Files
activity-core/docker-compose.railiance.yml
tegwick 00e688bd8e fix(WP-0004): live deployment fixes from integration test
- Dockerfile: copy alembic.ini + migrations/ so actcore-migrate works
- docker-compose.railiance.yml:
    - Temporal: add dynamicconfig volume mount + correct DYNAMIC_CONFIG_FILE_PATH
    - Temporal: healthcheck uses 'temporal operator cluster health' (not tctl)
    - NATS: add monitoring port -m 8222 for wget-based healthcheck
    - actcore-api healthcheck: use Python urllib (curl absent from slim image)
- api.py: fix /health Temporal probe — Client has no describe_namespace;
    use workflow_service.get_system_info(GetSystemInfoRequest()) instead
- Makefile: grep -Eh to suppress filename prefix when MAKEFILE_LIST has
    multiple files (.env included via -include)

All 8 services start cleanly; /health returns {"status":"ok",...} HTTP 200;
SIGTERM drains worker cleanly within grace period; make help correct.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-15 09:23:14 +02:00

179 lines
5.6 KiB
YAML

services:
# ── Temporal persistence DB ──────────────────────────────────────────────────
temporal-db:
image: postgres:16
environment:
POSTGRES_USER: temporal
POSTGRES_PASSWORD: temporal
POSTGRES_DB: temporal
volumes:
- temporal-db-data:/var/lib/postgresql/data
networks:
- actcore-net
healthcheck:
test: ["CMD-SHELL", "pg_isready -U temporal"]
interval: 5s
timeout: 5s
retries: 10
# ── Temporal server (PostgreSQL visibility, no Elasticsearch) ─────────────────
temporal:
image: temporalio/auto-setup:1.29.1
depends_on:
temporal-db:
condition: service_healthy
environment:
DB: postgres12
DB_PORT: 5432
POSTGRES_USER: temporal
POSTGRES_PWD: temporal
POSTGRES_SEEDS: temporal-db
DYNAMIC_CONFIG_FILE_PATH: config/dynamicconfig/development-sql.yaml
ENABLE_ES: "false"
VISIBILITY_DBNAME: temporal_visibility
TEMPORAL_ADDRESS: temporal:7233
volumes:
- ./dynamicconfig:/etc/temporal/config/dynamicconfig
networks:
- actcore-net
healthcheck:
test: ["CMD", "temporal", "operator", "cluster", "health", "--address", "temporal:7233"]
interval: 10s
timeout: 10s
retries: 20
start_period: 30s
# ── Temporal Web UI ───────────────────────────────────────────────────────────
temporal-ui:
image: temporalio/ui:latest
depends_on:
temporal:
condition: service_healthy
environment:
TEMPORAL_ADDRESS: temporal:7233
TEMPORAL_CORS_ORIGINS: http://localhost:8080
ports:
- "8080:8080"
networks:
- actcore-net
# ── NATS with JetStream ───────────────────────────────────────────────────────
nats:
image: nats:2.10-alpine
command: ["-js", "-sd", "/data", "-m", "8222"]
volumes:
- nats-data:/data
ports:
- "4222:4222"
- "8222:8222"
networks:
- actcore-net
healthcheck:
test: ["CMD-SHELL", "wget -qO- http://localhost:8222/healthz | grep -q ok"]
interval: 5s
timeout: 5s
retries: 10
# ── Application DB ────────────────────────────────────────────────────────────
app-db:
image: postgres:16
environment:
POSTGRES_USER: actcore
POSTGRES_PASSWORD: actcore
POSTGRES_DB: actcore
volumes:
- app-db-data:/var/lib/postgresql/data
networks:
- actcore-net
healthcheck:
test: ["CMD-SHELL", "pg_isready -U actcore"]
interval: 5s
timeout: 5s
retries: 10
# ── One-shot migration runner ─────────────────────────────────────────────────
actcore-migrate:
build: .
command: ["python", "-m", "alembic", "upgrade", "head"]
env_file: .env
depends_on:
app-db:
condition: service_healthy
networks:
- actcore-net
restart: "no"
# ── Temporal worker ───────────────────────────────────────────────────────────
actcore-worker:
build: .
command: ["python", "-m", "activity_core.worker"]
env_file: .env
depends_on:
temporal:
condition: service_healthy
app-db:
condition: service_healthy
nats:
condition: service_healthy
actcore-migrate:
condition: service_completed_successfully
ports:
- "9090:9090"
networks:
- actcore-net
restart: unless-stopped
# ── REST API ──────────────────────────────────────────────────────────────────
actcore-api:
build: .
command: ["uvicorn", "activity_core.api:app", "--host", "0.0.0.0", "--port", "8010"]
env_file: .env
depends_on:
temporal:
condition: service_healthy
app-db:
condition: service_healthy
nats:
condition: service_healthy
actcore-migrate:
condition: service_completed_successfully
ports:
- "8010:8010"
networks:
- actcore-net
restart: unless-stopped
healthcheck:
test: ["CMD", "python", "-c", "import urllib.request,sys; r=urllib.request.urlopen('http://localhost:8010/health'); sys.exit(0 if r.status==200 else 1)"]
interval: 10s
timeout: 5s
retries: 5
start_period: 15s
# ── Event Router ──────────────────────────────────────────────────────────────
actcore-event-router:
build: .
command: ["python", "-m", "activity_core.event_router"]
env_file: .env
depends_on:
temporal:
condition: service_healthy
app-db:
condition: service_healthy
nats:
condition: service_healthy
actcore-migrate:
condition: service_completed_successfully
networks:
- actcore-net
restart: unless-stopped
volumes:
temporal-db-data:
app-db-data:
nats-data:
networks:
actcore-net:
driver: bridge