Files
bluejay-infra/apps/worldbuilder/worldbuilder.yaml
2026-06-04 15:55:07 -05:00

283 lines
9.7 KiB
YAML

# FlowerCore.WorldBuilder — comic / storyboard authoring service.
#
# Deployment + Service + PVC + Certificate + IngressRoute. ArgoCD-managed
# end-to-end. See apps/worldbuilder/README.md for the per-deploy runbook.
#
# Image build (BLUEJAY-WS):
# bash deploy/build.sh # in FlowerCore.WorldBuilder repo
# podman save localhost/fc-worldbuilder:v<TAG> -o /tmp/fc-worldbuilder-v<TAG>.tar
# for h in 10.0.56.11 10.0.56.12 10.0.56.13; do
# scp /tmp/fc-worldbuilder-v<TAG>.tar fcadmin@$h:/tmp/
# ssh fcadmin@$h "sudo /var/lib/rancher/rke2/bin/ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images import /tmp/fc-worldbuilder-v<TAG>.tar"
# done
---
apiVersion: v1
kind: Namespace
metadata:
name: fc-worldbuilder
labels:
app.kubernetes.io/name: fc-worldbuilder
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
---
# SQLite DB + generated image gallery + PDF/PNG exports.
# Longhorn RWO — single replica with `Recreate` rollout strategy keeps it safe.
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: worldbuilder-data
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-data
app.kubernetes.io/component: storage
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
resources:
requests:
storage: 5Gi
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: worldbuilder-web
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
flowercore.io/traceability-standard: k8s-pod-ownership-and-traceability-standard
spec:
replicas: 1
revisionHistoryLimit: 3
strategy:
# RWO PVC + single replica. Recreate avoids multi-attach overlap.
type: Recreate
selector:
matchLabels:
app.kubernetes.io/name: worldbuilder-web
template:
metadata:
labels:
app.kubernetes.io/name: worldbuilder-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
fc.flowercore.io/healthz-anon: "true"
fc.flowercore.io/probe-path: "/healthz"
prometheus.io/scrape: "true"
prometheus.io/port: "8080"
prometheus.io/path: "/metrics/prometheus"
flowercore.io/audit-trace-id: "worldbuilder-runtime-demo"
spec:
securityContext:
fsGroup: 1654
fsGroupChangePolicy: OnRootMismatch
containers:
- name: web
# Bump tag for each rebuild. Initial deploy: v202605062048
image: localhost/fc-worldbuilder:v202605062048
imagePullPolicy: Never
ports:
- containerPort: 8080
name: http
# fc-safe-to-expose: X-Forwarded-Proto handled by AddFlowerCoreWebAuth (ADR-178) before any future public/OIDC flip.
env:
- name: ASPNETCORE_URLS
value: "http://+:8080"
- name: ASPNETCORE_ENVIRONMENT
value: "Production"
- name: DOTNET_RUNNING_IN_CONTAINER
value: "true"
- name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
value: "false"
# SQLite path overrides (default appsettings uses relative paths).
- name: ConnectionStrings__DefaultConnection
value: "Data Source=/data/worldbuilder.db"
- name: FlowerCore__Database__Provider
value: "Sqlite"
- name: FlowerCore__Database__ConnectionStrings__Sqlite
value: "Data Source=/data/worldbuilder.db"
# Generated image gallery + exports persist on /data.
- name: FlowerCore__WorldBuilder__ImageStore__RootPath
value: "/data/gallery"
- name: FlowerCore__WorldBuilder__Export__RootPath
value: "/data/exports"
# Visitor-safe Sprint 32 profile: fake backend keeps public demo
# rendering deterministic and avoids exposing BLUEJAY-WS GPU.
- name: FlowerCore__WorldBuilder__ImageGeneration__BaseUrl
value: "http://127.0.0.1:1"
- name: FlowerCore__WorldBuilder__ImageGeneration__ClientMode
value: "fake"
- name: FlowerCore__WorldBuilder__ImageGeneration__BackendId
value: "fake"
resources:
# Cluster CPU-request budget runs hot (99% on all 3 nodes at deploy
# time) while actual CPU usage is well below capacity. Idle Blazor
# Server + SignalR + a single ComfyUI poller uses ~5m, so 25m is
# generous. Re-evaluate if active rendering/export workers ever
# push past the limit.
requests:
cpu: 25m
memory: 256Mi
limits:
cpu: 1000m
memory: 768Mi
# /healthz is registered explicitly in Program.cs (anonymous, no DB
# or OpenAPI dependency). Liveness uses tcpSocket as a cheap fallback
# in case future middleware changes accidentally gate /healthz.
# Memory: feedback_k8s_probes_must_not_hit_openapi,
# feedback_k8s_probes_behind_auth_middleware.
startupProbe:
httpGet:
path: /healthz
port: 8080
initialDelaySeconds: 5
periodSeconds: 5
failureThreshold: 30
readinessProbe:
httpGet:
path: /healthz
port: 8080
periodSeconds: 10
failureThreshold: 3
livenessProbe:
tcpSocket:
port: 8080
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
securityContext:
runAsNonRoot: true
runAsUser: 1654
runAsGroup: 1654
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop:
- ALL
volumeMounts:
- name: data
mountPath: /data
- name: tmp
mountPath: /tmp
- name: logs
mountPath: /app/logs
volumes:
- name: data
persistentVolumeClaim:
claimName: worldbuilder-data
- name: tmp
emptyDir: {}
- name: logs
emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
name: worldbuilder-web
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
type: ClusterIP
selector:
app.kubernetes.io/name: worldbuilder-web
ports:
- name: http
port: 80
targetPort: 8080
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: worldbuilder-web-tls
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-web-tls
app.kubernetes.io/component: ingress
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
secretName: worldbuilder-web-tls
issuerRef:
name: step-ca-acme
kind: ClusterIssuer
dnsNames:
- worldbuilder.iamworkin.lan
# step-ca ACME provisioner caps lifetime at 30d. Requesting 90d
# silently capped to 30d, making renewBefore 720h (30d) equal to the
# actual cert lifetime — triggered a perpetual renewal loop that
# generated 2365+ CertificateRequest objects in 18h. Match the working
# 720h/240h pattern used by every other FC service cert.
duration: 720h # 30d (step-ca cap)
renewBefore: 240h # 10d
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: worldbuilder-web
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-web
app.kubernetes.io/component: ingress
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
entryPoints:
- websecure
routes:
- match: Host(`worldbuilder.iamworkin.lan`)
kind: Rule
services:
- name: worldbuilder-web
port: 80
tls:
secretName: worldbuilder-web-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose worldbuilder-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: worldbuilder-web-public
# namespace: worldbuilder
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`worldbuilder.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: worldbuilder-web-public-profile-header # injects entitlement profile
# services:
# - name: worldbuilder-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).