Timmy-time-dashboard/docker-compose.yml

# ── Development Compose ───────────────────────────────────────────────────────
#
# Services
#   dashboard     FastAPI app (always on)
#   celery-worker (behind 'celery' profile)
#   openfang      (behind 'openfang' profile)
#
# Usage
#   make docker-build    build the image
#   make docker-up       start dashboard
#   make docker-down     stop everything
#   make docker-logs     tail logs
#
# ── Security note ─────────────────────────────────────────────────────────
# Override user per-environment — see docker-compose.dev.yml / docker-compose.prod.yml
#
# ── Ollama host access ──────────────────────────────────────────────────────
# By default OLLAMA_URL points to http://host.docker.internal:11434 which
# reaches Ollama running on the Docker host (macOS/Windows native).
#
# Linux:  The extra_hosts entry maps host.docker.internal → host-gateway,
#         which resolves to the host IP on Docker 20.10+.

services:

  # ── Dashboard (FastAPI) ──────────────────────────────────────────────────
  dashboard:
    build: .
    image: timmy-time:latest
    container_name: timmy-dashboard
    user: ""  # see security note above
    ports:
      - "8000:8000"
    volumes:
      - timmy-data:/app/data
      - ./src:/app/src        # live-reload: source changes reflect immediately
      - ./static:/app/static  # live-reload: CSS/asset changes reflect immediately
    environment:
      DEBUG: "true"
      OLLAMA_URL: "${OLLAMA_URL:-http://host.docker.internal:11434}"
      # Grok (xAI) — opt-in premium cloud backend
      GROK_ENABLED: "${GROK_ENABLED:-false}"
      XAI_API_KEY: "${XAI_API_KEY:-}"
      GROK_DEFAULT_MODEL: "${GROK_DEFAULT_MODEL:-grok-3-fast}"
      # vLLM backend — set TIMMY_LLM_BACKEND=vllm to activate
      TIMMY_LLM_BACKEND: "${TIMMY_LLM_BACKEND:-ollama}"
      VLLM_URL: "${VLLM_URL:-http://localhost:8001}"
      VLLM_MODEL: "${VLLM_MODEL:-Qwen/Qwen2.5-14B-Instruct}"
    extra_hosts:
      - "host.docker.internal:host-gateway"  # Linux: maps to host IP
    networks:
      - timmy-net
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 30s

  # ── Celery Worker — background task processing ──────────────────────────
  celery-worker:
    build: .
    image: timmy-time:latest
    container_name: timmy-celery-worker
    user: ""
    command: ["celery", "-A", "infrastructure.celery.app", "worker", "--loglevel=info", "--concurrency=2"]
    volumes:
      - timmy-data:/app/data
      - ./src:/app/src
    environment:
      OLLAMA_URL: "${OLLAMA_URL:-http://host.docker.internal:11434}"
    extra_hosts:
      - "host.docker.internal:host-gateway"
    networks:
      - timmy-net
    restart: unless-stopped
    profiles:
      - celery

  # ── vLLM — high-throughput inference server (GPU optional) ──────────────
  # Requires the 'vllm' profile: docker compose --profile vllm up
  #
  # GPU (NVIDIA):  set VLLM_MODEL and ensure nvidia-container-toolkit is installed.
  # CPU-only:      add --device cpu to VLLM_EXTRA_ARGS (slower, but works anywhere).
  #
  # The dashboard reaches vLLM at http://vllm:8001 (inside timmy-net).
  # Set VLLM_URL=http://vllm:8001 in the dashboard environment when using this service.
  vllm:
    image: vllm/vllm-openai:latest
    container_name: timmy-vllm
    profiles:
      - vllm
    ports:
      - "8001:8001"
    environment:
      # Model to load — override with VLLM_MODEL env var
      VLLM_MODEL: "${VLLM_MODEL:-Qwen/Qwen2.5-7B-Instruct}"
    command: >
      --model ${VLLM_MODEL:-Qwen/Qwen2.5-7B-Instruct}
      --port 8001
      --host 0.0.0.0
      ${VLLM_EXTRA_ARGS:-}
    volumes:
      - vllm-cache:/root/.cache/huggingface
    networks:
      - timmy-net
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8001/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 120s
    # GPU support — uncomment to enable NVIDIA GPU passthrough
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: all
    #           capabilities: [gpu]

  # ── OpenFang — vendored agent runtime sidecar ────────────────────────────
  openfang:
    build:
      context: .
      dockerfile: docker/Dockerfile.openfang
    image: timmy-openfang:latest
    container_name: timmy-openfang
    profiles:
      - openfang
    environment:
      OLLAMA_URL: "${OLLAMA_URL:-http://host.docker.internal:11434}"
      OPENFANG_DATA_DIR: "/app/data"
    extra_hosts:
      - "host.docker.internal:host-gateway"
    volumes:
      - openfang-data:/app/data
    networks:
      - timmy-net
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 15s

# ── Volumes ──────────────────────────────────────────────────────────────────
volumes:
  timmy-data:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: "${PWD}/data"
  openfang-data:
    driver: local
  vllm-cache:
    driver: local

# ── Internal network ────────────────────────────────────────────────────────
networks:
  timmy-net:
    driver: bridge