rootandClaude Fable 5
5462842b8a
The API image ran four uvicorn workers, and each one built a full flow controller — four sets of MQTT subscriptions, cron ticks and webhooks. Runs one worker now; scaling out is the worker split, not more processes. Adds a loop-lag watchdog and a deep /utils/health/ that fails when the event loop is wedged or Redis is unreachable, the two failure modes a process-alive check never sees. Autoheal restarts on that signal, behind a compose profile because it mounts the Docker socket. The private user-seeding routes now need an explicit opt-in rather than just ENVIRONMENT=local, so a deployment that kept the default never exposes them. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011LF61rxW1FG5YCD2J9YqjY
251 lines
8.6 KiB
YAML
251 lines
8.6 KiB
YAML
# Production stack. Layered by the Makefile:
|
|
# compose.yml → production (Traefik + TLS, restart always)
|
|
# + compose.dev.yml → local dev (published ports, hot reload)
|
|
# + compose.local.yml → integrated stack on the shared `proxy` net
|
|
# Paths are relative to this directory, which compose uses as the project
|
|
# directory (build contexts therefore point at `..`, the repo root).
|
|
|
|
services:
|
|
|
|
db:
|
|
image: postgres:18
|
|
container_name: fluksio-db
|
|
restart: always
|
|
security_opt:
|
|
- no-new-privileges:true
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER} -d ${POSTGRES_DB}"]
|
|
interval: 10s
|
|
retries: 5
|
|
start_period: 30s
|
|
timeout: 10s
|
|
volumes:
|
|
- app-db-data:/var/lib/postgresql/data/pgdata
|
|
env_file:
|
|
- ../.env
|
|
environment:
|
|
- PGDATA=/var/lib/postgresql/data/pgdata
|
|
- POSTGRES_PASSWORD=${POSTGRES_PASSWORD?Variable not set}
|
|
- POSTGRES_USER=${POSTGRES_USER?Variable not set}
|
|
- POSTGRES_DB=${POSTGRES_DB?Variable not set}
|
|
|
|
redis:
|
|
image: redis:8.2-alpine
|
|
container_name: fluksio-redis
|
|
restart: always
|
|
security_opt:
|
|
- no-new-privileges:true
|
|
# Flow state, not a cache: append-only persistence keeps the last value of
|
|
# every message across a restart.
|
|
command: redis-server --appendonly yes
|
|
# Deliberately not on `proxy` and not published: only the backend talks to it.
|
|
networks:
|
|
- default
|
|
healthcheck:
|
|
test: ["CMD", "redis-cli", "ping"]
|
|
interval: 10s
|
|
retries: 5
|
|
start_period: 10s
|
|
timeout: 5s
|
|
volumes:
|
|
- app-redis-data:/data
|
|
|
|
adminer:
|
|
image: adminer
|
|
container_name: fluksio-adminer
|
|
restart: always
|
|
security_opt:
|
|
- no-new-privileges:true
|
|
# Deliberately not on `proxy`: the Postgres UI is reachable from the host
|
|
# in dev only (see compose.dev.yml), never routed from the internet.
|
|
networks:
|
|
- default
|
|
depends_on:
|
|
- db
|
|
environment:
|
|
- ADMINER_DESIGN=pepa-linha-dark
|
|
|
|
prestart:
|
|
image: '${DOCKER_IMAGE_BACKEND?Variable not set}:${TAG-latest}'
|
|
container_name: fluksio-prestart
|
|
build:
|
|
context: ..
|
|
dockerfile: backend/Dockerfile
|
|
security_opt:
|
|
- no-new-privileges:true
|
|
networks:
|
|
- proxy
|
|
- default
|
|
depends_on:
|
|
db:
|
|
condition: service_healthy
|
|
restart: true
|
|
command: bash scripts/prestart.sh
|
|
env_file:
|
|
- ../.env
|
|
environment:
|
|
- DOMAIN=${DOMAIN}
|
|
- FRONTEND_HOST=${FRONTEND_HOST?Variable not set}
|
|
- ENVIRONMENT=${ENVIRONMENT}
|
|
- BACKEND_CORS_ORIGINS=${BACKEND_CORS_ORIGINS}
|
|
- SECRET_KEY=${SECRET_KEY?Variable not set}
|
|
- FIRST_SUPERUSER=${FIRST_SUPERUSER?Variable not set}
|
|
- FIRST_SUPERUSER_PASSWORD=${FIRST_SUPERUSER_PASSWORD?Variable not set}
|
|
- SMTP_HOST=${SMTP_HOST}
|
|
- SMTP_USER=${SMTP_USER}
|
|
- SMTP_PASSWORD=${SMTP_PASSWORD}
|
|
- EMAILS_FROM_EMAIL=${EMAILS_FROM_EMAIL}
|
|
- POSTGRES_SERVER=db
|
|
- POSTGRES_PORT=${POSTGRES_PORT}
|
|
- POSTGRES_DB=${POSTGRES_DB}
|
|
- POSTGRES_USER=${POSTGRES_USER?Variable not set}
|
|
- POSTGRES_PASSWORD=${POSTGRES_PASSWORD?Variable not set}
|
|
- SENTRY_DSN=${SENTRY_DSN}
|
|
|
|
backend:
|
|
image: '${DOCKER_IMAGE_BACKEND?Variable not set}:${TAG-latest}'
|
|
container_name: fluksio-api
|
|
restart: always
|
|
security_opt:
|
|
- no-new-privileges:true
|
|
networks:
|
|
- proxy
|
|
- default
|
|
depends_on:
|
|
db:
|
|
condition: service_healthy
|
|
restart: true
|
|
redis:
|
|
condition: service_healthy
|
|
restart: true
|
|
prestart:
|
|
condition: service_completed_successfully
|
|
env_file:
|
|
- ../.env
|
|
environment:
|
|
- DOMAIN=${DOMAIN}
|
|
- FRONTEND_HOST=${FRONTEND_HOST?Variable not set}
|
|
- ENVIRONMENT=${ENVIRONMENT}
|
|
- BACKEND_CORS_ORIGINS=${BACKEND_CORS_ORIGINS}
|
|
- SECRET_KEY=${SECRET_KEY?Variable not set}
|
|
- FIRST_SUPERUSER=${FIRST_SUPERUSER?Variable not set}
|
|
- FIRST_SUPERUSER_PASSWORD=${FIRST_SUPERUSER_PASSWORD?Variable not set}
|
|
- SMTP_HOST=${SMTP_HOST}
|
|
- SMTP_USER=${SMTP_USER}
|
|
- SMTP_PASSWORD=${SMTP_PASSWORD}
|
|
- EMAILS_FROM_EMAIL=${EMAILS_FROM_EMAIL}
|
|
- POSTGRES_SERVER=db
|
|
- POSTGRES_PORT=${POSTGRES_PORT}
|
|
- POSTGRES_DB=${POSTGRES_DB}
|
|
- POSTGRES_USER=${POSTGRES_USER?Variable not set}
|
|
- POSTGRES_PASSWORD=${POSTGRES_PASSWORD?Variable not set}
|
|
- SENTRY_DSN=${SENTRY_DSN}
|
|
# Flow state survives a restart in Redis; without a host it stays in memory.
|
|
- REDIS_HOST=redis
|
|
# Flows are files in a git repository; secrets sit encrypted beside it.
|
|
- FLOWS_DIR=/data/flows
|
|
- SECRETS_FILE=/data/secrets.enc
|
|
# The MCP endpoint for agents, and the key its tokens are signed with.
|
|
# The key lives on the same volume as the flows, so it survives a rebuild
|
|
# and every issued token with it.
|
|
- MCP_ENABLED=${MCP_ENABLED-false}
|
|
- OAUTH_PRIVATE_KEY_FILE=/data/oauth-key.pem
|
|
|
|
volumes:
|
|
- app-flow-data:/data
|
|
|
|
# Deep health: fails when the event loop is wedged or Redis is gone, not
|
|
# just when the process is dead. Autoheal restarts on unhealthy.
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:8000/api/v1/utils/health/"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
start_period: 30s
|
|
|
|
build:
|
|
context: ..
|
|
dockerfile: backend/Dockerfile
|
|
labels:
|
|
- autoheal=true
|
|
- traefik.enable=true
|
|
- traefik.docker.network=proxy
|
|
- traefik.constraint-label=proxy
|
|
|
|
- traefik.http.services.${STACK_NAME?Variable not set}-backend.loadbalancer.server.port=8000
|
|
|
|
- traefik.http.routers.${STACK_NAME?Variable not set}-backend-http.rule=Host(`api.${DOMAIN?Variable not set}`)
|
|
- traefik.http.routers.${STACK_NAME?Variable not set}-backend-http.entrypoints=http
|
|
|
|
- traefik.http.routers.${STACK_NAME?Variable not set}-backend-https.rule=Host(`api.${DOMAIN?Variable not set}`)
|
|
- traefik.http.routers.${STACK_NAME?Variable not set}-backend-https.entrypoints=https
|
|
- traefik.http.routers.${STACK_NAME?Variable not set}-backend-https.tls=true
|
|
- traefik.http.routers.${STACK_NAME?Variable not set}-backend-https.tls.certresolver=le
|
|
|
|
- traefik.http.routers.${STACK_NAME?Variable not set}-backend-http.middlewares=https-redirect
|
|
|
|
frontend:
|
|
image: '${DOCKER_IMAGE_FRONTEND?Variable not set}:${TAG-latest}'
|
|
container_name: fluksio-app
|
|
restart: always
|
|
security_opt:
|
|
- no-new-privileges:true
|
|
networks:
|
|
- proxy
|
|
- default
|
|
build:
|
|
context: ..
|
|
dockerfile: frontend/Dockerfile
|
|
args:
|
|
- VITE_API_URL=https://api.${DOMAIN?Variable not set}
|
|
- NODE_ENV=production
|
|
labels:
|
|
- traefik.enable=true
|
|
- traefik.docker.network=proxy
|
|
- traefik.constraint-label=proxy
|
|
|
|
- traefik.http.services.${STACK_NAME?Variable not set}-frontend.loadbalancer.server.port=80
|
|
|
|
- traefik.http.routers.${STACK_NAME?Variable not set}-frontend-http.rule=Host(`app.${DOMAIN?Variable not set}`)
|
|
- traefik.http.routers.${STACK_NAME?Variable not set}-frontend-http.entrypoints=http
|
|
|
|
- traefik.http.routers.${STACK_NAME?Variable not set}-frontend-https.rule=Host(`app.${DOMAIN?Variable not set}`)
|
|
- traefik.http.routers.${STACK_NAME?Variable not set}-frontend-https.entrypoints=https
|
|
- traefik.http.routers.${STACK_NAME?Variable not set}-frontend-https.tls=true
|
|
- traefik.http.routers.${STACK_NAME?Variable not set}-frontend-https.tls.certresolver=le
|
|
|
|
- traefik.http.routers.${STACK_NAME?Variable not set}-frontend-http.middlewares=https-redirect
|
|
|
|
# Docker never restarts a merely *unhealthy* container on its own; autoheal
|
|
# closes that gap for the services labeled autoheal=true.
|
|
#
|
|
# Behind a profile because it needs the Docker socket, which is host-wide
|
|
# authority: on a machine that runs anything besides this stack, that is a
|
|
# deliberate operator decision. `make up` opts in; the dev stacks do not.
|
|
autoheal:
|
|
image: willfarrell/autoheal:latest
|
|
container_name: fluksio-autoheal
|
|
profiles: ["autoheal"]
|
|
restart: always
|
|
security_opt:
|
|
- no-new-privileges:true
|
|
networks:
|
|
- default
|
|
environment:
|
|
# Scoped by label, so it only ever restarts this stack's backend.
|
|
- AUTOHEAL_CONTAINER_LABEL=autoheal
|
|
- AUTOHEAL_INTERVAL=15
|
|
volumes:
|
|
- /var/run/docker.sock:/var/run/docker.sock:ro
|
|
|
|
volumes:
|
|
app-db-data:
|
|
app-redis-data:
|
|
app-flow-data:
|
|
|
|
networks:
|
|
# Shared with the website stack and whatever reverse proxy fronts them.
|
|
# Created once by the workspace root's scripts/setup.sh.
|
|
proxy:
|
|
external: true
|