Adds the SciMesh coordinator: a durable task-queue server on PostgreSQL that owns all database access, with workers reaching it over HTTP only. Structured as a modular monolith following Clean Architecture: domain entities and their invariants, no I/O usecase business operations + repository/clock ports transport HTTP handlers, DTOs, auth, error mapping storage PostgreSQL repositories, transactions carried in context infra config, pool, clock, server, lease reaper Dependencies point strictly inward; domain imports nothing from the module. Working: layer wiring, routing, shared-token auth, access logging, request IDs, domain-error to status-code mapping, transactional boundaries, graceful shutdown (HTTP drain -> reaper stop -> pool close), migrations, and a Compose stack starting Postgres -> migrations -> coordinator. The domain is complete and covered by unit tests that need no database: lease ownership, stale attempts, idempotent result replay, retry budgets, and lease expiry. Repository methods are stubs returning ErrNotImplemented (HTTP 501). The SQL for atomic claiming (FOR UPDATE SKIP LOCKED) and for lease expiry is written and ready to wire up. See coordinator/ARCHITECTURE.md for the layer map and a request traced through every layer.
68 lines
2.1 KiB
YAML
68 lines
2.1 KiB
YAML
name: scimesh
|
|
|
|
services:
|
|
postgres:
|
|
image: postgres:16-alpine
|
|
environment:
|
|
POSTGRES_USER: ${POSTGRES_USER:-scimesh}
|
|
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-scimesh}
|
|
POSTGRES_DB: ${POSTGRES_DB:-scimesh}
|
|
ports:
|
|
- "${POSTGRES_PORT:-5432}:5432"
|
|
volumes:
|
|
- pgdata:/var/lib/postgresql/data
|
|
healthcheck:
|
|
# Everything else waits on this, so the check must prove the server
|
|
# accepts queries — not merely that the port is open.
|
|
test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-scimesh} -d ${POSTGRES_DB:-scimesh}"]
|
|
interval: 5s
|
|
timeout: 3s
|
|
retries: 10
|
|
start_period: 5s
|
|
|
|
# One-shot: applies migrations, then exits. Schema changes stay an explicit
|
|
# deployment step — the coordinator binary never migrates on startup.
|
|
migrate:
|
|
image: migrate/migrate:v4.17.1
|
|
depends_on:
|
|
postgres:
|
|
condition: service_healthy
|
|
volumes:
|
|
- ./migrations:/migrations:ro
|
|
command:
|
|
- -path=/migrations
|
|
- -database=postgres://${POSTGRES_USER:-scimesh}:${POSTGRES_PASSWORD:-scimesh}@postgres:5432/${POSTGRES_DB:-scimesh}?sslmode=disable
|
|
- up
|
|
restart: on-failure
|
|
|
|
coordinator:
|
|
build:
|
|
context: .
|
|
depends_on:
|
|
postgres:
|
|
condition: service_healthy
|
|
# Start only once the schema exists, otherwise the first query fails.
|
|
migrate:
|
|
condition: service_completed_successfully
|
|
environment:
|
|
COORDINATOR_ADDR: ":8080"
|
|
# Host is the service name: compose resolves it on the project network.
|
|
DATABASE_URL: postgres://${POSTGRES_USER:-scimesh}:${POSTGRES_PASSWORD:-scimesh}@postgres:5432/${POSTGRES_DB:-scimesh}?sslmode=disable
|
|
WORKER_AUTH_TOKEN: ${WORKER_AUTH_TOKEN:-dev-token}
|
|
DB_MAX_CONNS: "10"
|
|
REQUEST_TIMEOUT: "15s"
|
|
LEASE_DURATION: "2m"
|
|
REAPER_INTERVAL: "30s"
|
|
ports:
|
|
- "${COORDINATOR_PORT:-8080}:8080"
|
|
healthcheck:
|
|
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:8080/health"]
|
|
interval: 10s
|
|
timeout: 3s
|
|
retries: 3
|
|
start_period: 5s
|
|
restart: unless-stopped
|
|
|
|
volumes:
|
|
pgdata:
|