cua-agent 0.4.33__tar.gz → 0.4.35__tar.gz

{cua_agent-0.4.33 → cua_agent-0.4.35}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cua-agent
-Version: 0.4.33
+Version: 0.4.35
 Summary: CUA (Computer Use) Agent for AI-driven computer interaction
 Author-Email: TryCua <gh@trycua.com>
 Requires-Python: >=3.12
@@ -18,6 +18,10 @@ Requires-Dist: certifi>=2024.2.2
 Requires-Dist: litellm>=1.74.12
 Provides-Extra: openai
 Provides-Extra: anthropic
+Provides-Extra: qwen
+Requires-Dist: qwen-vl-utils; extra == "qwen"
+Requires-Dist: qwen-agent; extra == "qwen"
+Requires-Dist: Pillow>=10.0.0; extra == "qwen"
 Provides-Extra: omni
 Requires-Dist: cua-som<0.2.0,>=0.1.0; extra == "omni"
 Provides-Extra: uitars
@@ -34,7 +38,7 @@ Requires-Dist: transformers-v4.55.0-GLM-4.5V-preview; extra == "glm45v-hf"
 Provides-Extra: opencua-hf
 Requires-Dist: accelerate; extra == "opencua-hf"
 Requires-Dist: torch; extra == "opencua-hf"
-Requires-Dist: transformers==4.53.0; extra == "opencua-hf"
+Requires-Dist: transformers>=4.53.0; extra == "opencua-hf"
 Requires-Dist: tiktoken>=0.11.0; extra == "opencua-hf"
 Requires-Dist: blobfile>=3.0.0; extra == "opencua-hf"
 Provides-Extra: internvl-hf
@@ -43,6 +47,10 @@ Requires-Dist: torch; extra == "internvl-hf"
 Requires-Dist: transformers>=4.55.0; extra == "internvl-hf"
 Requires-Dist: einops; extra == "internvl-hf"
 Requires-Dist: timm; extra == "internvl-hf"
+Provides-Extra: moondream3
+Requires-Dist: accelerate; extra == "moondream3"
+Requires-Dist: torch; extra == "moondream3"
+Requires-Dist: transformers>=4.55.0; extra == "moondream3"
 Provides-Extra: ui
 Requires-Dist: gradio>=5.23.3; extra == "ui"
 Requires-Dist: python-dotenv>=1.0.1; extra == "ui"
@@ -66,6 +74,9 @@ Requires-Dist: python-dotenv>=1.0.1; extra == "all"
 Requires-Dist: yaspin>=3.1.0; extra == "all"
 Requires-Dist: hud-python==0.4.52; extra == "all"
 Requires-Dist: google-genai>=1.41.0; extra == "all"
+Requires-Dist: qwen-vl-utils; extra == "all"
+Requires-Dist: qwen-agent; extra == "all"
+Requires-Dist: Pillow>=10.0.0; extra == "all"
 Description-Content-Type: text/markdown
 
 <div align="center">
@@ -78,10 +89,11 @@ Description-Content-Type: text/markdown
     </picture>
   </div>
 
-  [![Python](https://img.shields.io/badge/Python-333333?logo=python&logoColor=white&labelColor=333333)](#)
-  [![macOS](https://img.shields.io/badge/macOS-000000?logo=apple&logoColor=F0F0F0)](#)
-  [![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?&logo=discord&logoColor=white)](https://discord.com/invite/mVnXXpdE85)
-  [![PyPI](https://img.shields.io/pypi/v/cua-computer?color=333333)](https://pypi.org/project/cua-computer/)
+[![Python](https://img.shields.io/badge/Python-333333?logo=python&logoColor=white&labelColor=333333)](#)
+[![macOS](https://img.shields.io/badge/macOS-000000?logo=apple&logoColor=F0F0F0)](#)
+[![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?&logo=discord&logoColor=white)](https://discord.com/invite/mVnXXpdE85)
+[![PyPI](https://img.shields.io/pypi/v/cua-computer?color=333333)](https://pypi.org/project/cua-computer/)
+
 </h1>
 </div>
 
@@ -117,7 +129,7 @@ async def main():
         name=os.getenv("CUA_CONTAINER_NAME"),
         api_key=os.getenv("CUA_API_KEY")
     ) as computer:
-        
+
         # Create agent
         agent = ComputerAgent(
             model="anthropic/claude-3-5-sonnet-20241022",
@@ -126,10 +138,10 @@ async def main():
             trajectory_dir="trajectories",
             max_trajectory_budget=5.0  # $5 budget limit
         )
-        
+
         # Run agent
         messages = [{"role": "user", "content": "Take a screenshot and tell me what you see"}]
-        
+
         async for result in agent.run(messages):
             for item in result["output"]:
                 if item["type"] == "message":
@@ -154,4 +166,4 @@ if __name__ == "__main__":
 
 ## License
 
-MIT License - see LICENSE file for details.
+MIT License - see LICENSE file for details.

{cua_agent-0.4.33 → cua_agent-0.4.35}/README.md

@@ -8,10 +8,11 @@
     </picture>
   </div>
 
-  [![Python](https://img.shields.io/badge/Python-333333?logo=python&logoColor=white&labelColor=333333)](#)
-  [![macOS](https://img.shields.io/badge/macOS-000000?logo=apple&logoColor=F0F0F0)](#)
-  [![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?&logo=discord&logoColor=white)](https://discord.com/invite/mVnXXpdE85)
-  [![PyPI](https://img.shields.io/pypi/v/cua-computer?color=333333)](https://pypi.org/project/cua-computer/)
+[![Python](https://img.shields.io/badge/Python-333333?logo=python&logoColor=white&labelColor=333333)](#)
+[![macOS](https://img.shields.io/badge/macOS-000000?logo=apple&logoColor=F0F0F0)](#)
+[![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?&logo=discord&logoColor=white)](https://discord.com/invite/mVnXXpdE85)
+[![PyPI](https://img.shields.io/pypi/v/cua-computer?color=333333)](https://pypi.org/project/cua-computer/)
+
 </h1>
 </div>
 
@@ -47,7 +48,7 @@ async def main():
         name=os.getenv("CUA_CONTAINER_NAME"),
         api_key=os.getenv("CUA_API_KEY")
     ) as computer:
-        
+
         # Create agent
         agent = ComputerAgent(
             model="anthropic/claude-3-5-sonnet-20241022",
@@ -56,10 +57,10 @@ async def main():
             trajectory_dir="trajectories",
             max_trajectory_budget=5.0  # $5 budget limit
         )
-        
+
         # Run agent
         messages = [{"role": "user", "content": "Take a screenshot and tell me what you see"}]
-        
+
         async for result in agent.run(messages):
             for item in result["output"]:
                 if item["type"] == "message":
@@ -84,4 +85,4 @@ if __name__ == "__main__":
 
 ## License
 
-MIT License - see LICENSE file for details.
+MIT License - see LICENSE file for details.

{cua_agent-0.4.33 → cua_agent-0.4.35}/agent/__init__.py

@@ -5,19 +5,13 @@ agent - Decorator-based Computer Use Agent with liteLLM integration
 import logging
 import sys
 
-from .decorators import register_agent
-from .agent import ComputerAgent
-from .types import Messages, AgentResponse
-
 # Import loops to register them
 from . import loops
+from .agent import ComputerAgent
+from .decorators import register_agent
+from .types import AgentResponse, Messages
 
-__all__ = [
-    "register_agent",
-    "ComputerAgent",
-    "Messages",
-    "AgentResponse"
-]
+__all__ = ["register_agent", "ComputerAgent", "Messages", "AgentResponse"]
 
 __version__ = "0.4.0"
 

{cua_agent-0.4.33 → cua_agent-0.4.35}/agent/__main__.py

@@ -5,8 +5,9 @@ Usage:
     python -m agent.cli <model_string>
 """
 
-import sys
 import asyncio
+import sys
+
 from .cli import main
 
 if __name__ == "__main__":

{cua_agent-0.4.33 → cua_agent-0.4.35}/agent/adapters/huggingfacelocal_adapter.py

@@ -2,27 +2,30 @@ import asyncio
 import functools
 import warnings
 from concurrent.futures import ThreadPoolExecutor
-from typing import Iterator, AsyncIterator, Dict, List, Any, Optional
-from litellm.types.utils import GenericStreamingChunk, ModelResponse
+from typing import Any, AsyncIterator, Dict, Iterator, List, Optional
+
+from litellm import acompletion, completion
 from litellm.llms.custom_llm import CustomLLM
-from litellm import completion, acompletion
+from litellm.types.utils import GenericStreamingChunk, ModelResponse
 
 # Try to import HuggingFace dependencies
 try:
     import torch
     from transformers import AutoModelForImageTextToText, AutoProcessor
+
     HF_AVAILABLE = True
 except ImportError:
     HF_AVAILABLE = False
 
 from .models import load_model as load_model_handler
 
+
 class HuggingFaceLocalAdapter(CustomLLM):
     """HuggingFace Local Adapter for running vision-language models locally."""
-    
+
     def __init__(self, device: str = "auto", trust_remote_code: bool = False, **kwargs):
         """Initialize the adapter.
-        
+
         Args:
             device: Device to load model on ("auto", "cuda", "cpu", etc.)
             trust_remote_code: Whether to trust remote code
@@ -34,129 +37,120 @@ class HuggingFaceLocalAdapter(CustomLLM):
         # Cache for model handlers keyed by model_name
         self._handlers: Dict[str, Any] = {}
         self._executor = ThreadPoolExecutor(max_workers=1)  # Single thread pool
-        
+
     def _get_handler(self, model_name: str):
         """Get or create a model handler for the given model name."""
         if model_name not in self._handlers:
-            self._handlers[model_name] = load_model_handler(model_name=model_name, device=self.device, trust_remote_code=self.trust_remote_code)
+            self._handlers[model_name] = load_model_handler(
+                model_name=model_name, device=self.device, trust_remote_code=self.trust_remote_code
+            )
         return self._handlers[model_name]
-    
+
     def _convert_messages(self, messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
         """Convert OpenAI format messages to HuggingFace format.
-        
+
         Args:
             messages: Messages in OpenAI format
-            
+
         Returns:
             Messages in HuggingFace format
         """
         converted_messages = []
-        
+
         for message in messages:
-            converted_message = {
-                "role": message["role"],
-                "content": []
-            }
-            
+            converted_message = {"role": message["role"], "content": []}
+
             content = message.get("content", [])
             if isinstance(content, str):
                 # Simple text content
-                converted_message["content"].append({
-                    "type": "text",
-                    "text": content
-                })
+                converted_message["content"].append({"type": "text", "text": content})
             elif isinstance(content, list):
                 # Multi-modal content
                 for item in content:
                     if item.get("type") == "text":
-                        converted_message["content"].append({
-                            "type": "text",
-                            "text": item.get("text", "")
-                        })
+                        converted_message["content"].append(
+                            {"type": "text", "text": item.get("text", "")}
+                        )
                     elif item.get("type") == "image_url":
                         # Convert image_url format to image format
                         image_url = item.get("image_url", {}).get("url", "")
-                        converted_message["content"].append({
-                            "type": "image",
-                            "image": image_url
-                        })
-            
+                        converted_message["content"].append({"type": "image", "image": image_url})
+
             converted_messages.append(converted_message)
-            
+
         return converted_messages
-    
+
     def _generate(self, **kwargs) -> str:
         """Generate response using the local HuggingFace model.
-        
+
         Args:
             **kwargs: Keyword arguments containing messages and model info
-            
+
         Returns:
             Generated text response
         """
         if not HF_AVAILABLE:
             raise ImportError(
                 "HuggingFace transformers dependencies not found. "
-                "Please install with: pip install \"cua-agent[uitars-hf]\""
+                'Please install with: pip install "cua-agent[uitars-hf]"'
             )
-        
+
         # Extract messages and model from kwargs
-        messages = kwargs.get('messages', [])
-        model_name = kwargs.get('model', 'ByteDance-Seed/UI-TARS-1.5-7B')
-        max_new_tokens = kwargs.get('max_tokens', 128)
-        
+        messages = kwargs.get("messages", [])
+        model_name = kwargs.get("model", "ByteDance-Seed/UI-TARS-1.5-7B")
+        max_new_tokens = kwargs.get("max_tokens", 128)
+
         # Warn about ignored kwargs
-        ignored_kwargs = set(kwargs.keys()) - {'messages', 'model', 'max_tokens'}
+        ignored_kwargs = set(kwargs.keys()) - {"messages", "model", "max_tokens"}
         if ignored_kwargs:
             warnings.warn(f"Ignoring unsupported kwargs: {ignored_kwargs}")
-        
+
         # Convert messages to HuggingFace format
         hf_messages = self._convert_messages(messages)
-        
+
         # Delegate to model handler
         handler = self._get_handler(model_name)
         generated_text = handler.generate(hf_messages, max_new_tokens=max_new_tokens)
         return generated_text
-    
+
     def completion(self, *args, **kwargs) -> ModelResponse:
         """Synchronous completion method.
-        
+
         Returns:
             ModelResponse with generated text
         """
         generated_text = self._generate(**kwargs)
-        
+
         return completion(
             model=f"huggingface-local/{kwargs['model']}",
             mock_response=generated_text,
         )
-    
+
     async def acompletion(self, *args, **kwargs) -> ModelResponse:
         """Asynchronous completion method.
-        
+
         Returns:
             ModelResponse with generated text
         """
         # Run _generate in thread pool to avoid blocking
         loop = asyncio.get_event_loop()
         generated_text = await loop.run_in_executor(
-            self._executor, 
-            functools.partial(self._generate, **kwargs)
+            self._executor, functools.partial(self._generate, **kwargs)
         )
-        
+
         return await acompletion(
             model=f"huggingface-local/{kwargs['model']}",
             mock_response=generated_text,
         )
-    
+
     def streaming(self, *args, **kwargs) -> Iterator[GenericStreamingChunk]:
         """Synchronous streaming method.
-        
+
         Returns:
             Iterator of GenericStreamingChunk
         """
         generated_text = self._generate(**kwargs)
-        
+
         generic_streaming_chunk: GenericStreamingChunk = {
             "finish_reason": "stop",
             "index": 0,
@@ -165,22 +159,21 @@ class HuggingFaceLocalAdapter(CustomLLM):
             "tool_use": None,
             "usage": {"completion_tokens": 0, "prompt_tokens": 0, "total_tokens": 0},
         }
-        
+
         yield generic_streaming_chunk
-    
+
     async def astreaming(self, *args, **kwargs) -> AsyncIterator[GenericStreamingChunk]:
         """Asynchronous streaming method.
-        
+
         Returns:
             AsyncIterator of GenericStreamingChunk
         """
         # Run _generate in thread pool to avoid blocking
         loop = asyncio.get_event_loop()
         generated_text = await loop.run_in_executor(
-            self._executor, 
-            functools.partial(self._generate, **kwargs)
+            self._executor, functools.partial(self._generate, **kwargs)
         )
-        
+
         generic_streaming_chunk: GenericStreamingChunk = {
             "finish_reason": "stop",
             "index": 0,
@@ -189,5 +182,5 @@ class HuggingFaceLocalAdapter(CustomLLM):
             "tool_use": None,
             "usage": {"completion_tokens": 0, "prompt_tokens": 0, "total_tokens": 0},
         }
-        
-        yield generic_streaming_chunk
+
+        yield generic_streaming_chunk