cua-agent 0.4.10__py3-none-any.whl → 0.4.11__py3-none-any.whl

agent/cli.py

@@ -94,14 +94,14 @@ def print_action(action_type: str, details: Dict[str, Any], total_cost: float):
     # Format action details
     args_str = ""
     if action_type == "click" and "x" in details and "y" in details:
-        args_str = f"({details['x']}, {details['y']})"
+        args_str = f"_{details['button']}({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']}'"
+        args_str = f'("{text}")'
+    elif action_type == "key" and "text" in details:
+        args_str = f"('{details['text']}')"
     elif action_type == "scroll" and "x" in details and "y" in details:
         args_str = f"({details['x']}, {details['y']})"
     

agent/computer_handler.py

@@ -3,7 +3,7 @@ Computer handler implementation for OpenAI computer-use-preview protocol.
 """
 
 import base64
-from typing import Dict, List, Any, Literal, Union
+from typing import Dict, List, Any, Literal, Union, Optional
 from .types import Computer
 
 
@@ -14,11 +14,13 @@ class OpenAIComputerHandler:
         """Initialize with a computer interface (from tool schema)."""
         self.interface = computer_interface
     
+    # ==== Computer-Use-Preview Action Space ==== 
+
     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()
@@ -94,6 +96,14 @@ class OpenAIComputerHandler:
         # For now, return empty string
         return ""
 
+    # ==== Anthropic Computer Action Space ==== 
+    async def left_mouse_down(self, x: Optional[int] = None, y: Optional[int] = None) -> None:
+        """Left mouse down at coordinates."""
+        await self.interface.mouse_down(x, y, button="left")
+    
+    async def left_mouse_up(self, x: Optional[int] = None, y: Optional[int] = None) -> None:
+        """Left mouse up at coordinates."""
+        await self.interface.mouse_up(x, y, button="left")
 
 def acknowledge_safety_check_callback(message: str, allow_always: bool = False) -> bool:
     """Safety check callback for user acknowledgment."""