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

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"]