cua-agent 0.4.5__py3-none-any.whl → 0.4.7__py3-none-any.whl

agent/adapters/huggingfacelocal_adapter.py

@@ -8,7 +8,7 @@ from litellm import completion, acompletion
 # Try to import HuggingFace dependencies
 try:
     import torch
-    from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
+    from transformers import AutoModelForImageTextToText, AutoProcessor
     HF_AVAILABLE = True
 except ImportError:
     HF_AVAILABLE = False
@@ -40,7 +40,7 @@ class HuggingFaceLocalAdapter(CustomLLM):
         """
         if model_name not in self.models:
             # Load model
-            model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+            model = AutoModelForImageTextToText.from_pretrained(
                 model_name,
                 torch_dtype=torch.float16,
                 device_map=self.device,
@@ -141,8 +141,7 @@ class HuggingFaceLocalAdapter(CustomLLM):
         )
         
         # Move inputs to the same device as model
-        if torch.cuda.is_available() and self.device != "cpu":
-            inputs = inputs.to("cuda")
+        inputs = inputs.to(model.device)
         
         # Generate response
         with torch.no_grad():

agent/agent.py

@@ -411,6 +411,9 @@ class ComputerAgent:
             # Perform computer actions
             action = item.get("action")
             action_type = action.get("type")
+            if action_type is None:
+                print(f"Action type cannot be `None`: action={action}, action_type={action_type}")
+                return []
             
             # Extract action arguments (all fields except 'type')
             action_args = {k: v for k, v in action.items() if k != "type"}

agent/callbacks/pii_anonymization.py

@@ -9,10 +9,7 @@ import io
 import logging
 
 try:
-    from presidio_analyzer import AnalyzerEngine
-    from presidio_anonymizer import AnonymizerEngine, DeanonymizeEngine
-    from presidio_anonymizer.entities import RecognizerResult, OperatorConfig
-    from presidio_image_redactor import ImageRedactorEngine
+    # TODO: Add Presidio dependencies
     from PIL import Image
     PRESIDIO_AVAILABLE = True
 except ImportError:
@@ -32,11 +29,7 @@ class PIIAnonymizationCallback(AsyncCallbackHandler):
     
     def __init__(
         self,
-        anonymize_text: bool = True,
-        anonymize_images: bool = True,
-        entities_to_anonymize: Optional[List[str]] = None,
-        anonymization_operator: str = "replace",
-        image_redaction_color: Tuple[int, int, int] = (255, 192, 203)  # Pink
+        # TODO: Any extra kwargs if needed
     ):
         """
         Initialize the PII anonymization callback.
@@ -51,23 +44,10 @@ class PIIAnonymizationCallback(AsyncCallbackHandler):
         if not PRESIDIO_AVAILABLE:
             raise ImportError(
                 "Presidio is not available. Install with: "
-                "pip install presidio-analyzer presidio-anonymizer presidio-image-redactor"
+                "pip install cua-agent[pii-anonymization]"
             )
         
-        self.anonymize_text = anonymize_text
-        self.anonymize_images = anonymize_images
-        self.entities_to_anonymize = entities_to_anonymize
-        self.anonymization_operator = anonymization_operator
-        self.image_redaction_color = image_redaction_color
-        
-        # Initialize Presidio engines
-        self.analyzer = AnalyzerEngine()
-        self.anonymizer = AnonymizerEngine()
-        self.deanonymizer = DeanonymizeEngine()
-        self.image_redactor = ImageRedactorEngine()
-        
-        # Store anonymization mappings for deanonymization
-        self.anonymization_mappings: Dict[str, Any] = {}
+        # TODO: Implement __init__
     
     async def on_llm_start(self, messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
         """
@@ -79,9 +59,6 @@ class PIIAnonymizationCallback(AsyncCallbackHandler):
         Returns:
             List of messages with PII anonymized
         """
-        if not self.anonymize_text and not self.anonymize_images:
-            return messages
-        
         anonymized_messages = []
         for msg in messages:
             anonymized_msg = await self._anonymize_message(msg)
@@ -99,9 +76,6 @@ class PIIAnonymizationCallback(AsyncCallbackHandler):
         Returns:
             List of output with PII deanonymized for tool calls
         """
-        if not self.anonymize_text:
-            return output
-        
         deanonymized_output = []
         for item in output:
             # Only deanonymize tool calls and computer_call messages
@@ -114,146 +88,9 @@ class PIIAnonymizationCallback(AsyncCallbackHandler):
         return deanonymized_output
     
     async def _anonymize_message(self, message: Dict[str, Any]) -> Dict[str, Any]:
-        """Anonymize PII in a single message."""
-        msg_copy = message.copy()
-        
-        # Anonymize text content
-        if self.anonymize_text:
-            msg_copy = await self._anonymize_text_content(msg_copy)
-        
-        # Redact images in computer_call_output
-        if self.anonymize_images and msg_copy.get("type") == "computer_call_output":
-            msg_copy = await self._redact_image_content(msg_copy)
-        
-        return msg_copy
-    
-    async def _anonymize_text_content(self, message: Dict[str, Any]) -> Dict[str, Any]:
-        """Anonymize text content in a message."""
-        msg_copy = message.copy()
-        
-        # Handle content array
-        content = msg_copy.get("content", [])
-        if isinstance(content, str):
-            anonymized_text, _ = await self._anonymize_text(content)
-            msg_copy["content"] = anonymized_text
-        elif isinstance(content, list):
-            anonymized_content = []
-            for item in content:
-                if isinstance(item, dict) and item.get("type") == "text":
-                    text = item.get("text", "")
-                    anonymized_text, _ = await self._anonymize_text(text)
-                    item_copy = item.copy()
-                    item_copy["text"] = anonymized_text
-                    anonymized_content.append(item_copy)
-                else:
-                    anonymized_content.append(item)
-            msg_copy["content"] = anonymized_content
-        
-        return msg_copy
-    
-    async def _redact_image_content(self, message: Dict[str, Any]) -> Dict[str, Any]:
-        """Redact PII from images in computer_call_output messages."""
-        msg_copy = message.copy()
-        output = msg_copy.get("output", {})
-        
-        if isinstance(output, dict) and "image_url" in output:
-            try:
-                # Extract base64 image data
-                image_url = output["image_url"]
-                if image_url.startswith("data:image/"):
-                    # Parse data URL
-                    header, data = image_url.split(",", 1)
-                    image_data = base64.b64decode(data)
-                    
-                    # Load image with PIL
-                    image = Image.open(io.BytesIO(image_data))
-                    
-                    # Redact PII from image
-                    redacted_image = self.image_redactor.redact(image, self.image_redaction_color)
-                    
-                    # Convert back to base64
-                    buffer = io.BytesIO()
-                    redacted_image.save(buffer, format="PNG")
-                    redacted_data = base64.b64encode(buffer.getvalue()).decode()
-                    
-                    # Update image URL
-                    output_copy = output.copy()
-                    output_copy["image_url"] = f"data:image/png;base64,{redacted_data}"
-                    msg_copy["output"] = output_copy
-                    
-            except Exception as e:
-                logger.warning(f"Failed to redact image: {e}")
-        
-        return msg_copy
+        # TODO: Implement _anonymize_message
+        return message
     
     async def _deanonymize_item(self, item: Dict[str, Any]) -> Dict[str, Any]:
-        """Deanonymize PII in tool calls and computer outputs."""
-        item_copy = item.copy()
-        
-        # Handle computer_call arguments
-        if item.get("type") == "computer_call":
-            args = item_copy.get("args", {})
-            if isinstance(args, dict):
-                deanonymized_args = {}
-                for key, value in args.items():
-                    if isinstance(value, str):
-                        deanonymized_value, _ = await self._deanonymize_text(value)
-                        deanonymized_args[key] = deanonymized_value
-                    else:
-                        deanonymized_args[key] = value
-                item_copy["args"] = deanonymized_args
-        
-        return item_copy
-    
-    async def _anonymize_text(self, text: str) -> Tuple[str, List[RecognizerResult]]:
-        """Anonymize PII in text and return the anonymized text and results."""
-        if not text.strip():
-            return text, []
-        
-        try:
-            # Analyze text for PII
-            analyzer_results = self.analyzer.analyze(
-                text=text,
-                entities=self.entities_to_anonymize,
-                language="en"
-            )
-            
-            if not analyzer_results:
-                return text, []
-            
-            # Anonymize the text
-            anonymized_result = self.anonymizer.anonymize(
-                text=text,
-                analyzer_results=analyzer_results,
-                operators={entity_type: OperatorConfig(self.anonymization_operator) 
-                          for entity_type in set(result.entity_type for result in analyzer_results)}
-            )
-            
-            # Store mapping for deanonymization
-            mapping_key = str(hash(text))
-            self.anonymization_mappings[mapping_key] = {
-                "original": text,
-                "anonymized": anonymized_result.text,
-                "results": analyzer_results
-            }
-            
-            return anonymized_result.text, analyzer_results
-            
-        except Exception as e:
-            logger.warning(f"Failed to anonymize text: {e}")
-            return text, []
-    
-    async def _deanonymize_text(self, text: str) -> Tuple[str, bool]:
-        """Attempt to deanonymize text using stored mappings."""
-        try:
-            # Look for matching anonymized text in mappings
-            for mapping_key, mapping in self.anonymization_mappings.items():
-                if mapping["anonymized"] == text:
-                    return mapping["original"], True
-            
-            # If no mapping found, return original text
-            return text, False
-            
-        except Exception as e:
-            logger.warning(f"Failed to deanonymize text: {e}")
-            return text, False
+        # TODO: Implement _deanonymize_item
+        return item

agent/ui/gradio/app.py

@@ -178,13 +178,20 @@ def create_computer_instance(
     """Create or get the global Computer instance."""
     global global_computer
     if global_computer is None:
-        global_computer = Computer(
-            verbosity=verbosity,
-            os_type=os_type,
-            provider_type=provider_type,
-            name=name if name else "",
-            api_key=api_key
-        )
+        if provider_type == "localhost":
+            global_computer = Computer(
+                verbosity=verbosity,
+                os_type=os_type,
+                use_host_computer_server=True
+            )
+        else:
+            global_computer = Computer(
+                verbosity=verbosity,
+                os_type=os_type,
+                provider_type=provider_type,
+                name=name if name else "",
+                api_key=api_key
+            )
     return global_computer
 
 

agent/ui/gradio/ui_components.py

@@ -211,7 +211,7 @@ if __name__ == "__main__":
                     is_windows = platform.system().lower() == "windows"
                     is_mac = platform.system().lower() == "darwin"
                     
-                    providers = ["cloud"]
+                    providers = ["cloud", "localhost"]
                     if is_mac:
                         providers += ["lume"]
                     if is_windows:
@@ -403,6 +403,23 @@ if __name__ == "__main__":
                         type="password",
                     )
                     
+                    # Provider visibility update function
+                    def update_provider_visibility(provider):
+                        """Update visibility of container name and API key based on selected provider."""
+                        is_localhost = provider == "localhost"
+                        return [
+                            gr.update(visible=not is_localhost),  # container_name
+                            gr.update(visible=not is_localhost and not has_cua_key)  # cua_cloud_api_key
+                        ]
+                    
+                    # Connect provider change event
+                    computer_provider.change(
+                        fn=update_provider_visibility,
+                        inputs=[computer_provider],
+                        outputs=[container_name, cua_cloud_api_key],
+                        queue=False
+                    )
+                    
                     # Connect UI update events
                     for dropdown in [agent_loop, omni_model_choice, uitars_model_choice, openai_model_choice, anthropic_model_choice]:
                         dropdown.change(

{cua_agent-0.4.5.dist-info → cua_agent-0.4.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cua-agent
-Version: 0.4.5
+Version: 0.4.7
 Summary: CUA (Computer Use) Agent for AI-driven computer interaction
 Author-Email: TryCua <gh@trycua.com>
 Requires-Python: >=3.11
@@ -12,7 +12,7 @@ Requires-Dist: typing-extensions>=4.12.2
 Requires-Dist: pydantic>=2.6.4
 Requires-Dist: rich>=13.7.1
 Requires-Dist: python-dotenv>=1.0.1
-Requires-Dist: cua-computer<0.5.0,>=0.3.0
+Requires-Dist: cua-computer<0.5.0,>=0.4.0
 Requires-Dist: cua-core<0.2.0,>=0.1.8
 Requires-Dist: certifi>=2024.2.2
 Requires-Dist: litellm>=1.74.8

{cua_agent-0.4.5.dist-info → cua_agent-0.4.7.dist-info}/RECORD

@@ -1,14 +1,14 @@
 agent/__init__.py,sha256=PfRgVa_aJQL9fK0D1g2r__Kdg3627EigNS31_M8Ivkk,1539
 agent/__main__.py,sha256=lBUe8Niqa5XoCjwFfXyX7GtnUwjjZXC1-j4V9mvUYSc,538
 agent/adapters/__init__.py,sha256=szM2HMten2WkcqXeRnan__-sXjpyS4eyvIW0LXSfj4U,178
-agent/adapters/huggingfacelocal_adapter.py,sha256=dnzzxYCvFiuDdNzsb_1uM-boWv1eS__dWMve_fAnlUc,8038
-agent/agent.py,sha256=Vn7ygehx19It5FarZJ2NwVwNTOtNYtD21x8LEBhlWcE,24609
+agent/adapters/huggingfacelocal_adapter.py,sha256=o2IQI1wuZWDYgGPj92dkxTb3uk07XjJdvC19O2_aeak,7963
+agent/agent.py,sha256=bSmc_5Jr4CTvTut8lgNwNpnk9w4sD9SACQb0GbT4zwg,24770
 agent/callbacks/__init__.py,sha256=yxxBXUqpXQ-jRi_ixJMtmQPxoNRy5Vz1PUBzNNa1Dwg,538
 agent/callbacks/base.py,sha256=UnnnYlh6XCm6HKZZsAPaT_Eyo9LUYLyjyNwF-QRm6Ns,4691
 agent/callbacks/budget_manager.py,sha256=RyKM-7iXQcDotYvrw3eURzeEHEXvQjID-NobtvQWE7k,1832
 agent/callbacks/image_retention.py,sha256=tiuRT5ke9xXTb2eP8Gz-2ITyAMY29LURUH6AbjX3RP8,6165
 agent/callbacks/logging.py,sha256=OOxU97EzrxlnUAtiEnvy9FB7SwCUK90-rdpDFA2Ae4E,10921
-agent/callbacks/pii_anonymization.py,sha256=UKAqNacHG3z92_6uocVzOIl8gJoqyofldCoCmB4UVIE,10268
+agent/callbacks/pii_anonymization.py,sha256=NEkUTUjQBi82nqus7kT-1E4RaeQ2hQrY7YCnKndLhP8,3272
 agent/callbacks/telemetry.py,sha256=PU7pkK7W1v1xjDN-9gA30lGvn4-WhqK3BPHGW3HpTOc,7497
 agent/callbacks/trajectory_saver.py,sha256=POE8aPT-MBzfW873wr6C7iiVUHtp483KwvLPxC1S3EY,11626
 agent/cli.py,sha256=odI7cdl1psOGK-mEQzezsPzbRcLFwDbi7A2ukvYq8dk,12130
@@ -25,9 +25,9 @@ agent/types.py,sha256=GiLxIcF7s1XIh_WaY7tjdQPFpdTXb5MWVe_ZUPA0gkY,2364
 agent/ui/__init__.py,sha256=DTZpK85QXscXK2nM9HtpAhVBF13yAamUrtwrQSuV-kM,126
 agent/ui/__main__.py,sha256=vudWXYvGM0aNT5aZ94HPtGW8YXOZ4cLXepHyhUM_k1g,73
 agent/ui/gradio/__init__.py,sha256=yv4Mrfo-Sj2U5sVn_UJHAuwYCezo-5O4ItR2C9jzNko,145
-agent/ui/gradio/app.py,sha256=X7he4jzyFqWJDP1y_M8yfZvfdy6GHNuclLn4k9iIwAw,8824
-agent/ui/gradio/ui_components.py,sha256=WxFE-4wvdEgj7FPLNXUrs118sXJ9vN3kLkZxtto-weo,34474
-cua_agent-0.4.5.dist-info/METADATA,sha256=VILpU50MidWIJQ3MP1ux45cuv8aOQL99XRbXIQcWu_g,12060
-cua_agent-0.4.5.dist-info/WHEEL,sha256=9P2ygRxDrTJz3gsagc0Z96ukrxjr-LFBGOgv3AuKlCA,90
-cua_agent-0.4.5.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
-cua_agent-0.4.5.dist-info/RECORD,,
+agent/ui/gradio/app.py,sha256=9UOPwuwspLrnHGY91zdzuRqkMH4cmwOBH-f-BC0gVC4,9077
+agent/ui/gradio/ui_components.py,sha256=hVMGZxAEq1LBHOqKj-RbDXJsj1j0Qw5dOV0ecWIHxmc,35397
+cua_agent-0.4.7.dist-info/METADATA,sha256=wCahxHMvzKL-FkTFy4XlZZirBwl1v-RYWRcYbFcJBDk,12060
+cua_agent-0.4.7.dist-info/WHEEL,sha256=9P2ygRxDrTJz3gsagc0Z96ukrxjr-LFBGOgv3AuKlCA,90
+cua_agent-0.4.7.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
+cua_agent-0.4.7.dist-info/RECORD,,