Production deployment profile + cutover runbook for hub.coulomb.social (CORE-WP-0005-T04)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-03 01:41:38 +02:00
parent a33191ab3a
commit defe4a6af8
5 changed files with 238 additions and 0 deletions
--- a/k8s/railiance-production/00-namespace.yaml
+++ b/k8s/railiance-production/00-namespace.yaml
@@ -0,0 +1,9 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: core-hub
+  labels:
+    app.kubernetes.io/name: core-hub
+    app.kubernetes.io/part-of: core-hub
+    environment: production
+    railiance.io/postgres-client: apps-pg
--- a/k8s/railiance-production/20-runtime.yaml
+++ b/k8s/railiance-production/20-runtime.yaml
@@ -0,0 +1,113 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: core-hub-prod-runtime
+  namespace: core-hub
+  labels:
+    app.kubernetes.io/name: core-hub
+    app.kubernetes.io/part-of: core-hub
+    environment: production
+data:
+  CORE_HUB_ENV: production
+  CORE_HUB_AUTO_CREATE_TABLES: "0"
+---
+apiVersion: batch/v1
+kind: Job
+metadata:
+  name: core-hub-prod-migrate
+  namespace: core-hub
+  labels:
+    app.kubernetes.io/name: core-hub
+    app.kubernetes.io/component: migration
+    app.kubernetes.io/part-of: core-hub
+    environment: production
+spec:
+  backoffLimit: 1
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: core-hub
+        app.kubernetes.io/component: migration
+        app.kubernetes.io/part-of: core-hub
+        environment: production
+    spec:
+      restartPolicy: Never
+      containers:
+        - name: migrate
+          image: gitea.coulomb.social/coulomb/core-hub:production-placeholder
+          imagePullPolicy: IfNotPresent
+          command: ["alembic", "upgrade", "head"]
+          envFrom:
+            - configMapRef:
+                name: core-hub-prod-runtime
+            - secretRef:
+                name: core-hub-prod-env
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: core-hub-api
+  namespace: core-hub
+  labels:
+    app.kubernetes.io/name: core-hub
+    app.kubernetes.io/component: api
+    app.kubernetes.io/part-of: core-hub
+    environment: production
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: core-hub
+      app.kubernetes.io/component: api
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: core-hub
+        app.kubernetes.io/component: api
+        app.kubernetes.io/part-of: core-hub
+        environment: production
+    spec:
+      containers:
+        - name: api
+          image: gitea.coulomb.social/coulomb/core-hub:production-placeholder
+          imagePullPolicy: IfNotPresent
+          ports:
+            - name: http
+              containerPort: 8010
+          envFrom:
+            - configMapRef:
+                name: core-hub-prod-runtime
+            - secretRef:
+                name: core-hub-prod-env
+          readinessProbe:
+            httpGet:
+              path: /readyz
+              port: http
+            initialDelaySeconds: 5
+            periodSeconds: 10
+          livenessProbe:
+            httpGet:
+              path: /healthz
+              port: http
+            initialDelaySeconds: 15
+            periodSeconds: 20
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: core-hub-api
+  namespace: core-hub
+  labels:
+    app.kubernetes.io/name: core-hub
+    app.kubernetes.io/component: api
+    app.kubernetes.io/part-of: core-hub
+    environment: production
+spec:
+  type: ClusterIP
+  selector:
+    app.kubernetes.io/name: core-hub
+    app.kubernetes.io/component: api
+  ports:
+    - name: http
+      port: 8010
+      targetPort: http
--- a/k8s/railiance-production/30-ingress.yaml
+++ b/k8s/railiance-production/30-ingress.yaml
@@ -0,0 +1,30 @@
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: core-hub
+  namespace: core-hub
+  annotations:
+    cert-manager.io/cluster-issuer: letsencrypt-prod
+    traefik.ingress.kubernetes.io/router.entrypoints: websecure
+    traefik.ingress.kubernetes.io/router.tls: "true"
+  labels:
+    app.kubernetes.io/name: core-hub
+    app.kubernetes.io/part-of: core-hub
+    environment: production
+spec:
+  ingressClassName: traefik
+  rules:
+    - host: hub.coulomb.social
+      http:
+        paths:
+          - backend:
+              service:
+                name: core-hub-api
+                port:
+                  number: 8010
+            path: /
+            pathType: Prefix
+  tls:
+    - hosts:
+        - hub.coulomb.social
+      secretName: core-hub-tls
--- a/k8s/railiance-production/README.md
+++ b/k8s/railiance-production/README.md
@@ -0,0 +1,47 @@
+# Core Hub production deployment (hub.coulomb.social cutover)
+
+`30-ingress.yaml` is the cutover flip — do NOT apply it while the inter-hub
+ingress still claims `hub.coulomb.social`.
+
+## Sequence
+
+```bash
+# 1. Image (operator: registry push)
+IMAGE_REPOSITORY=gitea.coulomb.social/coulomb/core-hub IMAGE_TAG=<sha> make container-build
+docker push gitea.coulomb.social/coulomb/core-hub:<sha>
+
+# 2. Prod DB + secret (operator: shared-DB DDL)
+#    role core_hub / db core_hub on apps-pg; secret core-hub-prod-env with
+#    CORE_HUB_DATABASE_URL (postgresql+asyncpg://...apps-pg-rw.databases...:5432/core_hub)
+#    and CORE_HUB_API_TOKEN (generated)
+
+# 3. Deploy (no traffic yet)
+kubectl apply -f k8s/railiance-production/00-namespace.yaml
+kubectl apply -f k8s/railiance-production/20-runtime.yaml
+kubectl -n core-hub set image job/core-hub-prod-migrate migrate=gitea.coulomb.social/coulomb/core-hub:<sha>
+kubectl -n core-hub set image deploy/core-hub-api api=gitea.coulomb.social/coulomb/core-hub:<sha>
+kubectl -n core-hub wait --for=condition=complete job/core-hub-prod-migrate --timeout=180s
+kubectl -n core-hub rollout status deploy/core-hub-api --timeout=180s
+
+# 4. Final data import (fresh Inter-Hub export at cutover time)
+kubectl exec -i -n databases net-kingdom-pg-1 -- psql -U postgres -d interhub -tA \
+  < scripts/migration/inter_hub_export.sql > final-bundle.json
+# validate, then import in-cluster (see scripts/migration/README.md)
+
+# 5. THE FLIP (operator approval point)
+kubectl -n inter-hub delete ingress inter-hub
+kubectl apply -f k8s/railiance-production/30-ingress.yaml
+# cert-manager issues core-hub-tls for hub.coulomb.social (~1 min)
+
+# 6. Verify
+curl -s https://hub.coulomb.social/healthz            # 200
+curl -s https://hub.coulomb.social/api/v2/widget-types | head -c 200
+curl -s -o /dev/null -w '%{http_code}' https://hub.coulomb.social/api/v2/hubs  # 401 = hardened contract
+
+## Rollback (any time; Inter-Hub deployment stays running)
+kubectl delete -f k8s/railiance-production/30-ingress.yaml
+kubectl -n inter-hub apply -f <saved inter-hub ingress>   # or helm upgrade inter-hub
+```
+
+Keep the Inter-Hub deployment/service running untouched until stabilization
+passes (CORE-WP-0005-T04); only the ingress moves.
--- a/k8s/railiance-production/rollback-inter-hub-ingress.yaml
+++ b/k8s/railiance-production/rollback-inter-hub-ingress.yaml
@@ -0,0 +1,39 @@
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  annotations:
+    cert-manager.io/cluster-issuer: letsencrypt-prod
+    meta.helm.sh/release-name: inter-hub
+    meta.helm.sh/release-namespace: inter-hub
+    traefik.ingress.kubernetes.io/router.entrypoints: websecure
+    traefik.ingress.kubernetes.io/router.tls: "true"
+  creationTimestamp: "2026-06-14T12:49:01Z"
+  generation: 1
+  labels:
+    app: inter-hub
+    app.kubernetes.io/managed-by: Helm
+  name: inter-hub
+  namespace: inter-hub
+  resourceVersion: "14479609"
+  uid: 2f1d1557-76be-445c-b77b-e03e7b0c3935
+spec:
+  ingressClassName: traefik
+  rules:
+  - host: hub.coulomb.social
+    http:
+      paths:
+      - backend:
+          service:
+            name: inter-hub
+            port:
+              number: 8000
+        path: /
+        pathType: Prefix
+  tls:
+  - hosts:
+    - hub.coulomb.social
+    secretName: inter-hub-tls
+status:
+  loadBalancer:
+    ingress:
+    - ip: 92.205.130.254