services: app: image: git.fabledsword.com/bvandeusen/fabledassistant:latest environment: DATABASE_URL: "postgresql+asyncpg://fabled:${DB_PASSWORD}@db:5432/fabledassistant" SECRET_KEY: "${SECRET_KEY}" OLLAMA_URL: "http://ollama:11434" OLLAMA_MODEL: "${OLLAMA_MODEL:-llama3.1}" LOG_LEVEL: "${LOG_LEVEL:-INFO}" TRUST_PROXY_HEADERS: "true" SECURE_COOKIES: "true" networks: - fabledassistant_backend healthcheck: test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:5000/api/health')"] interval: 30s timeout: 10s retries: 3 start_period: 30s deploy: restart_policy: condition: on-failure max_attempts: 5 db: image: postgres:16-alpine stop_grace_period: 120s volumes: - pgdata:/var/lib/postgresql/data environment: POSTGRES_USER: fabled POSTGRES_PASSWORD: "${DB_PASSWORD}" POSTGRES_DB: fabledassistant networks: - fabledassistant_backend # Lenient by design: a transient host exec/healthcheck stall (incident: # runc setns failures -> "unhealthy" -> SIGKILL -> crash loop) must never # escalate to killing the DB. Health here only gates app startup order. healthcheck: test: ["CMD-SHELL", "pg_isready -U fabled"] interval: 30s timeout: 10s retries: 10 start_period: 180s deploy: restart_policy: condition: on-failure delay: 10s max_attempts: 0 window: 120s ollama: image: ollama/ollama volumes: - ollama_models:/root/.ollama networks: - fabledassistant_backend environment: OLLAMA_MAX_LOADED_MODELS: "2" OLLAMA_KEEP_ALIVE: "30m" OLLAMA_FLASH_ATTENTION: "1" healthcheck: test: ["CMD-SHELL", "ollama list || exit 1"] interval: 30s timeout: 10s retries: 5 start_period: 30s deploy: placement: constraints: - node.role == worker resources: reservations: devices: - driver: nvidia count: all capabilities: [gpu] restart_policy: condition: on-failure max_attempts: 5 volumes: pgdata: ollama_models: networks: fabledassistant_backend: driver: overlay