cua-agent 0.4.34__py3-none-any.whl → 0.4.36__py3-none-any.whl

agent/proxy/examples.py

@@ -1,19 +1,22 @@
 """
 Example usage of the proxy server and client requests.
 """
+
 import dotenv
+
 dotenv.load_dotenv()
 
 import asyncio
 import json
 import os
+from typing import Any, Dict
+
 import aiohttp
-from typing import Dict, Any
 
 
 async def test_http_endpoint():
     """Test the HTTP /responses endpoint."""
-    
+
     anthropic_api_key = os.getenv("ANTHROPIC_API_KEY")
     assert isinstance(anthropic_api_key, str), "ANTHROPIC_API_KEY environment variable must be set"
 
@@ -21,11 +24,9 @@ async def test_http_endpoint():
     simple_request = {
         "model": "anthropic/claude-3-5-sonnet-20241022",
         "input": "Tell me a three sentence bedtime story about a unicorn.",
-        "env": {
-            "ANTHROPIC_API_KEY": anthropic_api_key
-        }
+        "env": {"ANTHROPIC_API_KEY": anthropic_api_key},
     }
-    
+
     # Example 2: Multi-modal request with image
     multimodal_request = {
         "model": "anthropic/claude-3-5-sonnet-20241022",
@@ -36,70 +37,72 @@ async def test_http_endpoint():
                     {"type": "input_text", "text": "what is in this image?"},
                     {
                         "type": "input_image",
-                        "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
-                    }
-                ]
+                        "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
+                    },
+                ],
             }
         ],
-        "env": {
-            "ANTHROPIC_API_KEY": anthropic_api_key
-        }
+        "env": {"ANTHROPIC_API_KEY": anthropic_api_key},
     }
-    
+
     # Example 3: Request with custom agent and computer kwargs
     custom_request = {
         "model": "anthropic/claude-3-5-sonnet-20241022",
         "input": "Take a screenshot and tell me what you see",
-        "env": {
-            "ANTHROPIC_API_KEY": anthropic_api_key
-        }
+        "env": {"ANTHROPIC_API_KEY": anthropic_api_key},
     }
-    
+
     # Test requests
     base_url = "https://m-linux-96lcxd2c2k.containers.cloud.trycua.com:8443"
     # base_url = "http://localhost:8000"
     api_key = os.getenv("CUA_API_KEY")
     assert isinstance(api_key, str), "CUA_API_KEY environment variable must be set"
-    
+
     async with aiohttp.ClientSession() as session:
-        for i, request_data in enumerate([
-            simple_request,
-            # multimodal_request,
-            custom_request
-        ], 1):
+        for i, request_data in enumerate(
+            [
+                simple_request,
+                # multimodal_request,
+                custom_request,
+            ],
+            1,
+        ):
             print(f"\n--- Test {i} ---")
             print(f"Request: {json.dumps(request_data, indent=2)}")
-            
+
             try:
                 print(f"Sending request to {base_url}/responses")
                 async with session.post(
                     f"{base_url}/responses",
                     json=request_data,
-                    headers={"Content-Type": "application/json", "X-API-Key": api_key}
+                    headers={"Content-Type": "application/json", "X-API-Key": api_key},
                 ) as response:
                     result = await response.json()
                     print(f"Status: {response.status}")
                     print(f"Response: {json.dumps(result, indent=2)}")
-                    
+
             except Exception as e:
                 print(f"Error: {e}")
 
 
 def curl_examples():
     """Print curl command examples."""
-    
+
     print("=== CURL Examples ===\n")
-    
+
     print("1. Simple text request:")
-    print("""curl http://localhost:8000/responses \\
+    print(
+        """curl http://localhost:8000/responses \\
   -H "Content-Type: application/json" \\
   -d '{
     "model": "anthropic/claude-3-5-sonnet-20241022",
     "input": "Tell me a three sentence bedtime story about a unicorn."
-  }'""")
-    
+  }'"""
+    )
+
     print("\n2. Multi-modal request with image:")
-    print("""curl http://localhost:8000/responses \\
+    print(
+        """curl http://localhost:8000/responses \\
   -H "Content-Type: application/json" \\
   -d '{
     "model": "anthropic/claude-3-5-sonnet-20241022",
@@ -115,10 +118,12 @@ def curl_examples():
         ]
       }
     ]
-  }'""")
-    
+  }'"""
+    )
+
     print("\n3. Request with custom configuration:")
-    print("""curl http://localhost:8000/responses \\
+    print(
+        """curl http://localhost:8000/responses \\
   -H "Content-Type: application/json" \\
   -d '{
     "model": "anthropic/claude-3-5-sonnet-20241022",
@@ -131,50 +136,49 @@ def curl_examples():
       "os_type": "linux",
       "provider_type": "cloud"
     }
-  }'""")
+  }'"""
+    )
 
 
 async def test_p2p_client():
     """Example P2P client using peerjs-python."""
     try:
-        from peerjs import Peer, PeerOptions, ConnectionEventType
         from aiortc import RTCConfiguration, RTCIceServer
-        
+        from peerjs import ConnectionEventType, Peer, PeerOptions
+
         # Set up client peer
         options = PeerOptions(
             host="0.peerjs.com",
             port=443,
             secure=True,
-            config=RTCConfiguration(
-                iceServers=[RTCIceServer(urls="stun:stun.l.google.com:19302")]
-            )
+            config=RTCConfiguration(iceServers=[RTCIceServer(urls="stun:stun.l.google.com:19302")]),
         )
-        
+
         client_peer = Peer(id="test-client", peer_options=options)
         await client_peer.start()
-        
+
         # Connect to proxy server
         connection = client_peer.connect("computer-agent-proxy")
-        
+
         @connection.on(ConnectionEventType.Open)
         async def connection_open():
             print("Connected to proxy server")
-            
+
             # Send a test request
             request = {
                 "model": "anthropic/claude-3-5-sonnet-20241022",
-                "input": "Hello from P2P client!"
+                "input": "Hello from P2P client!",
             }
             await connection.send(json.dumps(request))
-        
+
         @connection.on(ConnectionEventType.Data)
         async def connection_data(data):
             print(f"Received response: {data}")
             await client_peer.destroy()
-        
+
         # Wait for connection
         await asyncio.sleep(10)
-        
+
     except ImportError:
         print("P2P dependencies not available. Install peerjs-python for P2P testing.")
     except Exception as e:
@@ -183,7 +187,7 @@ async def test_p2p_client():
 
 if __name__ == "__main__":
     import sys
-    
+
     if len(sys.argv) > 1 and sys.argv[1] == "curl":
         curl_examples()
     elif len(sys.argv) > 1 and sys.argv[1] == "p2p":

agent/proxy/handlers.py

@@ -7,24 +7,25 @@ import json
 import logging
 import os
 from contextlib import contextmanager
-from typing import Dict, Any, List, Union, Optional
+from typing import Any, Dict, List, Optional, Union
 
-from ..agent import ComputerAgent
 from computer import Computer
 
+from ..agent import ComputerAgent
+
 logger = logging.getLogger(__name__)
 
 
 class ResponsesHandler:
     """Handler for /responses endpoint that processes agent requests."""
-    
+
     def __init__(self):
         self.computer = None
         self.agent = None
         # Simple in-memory caches
         self._computer_cache: Dict[str, Any] = {}
         self._agent_cache: Dict[str, Any] = {}
-    
+
     async def setup_computer_agent(
         self,
         model: str,
@@ -75,7 +76,9 @@ class ResponsesHandler:
                 computer = Computer(**default_c_config)
                 await computer.__aenter__()
                 self._computer_cache[comp_key] = computer
-                logger.info(f"Computer created and cached with key={comp_key} config={default_c_config}")
+                logger.info(
+                    f"Computer created and cached with key={comp_key} config={default_c_config}"
+                )
             else:
                 logger.info(f"Reusing cached computer for key={comp_key}")
 
@@ -115,14 +118,14 @@ class ResponsesHandler:
 
         # Bind current agent reference
         self.agent = agent
-    
+
     async def process_request(self, request_data: Dict[str, Any]) -> Dict[str, Any]:
         """
         Process a /responses request and return the result.
-        
+
         Args:
             request_data: Dictionary containing model, input, and optional kwargs
-            
+
         Returns:
             Dictionary with the agent's response
         """
@@ -133,12 +136,12 @@ class ResponsesHandler:
             agent_kwargs = request_data.get("agent_kwargs", {})
             computer_kwargs = request_data.get("computer_kwargs", {})
             env_overrides = request_data.get("env", {}) or {}
-            
+
             if not model:
                 raise ValueError("Model is required")
             if not input_data:
                 raise ValueError("Input is required")
-            
+
             # Apply env overrides for the duration of this request
             with self._env_overrides(env_overrides):
                 # Set up (and possibly reuse) computer and agent via caches
@@ -155,28 +158,22 @@ class ResponsesHandler:
                 # Run agent and get first result
                 async for result in agent.run(messages):
                     # Return the first result and break
-                    return {
-                        "success": True,
-                        "result": result,
-                        "model": model
-                    }
-                
+                    return {"success": True, "result": result, "model": model}
+
             # If no results were yielded
-            return {
-                "success": False,
-                "error": "No results from agent",
-                "model": model
-            }
-            
+            return {"success": False, "error": "No results from agent", "model": model}
+
         except Exception as e:
             logger.error(f"Error processing request: {e}")
             return {
                 "success": False,
                 "error": str(e),
-                "model": request_data.get("model", "unknown")
+                "model": request_data.get("model", "unknown"),
             }
-    
-    def _convert_input_to_messages(self, input_data: Union[str, List[Dict[str, Any]]]) -> List[Dict[str, Any]]:
+
+    def _convert_input_to_messages(
+        self, input_data: Union[str, List[Dict[str, Any]]]
+    ) -> List[Dict[str, Any]]:
         """Convert input data to messages format."""
         if isinstance(input_data, str):
             # Simple string input
@@ -192,22 +189,18 @@ class ResponsesHandler:
                         if part.get("type") == "input_text":
                             content_parts.append({"type": "text", "text": part["text"]})
                         elif part.get("type") == "input_image":
-                            content_parts.append({
-                                "type": "image_url",
-                                "image_url": {"url": part["image_url"]}
-                            })
+                            content_parts.append(
+                                {"type": "image_url", "image_url": {"url": part["image_url"]}}
+                            )
                         else:
                             content_parts.append(part)
-                    messages.append({
-                        "role": msg["role"],
-                        "content": content_parts
-                    })
+                    messages.append({"role": msg["role"], "content": content_parts})
                 else:
                     messages.append(msg)
             return messages
         else:
             raise ValueError("Input must be string or list of messages")
-    
+
     async def cleanup(self):
         """Clean up resources."""
         if self.computer: