FabledCurator/docker-compose.single.yml

# FabledCurator in three containers — the install path.
#
#     docker compose -f docker-compose.single.yml up -d
#
# Milestone 422 step 5. FabledCurator runs web and every worker lane inside
# ONE container, with Postgres and Redis beside it. How much work each lane
# does is then a dial in the web UI (Settings -> Activity -> Worker lanes),
# live, with no compose edit and no restart.
#
# THE MULTI-SERVICE STACK IS NOT REPLACED. `docker-compose.yml` still runs the
# five app services separately and is the right shape for a Swarm deployment
# spread across hosts, where per-service rolling rollback and placement
# constraints matter. This file is the adopter path: one box, one command.
#
# What consolidating costs, stated here rather than discovered later:
#   - Everything shares one host, so there is no spreading work across nodes.
#   - Rollback is all-or-nothing; there is no rolling back `web` alone.
#   - One stop timeout for the whole container, sized to the slowest lane.
#
# NOT a cost, recorded so it is not rediscovered and raised again: the
# multi-service stack mounts /images:ro on ml-worker and one container cannot
# mount one path two ways. Operator ruled that a non-issue (2026-09-22) — it
# is the same codebase either way.
#
# FabledCurator has no authentication. Whatever can reach ${PORT} is an
# administrator, including over the stored platform session cookies. Do not
# publish this port beyond a network you trust — see "Before you expose it"
# in README.md.

services:
  redis:
    image: redis:7-alpine
    volumes:
      - redis_data:/data
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5
    restart: unless-stopped

  postgres:
    image: pgvector/pgvector:pg16
    environment:
      POSTGRES_USER: ${DB_USER:-curator}
      POSTGRES_PASSWORD: ${DB_PASSWORD:-postgres}
      POSTGRES_DB: ${DB_NAME:-curator}
    volumes:
      - postgres_data:/var/lib/postgresql/data
    # pgvector index builds and the gallery's TABLESAMPLE reads both want more
    # shared memory than docker's 64MB default.
    shm_size: 512m
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${DB_USER:-curator} -d ${DB_NAME:-curator}"]
      interval: 10s
      timeout: 5s
      retries: 5
    restart: unless-stopped

  fabledcurator:
    image: git.fabledsword.com/bvandeusen/fabledcurator:latest
    # No `command:`. Everything — hypercorn plus one celery process per lane
    # under supervisord — is what the image does by default, and supervisord's
    # config is generated from the application's own lane table so the two
    # cannot disagree. `command: ["all"]` still works and means the same thing.
    # tini as PID 1, in front of supervisord. supervisord reaps its own
    # children, but a container's PID 1 also inherits orphans from anywhere
    # below — celery's prefork pool and gallery-dl's subprocesses both make
    # them. Without this they accumulate as zombies for the life of the
    # container.
    init: true
    # Sized to the SLOWEST lane, not the average. maintenance_long runs DB
    # backups, library audits and translation backfill, and gets 180s to
    # finish a chunk; the lanes stop in parallel, so this covers the max
    # rather than their sum. Below this, a routine restart becomes a SIGKILL
    # mid-backup — which is recoverable (the work is chunked and idempotent)
    # but wastes however long it had run.
    stop_grace_period: 200s
    # BOTH halves: hypercorn answers AND every configured lane is answering
    # the broker. A web-only check would report a healthy container while
    # every lane inside it had crashed — the failure mode consolidation
    # creates, since docker can no longer see the lanes as separate services.
    healthcheck:
      test: ["CMD", "python", "-m", "backend.app.scripts.healthcheck_all"]
      interval: 30s
      timeout: 15s
      retries: 3
      # Covers alembic + hypercorn boot + four celery workers registering.
      start_period: 90s
    environment:
      DB_USER: ${DB_USER:-curator}
      DB_PASSWORD: ${DB_PASSWORD:-postgres}
      DB_HOST: postgres
      DB_PORT: "5432"
      DB_NAME: ${DB_NAME:-curator}
      CELERY_BROKER_URL: redis://redis:6379/0
      CELERY_RESULT_BACKEND: redis://redis:6379/0
      SECRET_KEY: ${SECRET_KEY:-change-me-before-you-expose-this}
      EXTENSION_API_KEY: ${EXTENSION_API_KEY:-}
      LOG_LEVEL: ${LOG_LEVEL:-INFO}
    ports:
      - "${PORT:-8080}:8080"
    volumes:
      - ${IMAGES_DIR:-./images}:/images
      # Read-only. The filesystem scan copies out of here and never writes to
      # it, so a mistake cannot reach the source library.
      - ${IMPORT_DIR:-./import}:/import:ro
    depends_on:
      postgres: { condition: service_healthy }
      redis: { condition: service_healthy }
    restart: unless-stopped

volumes:
  redis_data:
  postgres_data: