visitor demo the workstation directly across the 10.0.56.0/24 VLAN (no Podman-style host-
deterministic, avoids GPU exposure, and still exercises the studio/gallery filter issues — K8s pods route via Calico, which is L3-routed across the
surface with persisted generated-image metadata. VLAN).
The previous ComfyUI backend target was `http://10.0.56.20:8188` on
BLUEJAY-WS (R9700 / gfx1201 / ROCm 7.2.1). Re-enable it only in an
operator-owned follow-up that also verifies workstation reachability and image
import freshness.

View File

@@ -16,11 +16,7 @@ kind: Namespace
metadata: metadata:
name: fc-worldbuilder name: fc-worldbuilder
labels: labels:
app.kubernetes.io/name: fc-worldbuilder
app.kubernetes.io/part-of: flowercore app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
--- ---
# SQLite DB + generated image gallery + PDF/PNG exports. # SQLite DB + generated image gallery + PDF/PNG exports.
# Longhorn RWO — single replica with `Recreate` rollout strategy keeps it safe. # Longhorn RWO — single replica with `Recreate` rollout strategy keeps it safe.
@@ -29,13 +25,6 @@ kind: PersistentVolumeClaim
metadata: metadata:
name: worldbuilder-data name: worldbuilder-data
namespace: fc-worldbuilder namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-data
app.kubernetes.io/component: storage
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec: spec:
accessModes: accessModes:
- ReadWriteOnce - ReadWriteOnce
@@ -51,13 +40,7 @@ metadata:
namespace: fc-worldbuilder namespace: fc-worldbuilder
labels: labels:
app.kubernetes.io/name: worldbuilder-web app.kubernetes.io/name: worldbuilder-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore 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: spec:
replicas: 1 replicas: 1
revisionHistoryLimit: 3 revisionHistoryLimit: 3
@@ -71,16 +54,11 @@ spec:
metadata: metadata:
labels: labels:
app.kubernetes.io/name: worldbuilder-web app.kubernetes.io/name: worldbuilder-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations: annotations:
prometheus.io/scrape: "true" prometheus.io/scrape: "true"
prometheus.io/port: "8080" prometheus.io/port: "8080"
prometheus.io/path: "/metrics/prometheus" prometheus.io/path: "/metrics/prometheus"
flowercore.io/audit-trace-id: "worldbuilder-runtime-demo"
spec: spec:
securityContext: securityContext:
fsGroup: 1654 fsGroup: 1654
@@ -114,14 +92,11 @@ spec:
value: "/data/gallery" value: "/data/gallery"
- name: FlowerCore__WorldBuilder__Export__RootPath - name: FlowerCore__WorldBuilder__Export__RootPath
value: "/data/exports" value: "/data/exports"
# Visitor-safe Sprint 32 profile: fake backend keeps public demo # ComfyUI on BLUEJAY-WS (R9700 / gfx1201 / ROCm 7.2.1).
# rendering deterministic and avoids exposing BLUEJAY-WS GPU.
- name: FlowerCore__WorldBuilder__ImageGeneration__BaseUrl - name: FlowerCore__WorldBuilder__ImageGeneration__BaseUrl
value: "http://127.0.0.1:1" value: "http://10.0.56.20:8188"
- name: FlowerCore__WorldBuilder__ImageGeneration__ClientMode - name: FlowerCore__WorldBuilder__ImageGeneration__ClientMode
value: "fake" value: "comfyui"
- name: FlowerCore__WorldBuilder__ImageGeneration__BackendId
value: "fake"
resources: resources:
# Cluster CPU-request budget runs hot (99% on all 3 nodes at deploy # Cluster CPU-request budget runs hot (99% on all 3 nodes at deploy
# time) while actual CPU usage is well below capacity. Idle Blazor # time) while actual CPU usage is well below capacity. Idle Blazor
@@ -190,11 +165,7 @@ metadata:
namespace: fc-worldbuilder namespace: fc-worldbuilder
labels: labels:
app.kubernetes.io/name: worldbuilder-web app.kubernetes.io/name: worldbuilder-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec: spec:
type: ClusterIP type: ClusterIP
selector: selector:
@@ -209,13 +180,6 @@ kind: Certificate
metadata: metadata:
name: worldbuilder-web-tls name: worldbuilder-web-tls
namespace: fc-worldbuilder namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-web-tls
app.kubernetes.io/component: ingress
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec: spec:
secretName: worldbuilder-web-tls secretName: worldbuilder-web-tls
issuerRef: issuerRef:
@@ -236,13 +200,6 @@ kind: IngressRoute
metadata: metadata:
name: worldbuilder-web name: worldbuilder-web
namespace: fc-worldbuilder namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-web
app.kubernetes.io/component: ingress
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec: spec:
entryPoints: entryPoints:
- websecure - websecure

View File

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

View File

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

View File

@@ -13,7 +13,6 @@ public sealed class FleetManifestLintTests
private static readonly HashSet<string> PublicReadOnlyHosts = new(StringComparer.Ordinal) private static readonly HashSet<string> PublicReadOnlyHosts = new(StringComparer.Ordinal)
{ {
"brochure.flowercore.io",
"dist.flowercore.io", "dist.flowercore.io",
"dns.iamworkin.lan", "dns.iamworkin.lan",
}; };
@@ -55,10 +54,8 @@ public sealed class FleetManifestLintTests
"ttsreader-piper", "ttsreader-piper",
}; };
private static readonly IReadOnlyDictionary<string, string> LinuxRunnerRepos = new Dictionary<string, string>(StringComparer.Ordinal) private static readonly IReadOnlyDictionary<string, string> TopLinuxRunnerRepos = new Dictionary<string, string>(StringComparer.Ordinal)
{ {
["github-runner"] = "https://github.com/astoltz/FlowerCore.Common",
["github-runner-sharedpos"] = "https://github.com/astoltz/FlowerCore.Shared.Pos",
["github-runner-puppet"] = "https://github.com/astoltz/FlowerCore.Puppet", ["github-runner-puppet"] = "https://github.com/astoltz/FlowerCore.Puppet",
["github-runner-signage"] = "https://github.com/astoltz/FlowerCore.Signage", ["github-runner-signage"] = "https://github.com/astoltz/FlowerCore.Signage",
["github-runner-dms"] = "https://github.com/astoltz/FlowerCore.DMS", ["github-runner-dms"] = "https://github.com/astoltz/FlowerCore.DMS",
@@ -69,29 +66,6 @@ public sealed class FleetManifestLintTests
["github-runner-kiosk-linux"] = "https://github.com/astoltz/FlowerCore.Kiosk.Linux", ["github-runner-kiosk-linux"] = "https://github.com/astoltz/FlowerCore.Kiosk.Linux",
}; };
private static readonly HashSet<string> ScaledLinuxRunnerDeployments = new(StringComparer.Ordinal)
{
"github-runner-sharedpos",
"github-runner-puppet",
"github-runner-signage",
"github-runner-dms",
"github-runner-telephony",
"github-runner-print-web",
"github-runner-chat",
"github-runner-mysql",
"github-runner-kiosk-linux",
};
private static readonly IReadOnlyDictionary<string, string> WritableRunnerEnv = new Dictionary<string, string>(StringComparer.Ordinal)
{
["HOME"] = "/home/runner",
["DOTNET_INSTALL_DIR"] = "/home/runner/.dotnet",
["DOTNET_CLI_HOME"] = "/home/runner",
["NUGET_PACKAGES"] = "/home/runner/.nuget/packages",
["XDG_CACHE_HOME"] = "/home/runner/.cache",
["RUNNER_TOOL_CACHE"] = "/home/runner/_tool",
};
[Fact] [Fact]
public void IngressRoutes_MustKeepServiceReferencesInTheSameNamespace() public void IngressRoutes_MustKeepServiceReferencesInTheSameNamespace()
{ {
@@ -226,11 +200,14 @@ public sealed class FleetManifestLintTests
} }
[Fact] [Fact]
public void GitHubRunnerFleet_MustRegisterRequiredReposAsRepoScopedDeployments() public void GitHubRunnerFleet_MustRegisterTopLinuxReposAsRepoScopedDeployments()
{ {
var deployments = GitHubRunnerDeployments(); var deployments = Inventory.Documents
.Where(document => document.Kind == "Deployment")
.Where(document => document.Namespace == "github-runner")
.ToDictionary(document => document.Name, StringComparer.Ordinal);
foreach (var expectedRunner in LinuxRunnerRepos) foreach (var expectedRunner in TopLinuxRunnerRepos)
{ {
deployments.Should().ContainKey(expectedRunner.Key); deployments.Should().ContainKey(expectedRunner.Key);
@@ -238,7 +215,6 @@ public sealed class FleetManifestLintTests
EnvValue(container, "REPO_URL").Should().Be(expectedRunner.Value); EnvValue(container, "REPO_URL").Should().Be(expectedRunner.Value);
EnvValue(container, "EPHEMERAL").Should().Be("true"); EnvValue(container, "EPHEMERAL").Should().Be("true");
EnvValue(container, "LABELS").Should().Be("self-hosted,linux,fc-build-linux"); EnvValue(container, "LABELS").Should().Be("self-hosted,linux,fc-build-linux");
EnvValue(container, "RUN_AS_ROOT").Should().Be("false");
EnvValue(container, "ACCESS_TOKEN").Should().BeNull("ACCESS_TOKEN must come from github-runner-token Secret, not a literal"); EnvValue(container, "ACCESS_TOKEN").Should().BeNull("ACCESS_TOKEN must come from github-runner-token Secret, not a literal");
EnvSecretName(container, "ACCESS_TOKEN").Should().Be("github-runner-token"); EnvSecretName(container, "ACCESS_TOKEN").Should().Be("github-runner-token");
EnvSecretKey(container, "ACCESS_TOKEN").Should().Be("credential"); EnvSecretKey(container, "ACCESS_TOKEN").Should().Be("credential");
@@ -246,75 +222,51 @@ public sealed class FleetManifestLintTests
} }
[Fact] [Fact]
public void GitHubRunnerFleet_MustSetWritableNonRootDotnetAndCachePaths() public void GitHubRunnerFleet_MustPreserveExistingCommonRunnerShape()
{ {
foreach (var deployment in GitHubRunnerDeployments().Values) var common = Inventory.Documents
{ .Single(document => document.Kind == "Deployment"
var container = deployment.ContainerMappings().Should().ContainSingle().Subject; && document.Namespace == "github-runner"
&& document.Name == "github-runner");
foreach (var expectedEnv in WritableRunnerEnv) var container = common.ContainerMappings().Should().ContainSingle().Subject;
{ EnvValue(container, "REPO_URL").Should().Be("https://github.com/astoltz/FlowerCore.Common");
EnvValue(container, expectedEnv.Key).Should().Be(expectedEnv.Value, $"{deployment.Name} must keep .NET paths writable for uid 1001"); EnvValue(container, "RUNNER_NAME_PREFIX").Should().Be("rke2-linux");
} EnvValue(container, "LABELS").Should().Be("self-hosted,linux,fc-build-linux");
var mounts = ManifestNodeExtensions.MappingSequence(container, "volumeMounts") var claimNames = common.MappingSequence("spec", "template", "spec", "volumes")
.ToDictionary(
mount => ManifestNodeExtensions.Scalar(mount, "name") ?? string.Empty,
mount => ManifestNodeExtensions.Scalar(mount, "mountPath") ?? string.Empty,
StringComparer.Ordinal);
mounts.Should().Contain("runner-home", "/home/runner");
mounts.Should().Contain("nuget-cache", "/home/runner/.nuget/packages");
mounts.Should().Contain("tmp", "/tmp");
}
}
[Fact]
public void GitHubRunnerFleet_MustAvoidRwoMultiAttachForScaledDeployments()
{
var deployments = GitHubRunnerDeployments();
foreach (var deploymentName in ScaledLinuxRunnerDeployments)
{
var deployment = deployments[deploymentName];
ReplicaCount(deployment).Should().Be(2);
var volumes = deployment.MappingSequence("spec", "template", "spec", "volumes");
var claimNames = volumes
.Select(volume => ManifestNodeExtensions.Scalar(volume, "persistentVolumeClaim", "claimName"))
.Where(value => !string.IsNullOrWhiteSpace(value))
.ToList();
claimNames.Should().BeEmpty($"{deploymentName} is scaled and must not share a RWO PVC");
volumes.Should().Contain(volume =>
string.Equals(ManifestNodeExtensions.Scalar(volume, "name"), "nuget-cache", StringComparison.Ordinal)
&& ManifestNodeExtensions.Mapping(volume, "emptyDir") != null);
}
var common = deployments["github-runner"];
ReplicaCount(common).Should().Be(1);
common.MappingSequence("spec", "template", "spec", "volumes")
.Select(volume => ManifestNodeExtensions.Scalar(volume, "persistentVolumeClaim", "claimName")) .Select(volume => ManifestNodeExtensions.Scalar(volume, "persistentVolumeClaim", "claimName"))
.Where(value => !string.IsNullOrWhiteSpace(value)) .Where(value => !string.IsNullOrWhiteSpace(value))
.Should() .ToList();
.ContainSingle()
.Which claimNames.Should().Contain("github-runner-nuget-cache");
.Should()
.Be("github-runner-nuget-cache");
} }
[Fact] [Fact]
public void Monitoring_MustAlertWhenLinuxRunnerDeploymentIsUnavailable() public void GitHubRunnerFleet_MustUseOneRwoCachePerRepoScopedDeployment()
{
var pvcNames = Inventory.Documents
.Where(document => document.Kind == "PersistentVolumeClaim")
.Where(document => document.Namespace == "github-runner")
.Select(document => document.Name)
.ToHashSet(StringComparer.Ordinal);
foreach (var deploymentName in TopLinuxRunnerRepos.Keys)
{
var suffix = deploymentName["github-runner-".Length..];
pvcNames.Should().Contain($"github-runner-{suffix}-nuget-cache");
}
}
[Fact]
public void Monitoring_MustAlertWhenTopLinuxRunnerDeploymentIsUnavailable()
{ {
var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml")); var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
monitoring.Should().Contain("MacMiniRunnerOffline");
monitoring.Should().Contain("LinuxRunnerOffline"); monitoring.Should().Contain("LinuxRunnerOffline");
monitoring.Should().Contain("kube_deployment_status_replicas_ready"); monitoring.Should().Contain("kube_deployment_status_replicas_available{namespace=\"github-runner\"");
monitoring.Should().Contain("github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"); monitoring.Should().Contain("github-runner(|-(puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))");
monitoring.Should().Contain("folder: CI Alerts"); monitoring.Should().Contain("runbook_url: \"https://gitea.iamworkin.lan/bluejay/FlowerCore.Notes/src/branch/master/docs/infrastructure/self-hosted-runner-fleet.md\"");
monitoring.Should().Contain("uid: linux-runner-offline");
monitoring.Should().Contain("alert_channel: irc");
} }
[Fact] [Fact]
@@ -421,184 +373,6 @@ public sealed class FleetManifestLintTests
violations.Should().BeEmpty(); violations.Should().BeEmpty();
} }
[Fact]
public void FcDeviceManagement_MustShipExpectedManifestSet()
{
var appRoot = Path.Combine(Inventory.BluejayRoot, "apps", "fc-devicemgmt");
Directory.Exists(appRoot).Should().BeTrue("Sprint 8 Cx-5 owns apps/fc-devicemgmt.");
var expectedFiles = new[]
{
"1password-item.yaml",
"argocd-application.yaml",
"certificate-web.yaml",
"clusterrole-operator.yaml",
"clusterrolebinding-operator.yaml",
"deployment-operator.yaml",
"deployment-web.yaml",
"ingressroute-web.yaml",
"namespace.yaml",
"network-policy.yaml",
"service-web.yaml",
"serviceaccount-operator.yaml",
};
Directory.GetFiles(appRoot, "*.yaml")
.Select(Path.GetFileName)
.Should()
.BeEquivalentTo(expectedFiles);
foreach (var expectedFile in expectedFiles)
{
FcDeviceManagementDocuments()
.Should()
.Contain(document => document.RelativePath == $"fc-devicemgmt/{expectedFile}");
}
}
[Fact]
public void FcDeviceManagement_ObjectsMustCarryStandardTraceabilityLabels()
{
var requiredLabels = new[]
{
"app.kubernetes.io/name",
"app.kubernetes.io/part-of",
"app.kubernetes.io/managed-by",
"flowercore.io/tenant-id",
"flowercore.io/created-by",
};
var violations = FcDeviceManagementDocuments()
.SelectMany(document => requiredLabels
.Where(label => string.IsNullOrWhiteSpace(document.Scalar("metadata", "labels", label)))
.Select(label => $"{document.Descriptor} is missing metadata.labels['{label}']."))
.Concat(FcDeviceManagementDocuments()
.Where(document => document.Kind == "Deployment")
.SelectMany(document => requiredLabels
.Where(label => string.IsNullOrWhiteSpace(document.Scalar("spec", "template", "metadata", "labels", label)))
.Select(label => $"{document.Descriptor} pod template is missing metadata.labels['{label}'].")))
.Concat(FcDeviceManagementDocuments()
.Where(document => document.Kind == "Deployment")
.Where(document => string.IsNullOrWhiteSpace(document.Scalar("spec", "template", "metadata", "annotations", "flowercore.io/audit-trace-id")))
.Select(document => $"{document.Descriptor} pod template is missing flowercore.io/audit-trace-id."))
.ToList();
violations.Should().BeEmpty();
}
[Fact]
public void FcDeviceManagement_IngressMustUseCertManagerAndKeepPublicHostDisabled()
{
var appText = string.Join(
Environment.NewLine,
Directory.GetFiles(Path.Combine(Inventory.BluejayRoot, "apps", "fc-devicemgmt"), "*.yaml")
.Select(File.ReadAllText));
appText.Should().NotContain("certResolver");
appText.Should().Contain("update.flowercore.io");
appText.Should().Contain("disabled-until-Q-OIDC-1");
FcDeviceManagementDocuments()
.Where(document => document.Kind == "IngressRoute")
.SelectMany(document => document.MappingSequence("spec", "routes"))
.Select(route => ManifestNodeExtensions.Scalar(route, "match") ?? string.Empty)
.Should()
.Contain(match => match.Contains("Host(`devices.iamworkin.lan`)", StringComparison.Ordinal))
.And.NotContain(match => match.Contains("Host(`update.flowercore.io`)", StringComparison.Ordinal));
var certificate = FcDeviceManagementDocuments()
.Single(document => document.Kind == "Certificate" && document.Name == "fc-devicemgmt-web-tls");
certificate.Scalar("spec", "issuerRef", "name").Should().Be("step-ca-acme");
certificate.Scalar("spec", "issuerRef", "kind").Should().Be("ClusterIssuer");
ManifestNodeExtensions.ScalarSequence(certificate.Root, "spec", "dnsNames")
.Should()
.ContainSingle("devices.iamworkin.lan");
}
[Fact]
public void FcDeviceManagement_OperatorRbacMustCoverDevicesAndOwnerLookup()
{
var clusterRole = FcDeviceManagementDocuments()
.Single(document => document.Kind == "ClusterRole" && document.Name == "fc-devicemgmt-operator");
var allScalars = clusterRole.AllScalars().ToList();
allScalars.Should().Contain("devices.flowercore.io");
allScalars.Should().Contain("*");
allScalars.Should().Contain("deployments");
allScalars.Should().Contain("get");
var operatorDeployment = FcDeviceManagementDocuments()
.Single(document => document.Kind == "Deployment" && document.Name == "fc-devicemgmt-operator");
operatorDeployment.AllScalars().Should().Contain("FLOWERCORE_KUBERNETES_OWNER_DEPLOYMENT");
operatorDeployment.AllScalars().Should().Contain("fc-devicemgmt-operator");
}
[Fact]
public void FcDeviceManagement_RuntimeSecretsMustUseOnePasswordItemPattern()
{
var item = FcDeviceManagementDocuments()
.Single(document => document.Kind == "OnePasswordItem" && document.Name == "fc-devicemgmt-runtime");
item.Scalar("spec", "itemPath")
.Should()
.Be("vaults/IAmWorkin/items/FlowerCore DeviceManagement Runtime");
var appText = string.Join(
Environment.NewLine,
Directory.GetFiles(Path.Combine(Inventory.BluejayRoot, "apps", "fc-devicemgmt"), "*.yaml")
.Select(File.ReadAllText));
FcDeviceManagementDocuments().Should().NotContain(document => document.Kind == "Secret");
appText.Should().Contain("secretKeyRef:");
appText.Should().Contain("secretName: fc-devicemgmt-runtime");
appText.Should().NotContain("stringData:");
appText.Should().NotContain("from-literal");
appText.Should().NotContain("tls.key:");
}
[Fact]
public void FcDeviceManagement_NetworkPoliciesMustAllowLanAgentsSynologyAndDnatPorts()
{
var policies = FcDeviceManagementDocuments()
.Where(document => document.Kind == "NetworkPolicy")
.ToList();
policies.Should().HaveCount(2);
var combinedScalars = policies.SelectMany(policy => policy.AllScalars()).ToList();
combinedScalars.Should().Contain("10.0.56.0/24");
combinedScalars.Should().Contain("10.0.57.0/24");
combinedScalars.Should().Contain("10.0.58.0/24");
combinedScalars.Should().Contain("10.0.68.0/27");
combinedScalars.Should().Contain("10.0.58.3/32");
var combinedEgressPorts = policies.SelectMany(policy => policy.EgressPorts()).ToHashSet(StringComparer.Ordinal);
combinedEgressPorts.Should().Contain(new[] { "80", "443", "8080", "8443", "2049", "111" });
var traefikVipPolicies = policies
.Where(policy => policy.AllScalars().Any(value => value.Contains("10.0.56.200", StringComparison.Ordinal)))
.ToList();
traefikVipPolicies.Should().ContainSingle();
traefikVipPolicies[0].EgressPorts().Should().Contain(new[] { "80", "443", "8080", "8443" });
}
[Fact]
public void FcDeviceManagement_ArgocdApplicationMustMatchApplicationSetDiscoveryConventions()
{
var application = FcDeviceManagementDocuments()
.Single(document => document.Kind == "Application" && document.Name == "infra-fc-devicemgmt");
application.Namespace.Should().Be("argocd");
application.Scalar("spec", "source", "repoURL")
.Should()
.Be("http://gitea-clusterip.gitea.svc.cluster.local:3000/bluejay/bluejay-infra.git");
application.Scalar("spec", "source", "path").Should().Be("apps/fc-devicemgmt");
application.Scalar("spec", "destination", "namespace").Should().Be("fc-devicemgmt");
}
private static IEnumerable<string> ProbeViolations( private static IEnumerable<string> ProbeViolations(
ManifestDocument document, ManifestDocument document,
YamlMappingNode container, YamlMappingNode container,
@@ -623,19 +397,6 @@ public sealed class FleetManifestLintTests
}; };
} }
private static IReadOnlyDictionary<string, ManifestDocument> GitHubRunnerDeployments()
{
return Inventory.Documents
.Where(document => document.Kind == "Deployment")
.Where(document => document.Namespace == "github-runner")
.ToDictionary(document => document.Name, StringComparer.Ordinal);
}
private static int ReplicaCount(ManifestDocument document)
{
return int.TryParse(document.Scalar("spec", "replicas"), out var replicas) ? replicas : 1;
}
private static string? EnvValue(YamlMappingNode container, string name) private static string? EnvValue(YamlMappingNode container, string name)
{ {
return EnvMapping(container, name) is { } env ? ManifestNodeExtensions.Scalar(env, "value") : null; return EnvMapping(container, name) is { } env ? ManifestNodeExtensions.Scalar(env, "value") : null;
@@ -660,13 +421,6 @@ public sealed class FleetManifestLintTests
return ManifestNodeExtensions.MappingSequence(container, "env") return ManifestNodeExtensions.MappingSequence(container, "env")
.SingleOrDefault(env => string.Equals(ManifestNodeExtensions.Scalar(env, "name"), name, StringComparison.Ordinal)); .SingleOrDefault(env => string.Equals(ManifestNodeExtensions.Scalar(env, "name"), name, StringComparison.Ordinal));
} }
private static IReadOnlyList<ManifestDocument> FcDeviceManagementDocuments()
{
return Inventory.Documents
.Where(document => document.RelativePath.StartsWith("fc-devicemgmt/", StringComparison.Ordinal))
.ToList();
}
} }
internal sealed class ManifestInventory internal sealed class ManifestInventory

View File

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

View File

@@ -174,13 +174,10 @@ 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("start flowercore-signage-player-pi-hdmi.service"); rule.Should().Contain("restart flowercore-signage-player-pi.service");
responder.Should().Contain("sleep 2"); rule.Should().Contain("start flowercore-signage-detect-display.service");
responder.Should().Contain("start flowercore-signage-detect-display.service");
responder.Should().Contain("restart flowercore-signage-player-pi.service");
} }
[Fact] [Fact]

View File

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