Merge pull request #62 from trycua/fix/cua-lint

Add dev container, fix lints

Author: f-trycua

.dockerignore

@@ -0,0 +1,37 @@
+# Version control
+.git
+.github
+.gitignore
+
+# Environment and cache
+.venv
+.env
+.env.local
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+.pytest_cache
+.pdm-build
+
+# Distribution / packaging
+dist
+build
+*.egg-info
+
+# Development
+.vscode
+.idea
+*.swp
+*.swo
+
+# Docs
+docs/site
+
+# Notebooks
+notebooks/.ipynb_checkpoints
+
+# Docker
+Dockerfile
+.dockerignore 

Dockerfile

@@ -0,0 +1,55 @@
+FROM python:3.11-slim
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PIP_NO_CACHE_DIR=1 \
+    PIP_DISABLE_PIP_VERSION_CHECK=1 \
+    PYTHONPATH="/app/libs/core:/app/libs/computer:/app/libs/agent:/app/libs/som:/app/libs/pylume:/app/libs/computer-server"
+
+# Install system dependencies for ARM architecture
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    git \
+    build-essential \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    libxcb-xinerama0 \
+    libxkbcommon-x11-0 \
+    cmake \
+    pkg-config \
+    curl \
+    iputils-ping \
+    net-tools \
+    sed \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set working directory
+WORKDIR /app
+
+# Copy the entire project temporarily
+# We'll mount the real source code over this at runtime
+COPY . /app/
+
+# Create a simple .env.local file for build.sh
+RUN echo "PYTHON_BIN=python" > /app/.env.local
+
+# Modify build.sh to skip virtual environment creation
+RUN sed -i 's/python -m venv .venv/echo "Skipping venv creation in Docker"/' /app/scripts/build.sh && \
+    sed -i 's/source .venv\/bin\/activate/echo "Skipping venv activation in Docker"/' /app/scripts/build.sh && \
+    sed -i 's/find . -type d -name ".venv" -exec rm -rf {} +/echo "Skipping .venv removal in Docker"/' /app/scripts/build.sh && \
+    chmod +x /app/scripts/build.sh
+
+# Run the build script to install dependencies
+RUN cd /app && ./scripts/build.sh
+
+# Clean up the source files now that dependencies are installed
+# When we run the container, we'll mount the actual source code
+RUN rm -rf /app/* /app/.??*
+
+# Note: This Docker image doesn't contain the lume executable (macOS-specific)
+# Instead, it relies on connecting to a lume server running on the host machine
+# via host.docker.internal:3000
+
+# Default command
+CMD ["bash"] 

docs/Developer-Guide.md

@@ -4,24 +4,29 @@
 
 The project is organized as a monorepo with these main packages:
 - `libs/core/` - Base package with telemetry support
-- `libs/pylume/` - Python bindings for Lume
-- `libs/computer/` - Core computer interaction library
+- `libs/computer/` - Computer-use interface (CUI) library
 - `libs/agent/` - AI agent library with multi-provider support
-- `libs/som/` - Computer vision and NLP processing library (formerly omniparser)
-- `libs/computer-server/` - Server implementation for computer control
-- `libs/lume/` - Swift implementation for enhanced macOS integration
+- `libs/som/` - Set-of-Mark parser
+- `libs/computer-server/` - Server component for VM
+- `libs/lume/` - Lume CLI
+- `libs/pylume/` - Python bindings for Lume
 
 Each package has its own virtual environment and dependencies, managed through PDM.
 
 ### Local Development Setup
 
-1. Clone the repository:
+1. Install Lume CLI:
+```bash
+/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/lume/scripts/install.sh)"
+```
+
+2. Clone the repository:
 ```bash
 git clone https://github.com/trycua/cua.git
 cd cua
 ```
 
-2. Create a `.env.local` file in the root directory with your API keys:
+3. Create a `.env.local` file in the root directory with your API keys:
 ```bash
 # Required for Anthropic provider
 ANTHROPIC_API_KEY=your_anthropic_key_here
@@ -30,7 +35,7 @@ ANTHROPIC_API_KEY=your_anthropic_key_here
 OPENAI_API_KEY=your_openai_key_here
 ```
 
-3. Run the build script to set up all packages:
+4. Run the build script to set up all packages:
 ```bash
 ./scripts/build.sh
 ```
@@ -41,9 +46,9 @@ This will:
 - Set up the correct Python path
 - Install development tools
 
-4. Open the workspace in VSCode or Cursor:
+5. Open the workspace in VSCode or Cursor:
 ```bash
-# Using VSCode or Cursor
+# For Cua Python development
 code .vscode/py.code-workspace
 
 # For Lume (Swift) development
@@ -56,9 +61,55 @@ Using the workspace file is strongly recommended as it:
 - Enables debugging configurations
 - Maintains consistent settings across packages
 
+### Docker Development Environment
+
+As an alternative to running directly on your host machine, you can use Docker for development. This approach has several advantages:
+
+- Ensures consistent development environment across different machines
+- Isolates dependencies from your host system
+- Works well for cross-platform development
+- Avoids conflicts with existing Python installations
+
+#### Prerequisites
+
+- Docker installed on your machine
+- Lume server running on your host (port 3000): `lume serve`
+
+#### Setup and Usage
+
+1. Build the development Docker image:
+```bash
+./scripts/run-docker-dev.sh build
+```
+
+2. Run an example in the container:
+```bash
+./scripts/run-docker-dev.sh run computer_examples.py
+```
+
+3. Get an interactive shell in the container:
+```bash
+./scripts/run-docker-dev.sh run --interactive
+```
+
+4. Stop any running containers:
+```bash
+./scripts/run-docker-dev.sh stop
+```
+
+#### How it Works
+
+The Docker development environment:
+- Installs all required Python dependencies in the container
+- Mounts your source code from the host at runtime
+- Automatically configures the connection to use host.docker.internal:3000 for accessing the Lume server on your host machine
+- Preserves your code changes without requiring rebuilds (source code is mounted as a volume)
+
+> **Note**: The Docker container doesn't include the macOS-specific Lume executable. Instead, it connects to the Lume server running on your host machine via host.docker.internal:3000. Make sure to start the Lume server on your host before running examples in the container.
+
 ### Cleanup and Reset
 
-If you need to clean up the environment and start fresh:
+If you need to clean up the environment (non-docker) and start fresh:
 
 ```bash
 ./scripts/cleanup.sh

examples/agent_examples.py

@@ -5,13 +5,13 @@
 import logging
 import traceback
 from pathlib import Path
-from datetime import datetime
 import signal
 
 from computer import Computer
 
 # Import the unified agent class and types
-from agent import ComputerAgent, AgentLoop, LLMProvider, LLM
+from agent import AgentLoop, LLMProvider, LLM
+from agent.core.computer_agent import ComputerAgent
 
 # Import utility functions
 from utils import load_dotenv_files, handle_sigint
@@ -23,18 +23,19 @@
 
 async def run_omni_agent_example():
     """Run example of using the ComputerAgent with OpenAI and Omni provider."""
-    print(f"\n=== Example: ComputerAgent with OpenAI and Omni provider ===")
+    print("\n=== Example: ComputerAgent with OpenAI and Omni provider ===")
+
     try:
         # Create Computer instance with default parameters
         computer = Computer(verbosity=logging.DEBUG)
 
         # Create agent with loop and provider
         agent = ComputerAgent(
             computer=computer,
-            # loop=AgentLoop.OMNI,
-            loop=AgentLoop.ANTHROPIC,
-            # model=LLM(provider=LLMProvider.OPENAI, name="gpt-4.5-preview"),
-            model=LLM(provider=LLMProvider.ANTHROPIC, name="claude-3-7-sonnet-20250219"),
+            # loop=AgentLoop.ANTHROPIC,
+            loop=AgentLoop.OMNI,
+            model=LLM(provider=LLMProvider.OPENAI, name="gpt-4.5-preview"),
+            # model=LLM(provider=LLMProvider.ANTHROPIC, name="claude-3-7-sonnet-20250219"),
             save_trajectory=True,
             trajectory_dir=str(Path("trajectories")),
             only_n_most_recent_images=3,
@@ -69,14 +70,15 @@ async def run_omni_agent_example():
                 print(f"Task {i} completed")
 
     except Exception as e:
-        logger.error(f"Error in run_anthropic_agent_example: {e}")
+        logger.error(f"Error in run_omni_agent_example: {e}")
         traceback.print_exc()
         raise
     finally:
         # Clean up resources
         if computer and computer._initialized:
             try:
-                await computer.stop()
+                # await computer.stop()
+                pass
             except Exception as e:
                 logger.warning(f"Error stopping computer: {e}")
 

examples/computer_examples.py

@@ -28,6 +28,8 @@
 async def main():
     try:
         print("\n=== Using direct initialization ===")
+
+        # Create computer with configured host
         computer = Computer(
             display="1024x768",  # Higher resolution
             memory="8GB",  # More memory
@@ -48,10 +50,10 @@ async def main():
             print(f"Accessibility tree: {accessibility_tree}")
 
             # Screen Actions Examples
-            print("\n===  Screen Actions ===")
-            screenshot = await computer.interface.screenshot()
-            with open("screenshot_direct.png", "wb") as f:
-                f.write(screenshot)
+            # print("\n===  Screen Actions ===")
+            # screenshot = await computer.interface.screenshot()
+            # with open("screenshot_direct.png", "wb") as f:
+            #     f.write(screenshot)
 
             screen_size = await computer.interface.get_screen_size()
             print(f"Screen size: {screen_size}")

libs/agent/agent/__init__.py

@@ -48,9 +48,7 @@
     # Other issues with telemetry
     logger.warning(f"Error initializing telemetry: {e}")
 
-from .core.factory import AgentFactory
-from .core.agent import ComputerAgent
 from .providers.omni.types import LLMProvider, LLM
-from .types.base import Provider, AgentLoop
+from .types.base import AgentLoop
 
-__all__ = ["AgentFactory", "Provider", "ComputerAgent", "AgentLoop", "LLMProvider", "LLM"]
+__all__ = ["AgentLoop", "LLMProvider", "LLM"]

libs/agent/agent/core/__init__.py

@@ -1,6 +1,5 @@
 """Core agent components."""
 
-from .base_agent import BaseComputerAgent
 from .loop import BaseLoop
 from .messages import (
     create_user_message,
@@ -12,7 +11,7 @@
     ImageRetentionConfig,
 )
 from .callbacks import (
-    CallbackManager, 
+    CallbackManager,
     CallbackHandler,
     BaseCallbackManager,
     ContentCallback,
@@ -21,9 +20,8 @@
 )
 
 __all__ = [
-    "BaseComputerAgent", 
-    "BaseLoop", 
-    "CallbackManager", 
+    "BaseLoop",
+    "CallbackManager",
     "CallbackHandler",
     "BaseMessageManager",
     "ImageRetentionConfig",