Files
dtf-system/docker-compose.yml
Cauê Faleiros b329f76378
All checks were successful
Build and deploy / Validate source (push) Successful in 7s
Build and deploy / Integration suite on a real stack (push) Successful in 1m25s
Build and deploy / Secret scan and release gate (push) Successful in 5s
Build and deploy / Publish images and notify Portainer (push) Successful in 1m31s
refactor: lay the repository out by role
local/ held six unrelated things under a name that stopped being true once it
became the production runtime: the service, the frontend, the tests, the ops
commands, the container definitions and the dependency lock, 65 files with
nothing to tell them apart.

  app/      the service: api/ routers, core/ for identity, database, models,
            prices and secret loading, and the worker, bootstrap and schema
  tests/    the twelve suites, no longer inside the shipped package
  ops/      backup, readiness, dependency audit, security summary
  infra/    Dockerfiles, gateway templates, ClamAV and storage configuration,
            the requirements and their hash lock
  web/      the Site, Kanban and portal pages with their scripts

deploy/Dockerfile.api now copies app/ alone, so the tests stop shipping to
production; the local image still carries them, because the suites run inside
the stack's network.

Five kinds of reference had to follow, and each was found by something different
rather than by reading. Imports of the form "from . import db" survived a rewrite
that only matched "from .db import". Tests kept relative imports of modules that
had left the package. A mock.patch target names its module in a string, where no
import rewriting can see it. The browser test resolves a fixture by path. And the
release gate's markers pointed at local/runtime.py and local/worker.py, which is
the decay its new marker test exists to catch — it caught it.

Verified from docker compose down -v: the stack starts, all six integration
suites, both browser suites and the twenty-nine unit tests pass.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-21 17:40:57 -03:00

189 lines
6.2 KiB
YAML

version: "3.8"
x-app-environment: &app-environment
APP_ENV: production
DATABASE_HOST: db
DATABASE_NAME: dtf
DATABASE_USER: dtf_app
# Must differ from POSTGRES_PASSWORD: the runtime role is DML-only, and reusing
# the administrator credential would make that restriction meaningless.
DATABASE_PASSWORD: ${APP_DB_PASSWORD:?set APP_DB_PASSWORD}
S3_ENDPOINT: ${R2_ENDPOINT:?set R2_ENDPOINT}
S3_PUBLIC_ENDPOINT: ${R2_ENDPOINT:?set R2_ENDPOINT}
S3_BUCKET: ${R2_BUCKET:?set R2_BUCKET}
AWS_ACCESS_KEY_ID: ${R2_ACCESS_KEY_ID:?set R2_ACCESS_KEY_ID}
AWS_SECRET_ACCESS_KEY: ${R2_SECRET_ACCESS_KEY:?set R2_SECRET_ACCESS_KEY}
AWS_DEFAULT_REGION: auto
# Optional at deploy time so a missing Kanban credential cannot make the
# entire Swarm stack invalid. The Kanban login endpoint fails closed until
# this value is configured.
OPERATOR_EMAIL: ${OPERATOR_EMAIL:-}
OPERATOR_PASSWORD: ${OPERATOR_PASSWORD:?set OPERATOR_PASSWORD}
PAYMENT_ADAPTER: fake
FREIGHT_ADAPTER: fake
TINY_ADAPTER: fake
WHATSAPP_ADAPTER: fake
STORAGE_ADAPTER: s3-r2
PUBLIC_ORIGIN: https://${SITE_DOMAIN:?set SITE_DOMAIN}
PUBLIC_HOST: ${SITE_DOMAIN:?set SITE_DOMAIN}
ALLOWED_HOSTS: ${SITE_DOMAIN:?set SITE_DOMAIN},${KANBAN_DOMAIN:?set KANBAN_DOMAIN}
ALLOWED_ORIGINS: https://${SITE_DOMAIN:?set SITE_DOMAIN},https://${KANBAN_DOMAIN:?set KANBAN_DOMAIN}
COOKIE_SECURE: "true"
MAX_UPLOAD_BYTES: "5368709120"
UPLOAD_PART_BYTES: "8388608"
STORAGE_QUOTA_BYTES: "53687091200"
OWNER_UPLOAD_QUOTA_BYTES: "10737418240"
MAX_PENDING_UPLOADS: "10"
SCAN_MAX_BYTES: "134217728"
services:
db:
image: postgres:17-alpine
environment:
POSTGRES_DB: dtf
POSTGRES_USER: dtf_admin
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:?set POSTGRES_PASSWORD}
volumes: [postgres-data:/var/lib/postgresql/data]
networks: [backend]
healthcheck:
test: [CMD-SHELL, 'pg_isready -U "$$POSTGRES_USER" -d "$$POSTGRES_DB"']
interval: 10s
timeout: 5s
retries: 12
start_period: 20s
deploy:
replicas: 1
restart_policy: {condition: on-failure, delay: 10s}
db-init:
image: ${API_IMAGE:-gitea.blyzer.com.br/blyzer/dtf-api}:${IMAGE_TAG:-latest}
command: python -m app.bootstrap
environment:
DATABASE_ADMIN_HOST: db
DATABASE_ADMIN_NAME: dtf
DATABASE_ADMIN_USER: dtf_admin
DATABASE_ADMIN_PASSWORD: ${POSTGRES_PASSWORD:?set POSTGRES_PASSWORD}
APP_DB_USER: dtf_app
APP_DB_PASSWORD: ${APP_DB_PASSWORD:?set APP_DB_PASSWORD}
# The migration job seeds the first operator account from these, so an
# existing deployment keeps its Kanban login after the accounts table
# lands. Without them there would be no account at all and login would
# fail closed with 503.
OPERATOR_EMAIL: ${OPERATOR_EMAIL:-}
OPERATOR_PASSWORD: ${OPERATOR_PASSWORD:?set OPERATOR_PASSWORD}
networks: [backend]
deploy:
replicas: 1
restart_policy: {condition: on-failure, delay: 5s, max_attempts: 20}
scanner:
image: clamav/clamav@sha256:9cb27d7660bdf66e9878c832cb433dd8aa152cfbe16f3c2c0084c80b04ae22b4
entrypoint: [clamd, --foreground=true, --config-file=/etc/clamav/clamd.conf]
configs:
- source: clamd_config
target: /etc/clamav/clamd.conf
mode: 0444
networks: [backend]
healthcheck:
test: [CMD, clamdscan, --config-file=/etc/clamav/clamd.conf, --ping, "3"]
interval: 15s
timeout: 5s
retries: 20
start_period: 90s
deploy:
replicas: 1
restart_policy: {condition: on-failure, delay: 10s}
resources:
limits: {memory: 3G}
api:
image: ${API_IMAGE:-gitea.blyzer.com.br/blyzer/dtf-api}:${IMAGE_TAG:-latest}
environment: *app-environment
networks: [backend, egress]
read_only: true
tmpfs: [/tmp]
healthcheck:
test: [CMD-SHELL, 'python -c "import os,urllib.request; r=urllib.request.Request(\"http://localhost:8000/health\",headers={\"Host\":os.environ[\"PUBLIC_HOST\"]}); urllib.request.urlopen(r,timeout=3)"']
interval: 15s
timeout: 5s
retries: 12
start_period: 30s
deploy:
replicas: 1
restart_policy: {condition: on-failure, delay: 5s}
worker:
image: ${API_IMAGE:-gitea.blyzer.com.br/blyzer/dtf-api}:${IMAGE_TAG:-latest}
command: python -m app.worker
environment: *app-environment
networks: [backend, egress]
read_only: true
tmpfs: [/tmp]
healthcheck:
test: [CMD, python, -c, "import urllib.request; urllib.request.urlopen('http://localhost:8002/health',timeout=3)"]
interval: 15s
timeout: 5s
retries: 12
start_period: 90s
deploy:
replicas: 1
restart_policy: {condition: on-failure, delay: 5s}
site:
image: ${WEB_IMAGE:-gitea.blyzer.com.br/blyzer/dtf-web}:${IMAGE_TAG:-latest}
environment:
WEB_INDEX: index.html
PUBLIC_HOST: ${SITE_DOMAIN:?set SITE_DOMAIN}
S3_PUBLIC_ENDPOINT: ${R2_ENDPOINT:?set R2_ENDPOINT}
networks: [backend]
ports:
- target: 8080
published: ${SITE_PORT:-18080}
protocol: tcp
mode: ingress
healthcheck:
test: [CMD-SHELL, 'wget -q --header="Host: $$PUBLIC_HOST" -O /dev/null http://127.0.0.1:8080/health']
interval: 15s
timeout: 5s
retries: 12
start_period: 15s
deploy:
replicas: 1
restart_policy: {condition: on-failure, delay: 5s}
kanban:
image: ${WEB_IMAGE:-gitea.blyzer.com.br/blyzer/dtf-web}:${IMAGE_TAG:-latest}
environment:
WEB_INDEX: kanban.html
PUBLIC_HOST: ${KANBAN_DOMAIN:?set KANBAN_DOMAIN}
S3_PUBLIC_ENDPOINT: ${R2_ENDPOINT:?set R2_ENDPOINT}
networks: [backend]
ports:
- target: 8080
published: ${KANBAN_PORT:-18081}
protocol: tcp
mode: ingress
healthcheck:
test: [CMD-SHELL, 'wget -q --header="Host: $$PUBLIC_HOST" -O /dev/null http://127.0.0.1:8080/health']
interval: 15s
timeout: 5s
retries: 12
start_period: 15s
deploy:
replicas: 1
restart_policy: {condition: on-failure, delay: 5s}
configs:
clamd_config:
file: ./infra/clamd.conf
volumes:
postgres-data:
networks:
backend:
driver: overlay
internal: true
egress:
driver: overlay