cua-agent 0.3.2__py3-none-any.whl → 0.4.0b1__py3-none-any.whl

agent/cli.py

@@ -0,0 +1,290 @@
+"""
+CLI chat interface for agent - Computer Use Agent
+
+Usage:
+    python -m agent.cli <model_string>
+    
+Examples:
+    python -m agent.cli openai/computer-use-preview
+    python -m agent.cli anthropic/claude-3-5-sonnet-20241022
+    python -m agent.cli omniparser+anthropic/claude-3-5-sonnet-20241022
+"""
+
+import asyncio
+import argparse
+import os
+import sys
+import json
+from typing import List, Dict, Any
+import dotenv
+from yaspin import yaspin
+
+# Load environment variables
+dotenv.load_dotenv()
+
+# Color codes for terminal output
+class Colors:
+    RESET = '\033[0m'
+    BOLD = '\033[1m'
+    DIM = '\033[2m'
+    
+    # Text colors
+    RED = '\033[31m'
+    GREEN = '\033[32m'
+    YELLOW = '\033[33m'
+    BLUE = '\033[34m'
+    MAGENTA = '\033[35m'
+    CYAN = '\033[36m'
+    WHITE = '\033[37m'
+    GRAY = '\033[90m'
+    
+    # Background colors
+    BG_RED = '\033[41m'
+    BG_GREEN = '\033[42m'
+    BG_YELLOW = '\033[43m'
+    BG_BLUE = '\033[44m'
+
+
+def print_colored(text: str, color: str = "", bold: bool = False, dim: bool = False, end: str = "\n"):
+    """Print colored text to terminal."""
+    prefix = ""
+    if bold:
+        prefix += Colors.BOLD
+    if dim:
+        prefix += Colors.DIM
+    if color:
+        prefix += color
+    
+    print(f"{prefix}{text}{Colors.RESET}", end=end)
+
+
+def print_action(action_type: str, details: Dict[str, Any]):
+    """Print computer action with nice formatting."""
+    # Format action details
+    args_str = ""
+    if action_type == "click" and "x" in details and "y" in details:
+        args_str = f"({details['x']}, {details['y']})"
+    elif action_type == "type" and "text" in details:
+        text = details["text"]
+        if len(text) > 50:
+            text = text[:47] + "..."
+        args_str = f'"{text}"'
+    elif action_type == "key" and "key" in details:
+        args_str = f"'{details['key']}'"
+    elif action_type == "scroll" and "x" in details and "y" in details:
+        args_str = f"({details['x']}, {details['y']})"
+    
+    print_colored(f"🛠️  {action_type}{args_str}", dim=True)
+
+
+def print_welcome(model: str, agent_loop: str, container_name: str):
+    """Print welcome message."""
+    print_colored(f"Connected to {container_name} ({model}, {agent_loop})")
+    print_colored("Type 'exit' to quit.", dim=True)
+
+async def ainput(prompt: str = ""):
+    return await asyncio.to_thread(input, prompt)
+
+async def chat_loop(agent, model: str, container_name: str):
+    """Main chat loop with the agent."""
+    print_welcome(model, agent.agent_loop.__name__, container_name)
+    
+    history = []
+    
+    while True:
+        # Get user input with prompt
+        print_colored("> ", end="")
+        user_input = await ainput()
+        
+        if user_input.lower() in ['exit', 'quit', 'q']:
+            print_colored("\n👋 Goodbye!")
+            break
+            
+        if not user_input:
+            continue
+            
+        # Add user message to history
+        history.append({"role": "user", "content": user_input})
+        
+        # Stream responses from the agent with spinner
+        with yaspin(text="Thinking...", spinner="line", attrs=["dark"]) as spinner:
+            spinner.hide()
+            
+            async for result in agent.run(history):
+                # Add agent responses to history
+                history.extend(result.get("output", []))
+                
+                # Process and display the output
+                for item in result.get("output", []):
+                    if item.get("type") == "message":
+                        # Display agent text response
+                        content = item.get("content", [])
+                        for content_part in content:
+                            if content_part.get("text"):
+                                text = content_part.get("text", "").strip()
+                                if text:
+                                    spinner.hide()
+                                    print_colored(text)
+                    
+                    elif item.get("type") == "computer_call":
+                        # Display computer action
+                        action = item.get("action", {})
+                        action_type = action.get("type", "")
+                        if action_type:
+                            spinner.hide()
+                            print_action(action_type, action)
+                            spinner.text = f"Performing {action_type}..."
+                            spinner.show()
+                    
+                    elif item.get("type") == "function_call":
+                        # Display function call
+                        function_name = item.get("name", "")
+                        spinner.hide()
+                        print_colored(f"🔧 Calling function: {function_name}", dim=True)
+                        spinner.text = f"Calling {function_name}..."
+                        spinner.show()
+                    
+                    elif item.get("type") == "function_call_output":
+                        # Display function output (dimmed)
+                        output = item.get("output", "")
+                        if output and len(output.strip()) > 0:
+                            spinner.hide()
+                            print_colored(f"📤 {output}", dim=True)
+            
+            spinner.hide()
+        
+
+async def main():
+    """Main CLI function."""
+    parser = argparse.ArgumentParser(
+        description="CUA Agent CLI - Interactive computer use assistant",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  python -m agent.cli openai/computer-use-preview
+  python -m agent.cli anthropic/claude-3-5-sonnet-20241022
+  python -m agent.cli omniparser+anthropic/claude-3-5-sonnet-20241022
+  python -m agent.cli huggingface-local/ByteDance-Seed/UI-TARS-1.5-7B
+        """
+    )
+    
+    parser.add_argument(
+        "model",
+        help="Model string (e.g., 'openai/computer-use-preview', 'anthropic/claude-3-5-sonnet-20241022')"
+    )
+    
+    parser.add_argument(
+        "--images",
+        type=int,
+        default=3,
+        help="Number of recent images to keep in context (default: 3)"
+    )
+    
+    parser.add_argument(
+        "--trajectory",
+        action="store_true",
+        help="Save trajectory for debugging"
+    )
+    
+    parser.add_argument(
+        "--budget",
+        type=float,
+        help="Maximum budget for the session (in dollars)"
+    )
+    
+    parser.add_argument(
+        "--verbose",
+        action="store_true",
+        help="Enable verbose logging"
+    )
+    
+    args = parser.parse_args()
+    
+    # Check for required environment variables
+    container_name = os.getenv("CUA_CONTAINER_NAME")
+    cua_api_key = os.getenv("CUA_API_KEY")
+    
+    # Prompt for missing environment variables
+    if not container_name:
+        print_colored("CUA_CONTAINER_NAME not set.", dim=True)
+        print_colored("You can get a CUA container at https://www.trycua.com/", dim=True)
+        container_name = input("Enter your CUA container name: ").strip()
+        if not container_name:
+            print_colored("❌ Container name is required.")
+            sys.exit(1)
+    
+    if not cua_api_key:
+        print_colored("CUA_API_KEY not set.", dim=True)
+        cua_api_key = input("Enter your CUA API key: ").strip()
+        if not cua_api_key:
+            print_colored("❌ API key is required.")
+            sys.exit(1)
+    
+    # Check for provider-specific API keys based on model
+    provider_api_keys = {
+        "openai/": "OPENAI_API_KEY",
+        "anthropic/": "ANTHROPIC_API_KEY",
+        "omniparser+": "OPENAI_API_KEY",
+        "omniparser+": "ANTHROPIC_API_KEY",
+    }
+    
+    # Find matching provider and check for API key
+    for prefix, env_var in provider_api_keys.items():
+        if args.model.startswith(prefix):
+            if not os.getenv(env_var):
+                print_colored(f"{env_var} not set.", dim=True)
+                api_key = input(f"Enter your {env_var.replace('_', ' ').title()}: ").strip()
+                if not api_key:
+                    print_colored(f"❌ {env_var.replace('_', ' ').title()} is required.")
+                    sys.exit(1)
+                # Set the environment variable for the session
+                os.environ[env_var] = api_key
+            break
+    
+    # Import here to avoid import errors if dependencies are missing
+    try:
+        from agent import ComputerAgent
+        from computer import Computer
+    except ImportError as e:
+        print_colored(f"❌ Import error: {e}", Colors.RED, bold=True)
+        print_colored("Make sure agent and computer libraries are installed.", Colors.YELLOW)
+        sys.exit(1)
+    
+    # Create computer instance
+    async with Computer(
+        os_type="linux",
+        provider_type="cloud",
+        name=container_name,
+        api_key=cua_api_key
+    ) as computer:
+        
+        # Create agent
+        agent_kwargs = {
+            "model": args.model,
+            "tools": [computer],
+            "only_n_most_recent_images": args.images,
+            "verbosity": 20 if args.verbose else 30,  # DEBUG vs WARNING
+        }
+        
+        if args.trajectory:
+            agent_kwargs["trajectory_dir"] = "trajectories"
+        
+        if args.budget:
+            agent_kwargs["max_trajectory_budget"] = {
+                "max_budget": args.budget,
+                "raise_error": True,
+                "reset_after_each_run": False
+            }
+        
+        agent = ComputerAgent(**agent_kwargs)
+        
+        # Start chat loop
+        await chat_loop(agent, args.model, container_name)
+
+
+
+if __name__ == "__main__":
+    try:
+        asyncio.run(main())
+    except (KeyboardInterrupt, EOFError) as _:
+        print_colored("\n\n👋 Goodbye!")

agent/computer_handler.py

@@ -0,0 +1,107 @@
+"""
+Computer handler implementation for OpenAI computer-use-preview protocol.
+"""
+
+import base64
+from typing import Dict, List, Any, Literal
+from .types import Computer
+
+
+class OpenAIComputerHandler:
+    """Computer handler that implements the Computer protocol using the computer interface."""
+    
+    def __init__(self, computer_interface):
+        """Initialize with a computer interface (from tool schema)."""
+        self.interface = computer_interface
+    
+    async def get_environment(self) -> Literal["windows", "mac", "linux", "browser"]:
+        """Get the current environment type."""
+        # For now, return a default - this could be enhanced to detect actual environment
+        return "windows"
+    
+    async def get_dimensions(self) -> tuple[int, int]:
+        """Get screen dimensions as (width, height)."""
+        screen_size = await self.interface.get_screen_size()
+        return screen_size["width"], screen_size["height"]
+    
+    async def screenshot(self) -> str:
+        """Take a screenshot and return as base64 string."""
+        screenshot_bytes = await self.interface.screenshot()
+        return base64.b64encode(screenshot_bytes).decode('utf-8')
+    
+    async def click(self, x: int, y: int, button: str = "left") -> None:
+        """Click at coordinates with specified button."""
+        if button == "left":
+            await self.interface.left_click(x, y)
+        elif button == "right":
+            await self.interface.right_click(x, y)
+        else:
+            # Default to left click for unknown buttons
+            await self.interface.left_click(x, y)
+    
+    async def double_click(self, x: int, y: int) -> None:
+        """Double click at coordinates."""
+        await self.interface.double_click(x, y)
+    
+    async def scroll(self, x: int, y: int, scroll_x: int, scroll_y: int) -> None:
+        """Scroll at coordinates with specified scroll amounts."""
+        await self.interface.move_cursor(x, y)
+        await self.interface.scroll(scroll_x, scroll_y)
+    
+    async def type(self, text: str) -> None:
+        """Type text."""
+        await self.interface.type_text(text)
+    
+    async def wait(self, ms: int = 1000) -> None:
+        """Wait for specified milliseconds."""
+        import asyncio
+        await asyncio.sleep(ms / 1000.0)
+    
+    async def move(self, x: int, y: int) -> None:
+        """Move cursor to coordinates."""
+        await self.interface.move_cursor(x, y)
+    
+    async def keypress(self, keys: List[str]) -> None:
+        """Press key combination."""
+        if len(keys) == 1:
+            await self.interface.press_key(keys[0])
+        else:
+            # Handle key combinations
+            await self.interface.hotkey(*keys)
+    
+    async def drag(self, path: List[Dict[str, int]]) -> None:
+        """Drag along specified path."""
+        if not path:
+            return
+        
+        # Start drag from first point
+        start = path[0]
+        await self.interface.mouse_down(start["x"], start["y"])
+        
+        # Move through path
+        for point in path[1:]:
+            await self.interface.move_cursor(point["x"], point["y"])
+        
+        # End drag at last point
+        end = path[-1]
+        await self.interface.mouse_up(end["x"], end["y"])
+    
+    async def get_current_url(self) -> str:
+        """Get current URL (for browser environments)."""
+        # This would need to be implemented based on the specific browser interface
+        # For now, return empty string
+        return ""
+
+
+def acknowledge_safety_check_callback(message: str) -> bool:
+    """Safety check callback for user acknowledgment."""
+    response = input(
+        f"Safety Check Warning: {message}\nDo you want to acknowledge and proceed? (y/n): "
+    ).lower()
+    return response.strip() == "y"
+
+
+def check_blocklisted_url(url: str) -> None:
+    """Check if URL is blocklisted (placeholder implementation)."""
+    # This would contain actual URL checking logic
+    pass

agent/decorators.py

@@ -0,0 +1,90 @@
+"""
+Decorators for agent - agent_loop decorator
+"""
+
+import asyncio
+import inspect
+from typing import Dict, List, Any, Callable, Optional
+from functools import wraps
+
+from .types import AgentLoopInfo
+
+# Global registry
+_agent_loops: List[AgentLoopInfo] = []
+
+def agent_loop(models: str, priority: int = 0):
+    """
+    Decorator to register an agent loop function.
+    
+    Args:
+        models: Regex pattern to match supported models
+        priority: Priority for loop selection (higher = more priority)
+    """
+    def decorator(func: Callable):
+        # Validate function signature
+        sig = inspect.signature(func)
+        required_params = {'messages', 'model'}
+        func_params = set(sig.parameters.keys())
+        
+        if not required_params.issubset(func_params):
+            missing = required_params - func_params
+            raise ValueError(f"Agent loop function must have parameters: {missing}")
+        
+        # Register the loop
+        loop_info = AgentLoopInfo(
+            func=func,
+            models_regex=models,
+            priority=priority
+        )
+        _agent_loops.append(loop_info)
+        
+        # Sort by priority (highest first)
+        _agent_loops.sort(key=lambda x: x.priority, reverse=True)
+        
+        @wraps(func)
+        async def wrapper(*args, **kwargs):
+            # Wrap the function in an asyncio.Queue for cancellation support
+            queue = asyncio.Queue()
+            task = None
+            
+            try:
+                # Create a task that can be cancelled
+                async def run_loop():
+                    try:
+                        result = await func(*args, **kwargs)
+                        await queue.put(('result', result))
+                    except Exception as e:
+                        await queue.put(('error', e))
+                
+                task = asyncio.create_task(run_loop())
+                
+                # Wait for result or cancellation
+                event_type, data = await queue.get()
+                
+                if event_type == 'error':
+                    raise data
+                return data
+                
+            except asyncio.CancelledError:
+                if task:
+                    task.cancel()
+                    try:
+                        await task
+                    except asyncio.CancelledError:
+                        pass
+                raise
+        
+        return wrapper
+    
+    return decorator
+
+def get_agent_loops() -> List[AgentLoopInfo]:
+    """Get all registered agent loops"""
+    return _agent_loops.copy()
+
+def find_agent_loop(model: str) -> Optional[AgentLoopInfo]:
+    """Find the best matching agent loop for a model"""
+    for loop_info in _agent_loops:
+        if loop_info.matches_model(model):
+            return loop_info
+    return None

agent/loops/__init__.py

@@ -0,0 +1,11 @@
+"""
+Agent loops for agent
+"""
+
+# Import the loops to register them
+from . import anthropic
+from . import openai
+from . import uitars
+from . import omniparser
+
+__all__ = ["anthropic", "openai", "uitars", "omniparser"]