cua-agent 0.4.10__tar.gz → 0.4.12__tar.gz

{cua_agent-0.4.10 → cua_agent-0.4.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cua-agent
-Version: 0.4.10
+Version: 0.4.12
 Summary: CUA (Computer Use) Agent for AI-driven computer interaction
 Author-Email: TryCua <gh@trycua.com>
 Requires-Python: >=3.11
@@ -25,16 +25,24 @@ Provides-Extra: uitars
 Provides-Extra: uitars-mlx
 Requires-Dist: mlx-vlm>=0.1.27; sys_platform == "darwin" and extra == "uitars-mlx"
 Provides-Extra: uitars-hf
+Requires-Dist: accelerate; extra == "uitars-hf"
+Requires-Dist: torch; extra == "uitars-hf"
 Requires-Dist: transformers>=4.54.0; extra == "uitars-hf"
 Provides-Extra: ui
 Requires-Dist: gradio>=5.23.3; extra == "ui"
 Requires-Dist: python-dotenv>=1.0.1; extra == "ui"
 Provides-Extra: cli
 Requires-Dist: yaspin>=3.1.0; extra == "cli"
+Provides-Extra: glm45v-hf
+Requires-Dist: accelerate; extra == "glm45v-hf"
+Requires-Dist: torch; extra == "glm45v-hf"
+Requires-Dist: transformers-v4.55.0-GLM-4.5V-preview; extra == "glm45v-hf"
 Provides-Extra: all
 Requires-Dist: ultralytics>=8.0.0; extra == "all"
 Requires-Dist: cua-som<0.2.0,>=0.1.0; extra == "all"
 Requires-Dist: mlx-vlm>=0.1.27; sys_platform == "darwin" and extra == "all"
+Requires-Dist: accelerate; extra == "all"
+Requires-Dist: torch; extra == "all"
 Requires-Dist: transformers>=4.54.0; extra == "all"
 Requires-Dist: gradio>=5.23.3; extra == "all"
 Requires-Dist: python-dotenv>=1.0.1; extra == "all"
@@ -80,6 +88,7 @@ pip install "cua-agent[omni]"          # Omniparser + any LLM support
 pip install "cua-agent[uitars]"        # UI-TARS
 pip install "cua-agent[uitars-mlx]"    # UI-TARS + MLX support
 pip install "cua-agent[uitars-hf]"     # UI-TARS + Huggingface support
+pip install "cua-agent[glm45v-hf]"     # GLM-4.5V + Huggingface support
 pip install "cua-agent[ui]"            # Gradio UI support
 ```
 

{cua_agent-0.4.10 → cua_agent-0.4.12}/README.md

@@ -37,6 +37,7 @@ pip install "cua-agent[omni]"          # Omniparser + any LLM support
 pip install "cua-agent[uitars]"        # UI-TARS
 pip install "cua-agent[uitars-mlx]"    # UI-TARS + MLX support
 pip install "cua-agent[uitars-hf]"     # UI-TARS + Huggingface support
+pip install "cua-agent[glm45v-hf]"     # GLM-4.5V + Huggingface support
 pip install "cua-agent[ui]"            # Gradio UI support
 ```
 

{cua_agent-0.4.10 → cua_agent-0.4.12}/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']})"
     

{cua_agent-0.4.10 → cua_agent-0.4.12}/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."""

{cua_agent-0.4.10 → cua_agent-0.4.12}/agent/loops/__init__.py

@@ -9,5 +9,6 @@ from . import uitars
 from . import omniparser
 from . import gta1
 from . import composed_grounded
+from . import glm45v
 
-__all__ = ["anthropic", "openai", "uitars", "omniparser", "gta1", "composed_grounded"]
+__all__ = ["anthropic", "openai", "uitars", "omniparser", "gta1", "composed_grounded", "glm45v"]