Deploy activity-core on railiance01

This commit is contained in:
2026-05-22 13:49:46 +02:00
parent cf92f0d686
commit e2aac3ad8c
8 changed files with 748 additions and 1 deletions

View File

@@ -13,6 +13,7 @@ COPY --from=builder /app/.venv /app/.venv
COPY --from=builder /app/src /app/src
COPY alembic.ini ./
COPY migrations/ ./migrations/
COPY scripts/ ./scripts/
COPY activity-definitions/ ./activity-definitions/
COPY event-types/ ./event-types/
COPY tasks/ ./tasks/

View File

@@ -0,0 +1,7 @@
apiVersion: v1
kind: Namespace
metadata:
name: activity-core
labels:
app.kubernetes.io/name: activity-core
app.kubernetes.io/part-of: custodian

View File

@@ -0,0 +1,364 @@
apiVersion: v1
kind: Service
metadata:
name: actcore-app-db
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-app-db
app.kubernetes.io/part-of: activity-core
spec:
selector:
app.kubernetes.io/name: actcore-app-db
ports:
- name: postgres
port: 5432
targetPort: postgres
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: actcore-app-db
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-app-db
app.kubernetes.io/part-of: activity-core
spec:
serviceName: actcore-app-db
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: actcore-app-db
template:
metadata:
labels:
app.kubernetes.io/name: actcore-app-db
app.kubernetes.io/part-of: activity-core
spec:
containers:
- name: postgres
image: postgres:16
imagePullPolicy: IfNotPresent
ports:
- name: postgres
containerPort: 5432
env:
- name: POSTGRES_USER
valueFrom:
secretKeyRef:
name: actcore-app-db-secret
key: username
- name: POSTGRES_PASSWORD
valueFrom:
secretKeyRef:
name: actcore-app-db-secret
key: password
- name: POSTGRES_DB
valueFrom:
secretKeyRef:
name: actcore-app-db-secret
key: database
readinessProbe:
exec:
command: ["pg_isready", "-U", "actcore"]
initialDelaySeconds: 5
periodSeconds: 10
livenessProbe:
exec:
command: ["pg_isready", "-U", "actcore"]
initialDelaySeconds: 30
periodSeconds: 20
volumeMounts:
- name: data
mountPath: /var/lib/postgresql/data
volumeClaimTemplates:
- metadata:
name: data
spec:
accessModes: ["ReadWriteOnce"]
resources:
requests:
storage: 5Gi
---
apiVersion: v1
kind: Service
metadata:
name: actcore-temporal-db
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-temporal-db
app.kubernetes.io/part-of: activity-core
spec:
selector:
app.kubernetes.io/name: actcore-temporal-db
ports:
- name: postgres
port: 5432
targetPort: postgres
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: actcore-temporal-db
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-temporal-db
app.kubernetes.io/part-of: activity-core
spec:
serviceName: actcore-temporal-db
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: actcore-temporal-db
template:
metadata:
labels:
app.kubernetes.io/name: actcore-temporal-db
app.kubernetes.io/part-of: activity-core
spec:
containers:
- name: postgres
image: postgres:16
imagePullPolicy: IfNotPresent
ports:
- name: postgres
containerPort: 5432
env:
- name: POSTGRES_USER
valueFrom:
secretKeyRef:
name: actcore-temporal-db-secret
key: username
- name: POSTGRES_PASSWORD
valueFrom:
secretKeyRef:
name: actcore-temporal-db-secret
key: password
- name: POSTGRES_DB
valueFrom:
secretKeyRef:
name: actcore-temporal-db-secret
key: database
readinessProbe:
exec:
command: ["pg_isready", "-U", "temporal"]
initialDelaySeconds: 5
periodSeconds: 10
livenessProbe:
exec:
command: ["pg_isready", "-U", "temporal"]
initialDelaySeconds: 30
periodSeconds: 20
volumeMounts:
- name: data
mountPath: /var/lib/postgresql/data
volumeClaimTemplates:
- metadata:
name: data
spec:
accessModes: ["ReadWriteOnce"]
resources:
requests:
storage: 8Gi
---
apiVersion: v1
kind: Service
metadata:
name: actcore-nats
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-nats
app.kubernetes.io/part-of: activity-core
spec:
selector:
app.kubernetes.io/name: actcore-nats
ports:
- name: client
port: 4222
targetPort: client
- name: monitor
port: 8222
targetPort: monitor
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: actcore-nats
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-nats
app.kubernetes.io/part-of: activity-core
spec:
serviceName: actcore-nats
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: actcore-nats
template:
metadata:
labels:
app.kubernetes.io/name: actcore-nats
app.kubernetes.io/part-of: activity-core
spec:
containers:
- name: nats
image: nats:2.10-alpine
imagePullPolicy: IfNotPresent
args: ["-js", "-sd", "/data", "-m", "8222"]
ports:
- name: client
containerPort: 4222
- name: monitor
containerPort: 8222
readinessProbe:
httpGet:
path: /healthz
port: monitor
initialDelaySeconds: 5
periodSeconds: 10
livenessProbe:
httpGet:
path: /healthz
port: monitor
initialDelaySeconds: 30
periodSeconds: 20
volumeMounts:
- name: data
mountPath: /data
volumeClaimTemplates:
- metadata:
name: data
spec:
accessModes: ["ReadWriteOnce"]
resources:
requests:
storage: 5Gi
---
apiVersion: v1
kind: Service
metadata:
name: actcore-temporal
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-temporal
app.kubernetes.io/part-of: activity-core
spec:
selector:
app.kubernetes.io/name: actcore-temporal
ports:
- name: grpc
port: 7233
targetPort: grpc
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: actcore-temporal
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-temporal
app.kubernetes.io/part-of: activity-core
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: actcore-temporal
template:
metadata:
labels:
app.kubernetes.io/name: actcore-temporal
app.kubernetes.io/part-of: activity-core
spec:
containers:
- name: temporal
image: temporalio/auto-setup:1.29.1
imagePullPolicy: IfNotPresent
ports:
- name: grpc
containerPort: 7233
env:
- name: DB
value: postgres12
- name: DB_PORT
value: "5432"
- name: POSTGRES_USER
valueFrom:
secretKeyRef:
name: actcore-temporal-db-secret
key: username
- name: POSTGRES_PWD
valueFrom:
secretKeyRef:
name: actcore-temporal-db-secret
key: password
- name: POSTGRES_SEEDS
value: actcore-temporal-db
- name: DBNAME
value: temporal
- name: VISIBILITY_DBNAME
value: temporal_visibility
- name: ENABLE_ES
value: "false"
- name: POD_IP
valueFrom:
fieldRef:
fieldPath: status.podIP
- name: TEMPORAL_ADDRESS
value: "$(POD_IP):7233"
readinessProbe:
exec:
command:
- sh
- -c
- temporal operator cluster health --address "${POD_IP}:7233"
initialDelaySeconds: 45
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 12
---
apiVersion: v1
kind: Service
metadata:
name: actcore-temporal-ui
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-temporal-ui
app.kubernetes.io/part-of: activity-core
spec:
selector:
app.kubernetes.io/name: actcore-temporal-ui
ports:
- name: http
port: 8080
targetPort: http
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: actcore-temporal-ui
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-temporal-ui
app.kubernetes.io/part-of: activity-core
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: actcore-temporal-ui
template:
metadata:
labels:
app.kubernetes.io/name: actcore-temporal-ui
app.kubernetes.io/part-of: activity-core
spec:
containers:
- name: temporal-ui
image: temporalio/ui:latest
imagePullPolicy: IfNotPresent
ports:
- name: http
containerPort: 8080
env:
- name: TEMPORAL_ADDRESS
value: actcore-temporal:7233
- name: TEMPORAL_CORS_ORIGINS
value: http://localhost:8080

View File

@@ -0,0 +1,221 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: actcore-runtime-config
namespace: activity-core
labels:
app.kubernetes.io/name: activity-core
app.kubernetes.io/part-of: activity-core
data:
TEMPORAL_HOST: actcore-temporal:7233
TEMPORAL_NAMESPACE: default
NATS_URL: nats://actcore-nats:4222
STATE_HUB_URL: http://inter-hub.inter-hub.svc.cluster.local:8000
REPO_SCOPING_URL: http://repo-scoping.repo-scoping.svc.cluster.local:8020
ISSUE_CORE_URL: http://issue-core.issue-core.svc.cluster.local:8010
ISSUE_SINK_TYPE: "null"
ACTIVITY_DEFINITION_DIRS: ""
PROMETHEUS_BIND_ADDR: 0.0.0.0:9090
ACTIVITY_CURATOR_GATE: disabled
---
apiVersion: batch/v1
kind: Job
metadata:
name: actcore-migrate
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-migrate
app.kubernetes.io/part-of: activity-core
spec:
backoffLimit: 3
template:
metadata:
labels:
app.kubernetes.io/name: actcore-migrate
app.kubernetes.io/part-of: activity-core
spec:
restartPolicy: OnFailure
containers:
- name: migrate
image: activity-core:railiance01-prod
imagePullPolicy: Never
command: ["python", "-m", "alembic", "upgrade", "head"]
envFrom:
- configMapRef:
name: actcore-runtime-config
- secretRef:
name: actcore-runtime-secret
---
apiVersion: batch/v1
kind: Job
metadata:
name: actcore-sync
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-sync
app.kubernetes.io/part-of: activity-core
spec:
backoffLimit: 3
template:
metadata:
labels:
app.kubernetes.io/name: actcore-sync
app.kubernetes.io/part-of: activity-core
spec:
restartPolicy: OnFailure
containers:
- name: sync
image: activity-core:railiance01-prod
imagePullPolicy: Never
command:
- sh
- -c
- python scripts/sync_event_types.py && python -m activity_core.sync_activity_definitions
envFrom:
- configMapRef:
name: actcore-runtime-config
- secretRef:
name: actcore-runtime-secret
---
apiVersion: v1
kind: Service
metadata:
name: actcore-api
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-api
app.kubernetes.io/part-of: activity-core
spec:
selector:
app.kubernetes.io/name: actcore-api
ports:
- name: http
port: 8010
targetPort: http
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: actcore-api
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-api
app.kubernetes.io/part-of: activity-core
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: actcore-api
template:
metadata:
labels:
app.kubernetes.io/name: actcore-api
app.kubernetes.io/part-of: activity-core
spec:
containers:
- name: api
image: activity-core:railiance01-prod
imagePullPolicy: Never
command: ["uvicorn", "activity_core.api:app", "--host", "0.0.0.0", "--port", "8010"]
ports:
- name: http
containerPort: 8010
envFrom:
- configMapRef:
name: actcore-runtime-config
- secretRef:
name: actcore-runtime-secret
readinessProbe:
httpGet:
path: /health
port: http
initialDelaySeconds: 10
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 6
livenessProbe:
httpGet:
path: /health
port: http
initialDelaySeconds: 45
periodSeconds: 20
timeoutSeconds: 5
---
apiVersion: v1
kind: Service
metadata:
name: actcore-worker-metrics
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-worker
app.kubernetes.io/part-of: activity-core
spec:
selector:
app.kubernetes.io/name: actcore-worker
ports:
- name: metrics
port: 9090
targetPort: metrics
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: actcore-worker
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-worker
app.kubernetes.io/part-of: activity-core
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: actcore-worker
template:
metadata:
labels:
app.kubernetes.io/name: actcore-worker
app.kubernetes.io/part-of: activity-core
spec:
containers:
- name: worker
image: activity-core:railiance01-prod
imagePullPolicy: Never
command: ["python", "-m", "activity_core.worker"]
ports:
- name: metrics
containerPort: 9090
envFrom:
- configMapRef:
name: actcore-runtime-config
- secretRef:
name: actcore-runtime-secret
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: actcore-event-router
namespace: activity-core
labels:
app.kubernetes.io/name: actcore-event-router
app.kubernetes.io/part-of: activity-core
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: actcore-event-router
template:
metadata:
labels:
app.kubernetes.io/name: actcore-event-router
app.kubernetes.io/part-of: activity-core
spec:
containers:
- name: event-router
image: activity-core:railiance01-prod
imagePullPolicy: Never
command: ["python", "-m", "activity_core.event_router"]
envFrom:
- configMapRef:
name: actcore-runtime-config
- secretRef:
name: actcore-runtime-secret

56
k8s/railiance/README.md Normal file
View File

@@ -0,0 +1,56 @@
# Railiance01 Kubernetes Deployment
This bundle establishes activity-core as an internal production service on the
railiance01 K3s cluster. It keeps the unauthenticated API as a ClusterIP service;
publish it through an authenticated ingress only after choosing the final host
name and access policy.
## Layout
- `00-namespace.yaml`: namespace and shared labels
- `10-infrastructure.yaml`: PostgreSQL for app data, PostgreSQL for Temporal,
NATS JetStream, Temporal, and Temporal UI
- `20-runtime.yaml`: migrate/sync jobs plus API, worker, and event-router
- `bootstrap-secrets.sh`: idempotently creates generated Kubernetes secrets
The runtime image tag is `activity-core:railiance01-prod` and is expected to be
loaded into the railiance01 K3s containerd image store.
## Deploy
```bash
docker build -t activity-core:railiance01-prod .
docker save -o /tmp/activity-core-railiance01-prod.tar activity-core:railiance01-prod
scp /tmp/activity-core-railiance01-prod.tar railiance01:/tmp/
ssh railiance01 sudo k3s ctr images import /tmp/activity-core-railiance01-prod.tar
rsync -a k8s/railiance/ railiance01:activity-core/k8s/railiance/
ssh railiance01
cd ~/activity-core
bash k8s/railiance/bootstrap-secrets.sh
kubectl apply -f k8s/railiance/10-infrastructure.yaml
kubectl -n activity-core wait --for=condition=ready pod -l app.kubernetes.io/name=actcore-app-db --timeout=180s
kubectl -n activity-core wait --for=condition=ready pod -l app.kubernetes.io/name=actcore-temporal-db --timeout=180s
kubectl -n activity-core wait --for=condition=ready pod -l app.kubernetes.io/name=actcore-nats --timeout=180s
kubectl -n activity-core rollout status deploy/actcore-temporal --timeout=300s
kubectl -n activity-core delete job actcore-migrate --ignore-not-found
kubectl apply -f k8s/railiance/20-runtime.yaml
kubectl -n activity-core wait --for=condition=complete job/actcore-migrate --timeout=180s
kubectl -n activity-core rollout status deploy/actcore-api --timeout=180s
kubectl -n activity-core rollout status deploy/actcore-worker --timeout=180s
kubectl -n activity-core rollout status deploy/actcore-event-router --timeout=180s
kubectl -n activity-core delete job actcore-sync --ignore-not-found
kubectl apply -f k8s/railiance/20-runtime.yaml
kubectl -n activity-core wait --for=condition=complete job/actcore-sync --timeout=180s
```
## Verify
```bash
kubectl -n activity-core exec deploy/actcore-api -- \
python -c "import urllib.request; print(urllib.request.urlopen('http://localhost:8010/health').read().decode())"
kubectl -n activity-core get pods
kubectl -n activity-core get svc
```

View File

@@ -0,0 +1,40 @@
#!/usr/bin/env bash
set -euo pipefail
NS="${NS:-activity-core}"
kubectl apply -f k8s/railiance/00-namespace.yaml
secret_exists() {
kubectl -n "$NS" get secret "$1" >/dev/null 2>&1
}
random_password() {
openssl rand -base64 32 | tr -d '\n'
}
if ! secret_exists actcore-app-db-secret; then
APP_DB_PASSWORD="$(random_password)"
kubectl -n "$NS" create secret generic actcore-app-db-secret \
--from-literal=username=actcore \
--from-literal=database=actcore \
--from-literal=password="$APP_DB_PASSWORD"
else
APP_DB_PASSWORD="$(kubectl -n "$NS" get secret actcore-app-db-secret -o jsonpath='{.data.password}' | base64 -d)"
fi
if ! secret_exists actcore-temporal-db-secret; then
kubectl -n "$NS" create secret generic actcore-temporal-db-secret \
--from-literal=username=temporal \
--from-literal=database=temporal \
--from-literal=password="$(random_password)"
fi
ACTCORE_DB_URL="postgresql+asyncpg://actcore:${APP_DB_PASSWORD}@actcore-app-db:5432/actcore"
if ! secret_exists actcore-runtime-secret; then
kubectl -n "$NS" create secret generic actcore-runtime-secret \
--from-literal=ACTCORE_DB_URL="$ACTCORE_DB_URL" \
--from-literal=WEBHOOK_SECRET_GITEA="" \
--from-literal=WEBHOOK_SECRET_GITHUB=""
fi

View File

@@ -183,7 +183,7 @@ async def sync_event_types(session_factory: Any) -> int:
(type_id, version, publisher, governance, status, attribute_schema, raw_md, synced_at)
VALUES
(:type_id, :version, :publisher, :governance, :status,
:attribute_schema::jsonb, :raw_md, now())
CAST(:attribute_schema AS jsonb), :raw_md, now())
ON CONFLICT (type_id) DO UPDATE SET
version = EXCLUDED.version,
publisher = EXCLUDED.publisher,

View File

@@ -0,0 +1,58 @@
---
id: ACTIVITY-WP-0005
type: workplan
title: "Railiance01 production service"
domain: custodian
repo: activity-core
status: finished
owner: codex
topic_slug: custodian
created: "2026-05-22"
updated: "2026-05-22"
---
# ACTIVITY-WP-0005 - Railiance01 Production Service
## Review Railiance Runtime
```task
id: ACTIVITY-WP-0005-T01
status: done
priority: high
```
Confirm railiance01 access, operating system, container runtime, and cluster
shape before selecting the production deployment path.
## Add Kubernetes Deployment Bundle
```task
id: ACTIVITY-WP-0005-T02
status: done
priority: high
```
Create a K3s-native deployment bundle for activity-core, including infrastructure,
runtime jobs, API, worker, event router, and generated Kubernetes secrets.
## Build And Import Production Image
```task
id: ACTIVITY-WP-0005-T03
status: done
priority: high
```
Build the production image locally, transfer it to railiance01, and import it
into the K3s containerd image store.
## Apply And Verify Service
```task
id: ACTIVITY-WP-0005-T04
status: done
priority: high
```
Apply the manifests on railiance01, run migrations and sync jobs, then verify
the API health endpoint and core pods.