cua-agent 0.4.11__py3-none-any.whl → 0.4.13__py3-none-any.whl

agent/integrations/hud/__init__.py

@@ -0,0 +1,77 @@
+"""HUD integration for ComputerAgent."""
+
+import logging
+from typing import Any, Optional, Dict
+from hud import run_job as hud_run_job
+
+from .agent import ComputerAgent
+from .adapter import ComputerAgentAdapter
+from .computer_handler import HUDComputerHandler
+
+
+async def run_job(
+    model: str,
+    task_or_taskset: Any,
+    job_name: str,
+    # Job kwargs
+    auto_reply_question: bool = False,
+    adapter_cls: Any = None,
+    adapter_kwargs: Optional[Dict[str, Any]] = None,
+    max_steps_per_task: int = 20,
+    run_parallel: bool = True,
+    job_metadata: Optional[Dict[str, Any]] = None,
+    show_progress: bool = True,
+    max_concurrent_env_creations: Optional[int] = 30,  # Limits gym.make calls
+    max_concurrent_agent_predictions: Optional[int] = None,  # No limit on LLM calls
+    max_concurrent_tasks: Optional[int] = 30,  # Limits overall task concurrency
+    **agent_kwargs: Any
+) -> Any:
+    """
+    Run a job using ComputerAgent with the specified model.
+    
+    Args:
+        model: Model string for ComputerAgent (e.g., "anthropic/claude-3-5-sonnet-20241022")
+        task_or_taskset: Task or TaskSet to run
+        job_name: Name for the job
+        auto_reply_question: Whether to auto-reply to questions
+        adapter_cls: Custom adapter class (defaults to ComputerAgentAdapter)
+        adapter_kwargs: Additional kwargs for the adapter
+        max_steps_per_task: Maximum steps per task
+        run_parallel: Whether to run tasks in parallel
+        job_metadata: Additional metadata for the job
+        show_progress: Whether to show progress
+        max_concurrent_env_creations: Max concurrent environment creations
+        max_concurrent_agent_predictions: Max concurrent agent predictions
+        max_concurrent_tasks: Max concurrent tasks
+        **agent_kwargs: Additional kwargs to pass to ComputerAgent
+    
+    Returns:
+        Job instance from HUD
+    """
+    # combine verbose and verbosity kwargs
+    if "verbose" in agent_kwargs:
+        agent_kwargs["verbosity"] = logging.INFO
+        del agent_kwargs["verbose"]
+    verbose = True if agent_kwargs.get("verbosity", logging.WARNING) > logging.INFO else False
+    
+    # run job
+    return await hud_run_job(
+        agent_cls=ComputerAgent,
+        agent_kwargs={"model": model, **agent_kwargs},
+        task_or_taskset=task_or_taskset,
+        job_name=job_name,
+        auto_reply_question=auto_reply_question,
+        adapter_cls=adapter_cls,
+        adapter_kwargs=adapter_kwargs,
+        max_steps_per_task=max_steps_per_task,
+        run_parallel=run_parallel,
+        job_metadata=job_metadata,
+        show_progress=show_progress,
+        verbose=verbose,
+        max_concurrent_env_creations=max_concurrent_env_creations,
+        max_concurrent_agent_predictions=max_concurrent_agent_predictions,
+        max_concurrent_tasks=max_concurrent_tasks
+    )
+
+
+__all__ = ["ComputerAgent", "ComputerAgentAdapter", "HUDComputerHandler", "run_job"]

agent/integrations/hud/adapter.py

@@ -0,0 +1,121 @@
+"""HUD Adapter for ComputerAgent integration."""
+
+from __future__ import annotations
+
+from typing import Any, ClassVar
+
+from hud.adapters.common import CLA, Adapter
+from hud.adapters.common.types import (
+    CLAButton,
+    CLAKey,
+    ClickAction,
+    CustomAction,
+    DragAction,
+    MoveAction,
+    Point,
+    PressAction,
+    ResponseAction,
+    ScreenshotFetch,
+    ScrollAction,
+    TypeAction,
+    WaitAction,
+)
+
+
+class ComputerAgentAdapter(Adapter):
+    """Adapter for ComputerAgent to work with HUD."""
+    
+    KEY_MAP: ClassVar[dict[str, CLAKey]] = {
+        "return": "enter",
+        "arrowup": "up",
+        "arrowdown": "down",
+        "arrowleft": "left",
+        "arrowright": "right",
+        "cmd": "ctrl",
+        "super": "win",
+        "meta": "win",
+    }
+
+    BUTTON_MAP: ClassVar[dict[str, CLAButton]] = {
+        "wheel": "middle",
+        "middle": "middle",
+    }
+
+    def __init__(self) -> None:
+        super().__init__()
+        # ComputerAgent default dimensions (can be overridden)
+        self.agent_width = 1024
+        self.agent_height = 768
+
+    def _map_key(self, key: str) -> CLAKey:
+        """Map a key to its standardized form."""
+        return self.KEY_MAP.get(key.lower(), key.lower())  # type: ignore
+
+    def convert(self, data: Any) -> CLA:
+        """Convert a ComputerAgent action to a HUD action."""
+        try:
+            action_type = data.get("type")
+
+            if action_type == "click":
+                x, y = data.get("x", 0), data.get("y", 0)
+                button = data.get("button", "left")
+                button = self.BUTTON_MAP.get(button, button)
+                if button is None:
+                    button = "left"
+                converted_action = ClickAction(point=Point(x=x, y=y), button=button)
+
+            elif action_type == "double_click":
+                x, y = data.get("x", 0), data.get("y", 0)
+                converted_action = ClickAction(point=Point(x=x, y=y), button="left", pattern=[100])
+
+            elif action_type == "scroll":
+                x, y = int(data.get("x", 0)), int(data.get("y", 0))
+                scroll_x = int(data.get("scroll_x", 0))
+                scroll_y = int(data.get("scroll_y", 0))
+                converted_action = ScrollAction(
+                    point=Point(x=x, y=y), scroll=Point(x=scroll_x, y=scroll_y)
+                )
+
+            elif action_type == "type":
+                text = data.get("text", "")
+                converted_action = TypeAction(text=text, enter_after=False)
+
+            elif action_type == "wait":
+                ms = data.get("ms", 1000)
+                converted_action = WaitAction(time=ms)
+
+            elif action_type == "move":
+                x, y = data.get("x", 0), data.get("y", 0)
+                converted_action = MoveAction(point=Point(x=x, y=y))
+
+            elif action_type == "keypress":
+                keys = data.get("keys", [])
+                if isinstance(keys, str):
+                    keys = [keys]
+                converted_action = PressAction(keys=[self._map_key(k) for k in keys])
+
+            elif action_type == "drag":
+                path = data.get("path", [])
+                points = [Point(x=p.get("x", 0), y=p.get("y", 0)) for p in path]
+                converted_action = DragAction(path=points)
+
+            elif action_type == "screenshot":
+                converted_action = ScreenshotFetch()
+
+            elif action_type == "response":
+                converted_action = ResponseAction(text=data.get("text", ""))
+                
+            elif action_type == "custom":
+                converted_action = CustomAction(action=data.get("action", ""))
+                
+            else:
+                raise ValueError(f"Unsupported action type: {action_type}")
+
+            # Add reasoning and logs if available
+            converted_action.reasoning = data.get("reasoning", "")
+            converted_action.logs = data.get("logs", "")
+
+            return converted_action
+
+        except Exception as e:
+            raise ValueError(f"Invalid action: {data}. Error: {e!s}") from e

agent/integrations/hud/agent.py

@@ -0,0 +1,373 @@
+"""HUD ComputerAgent wrapper for OSWorld benchmarking."""
+
+import logging
+from typing import Any, Literal, Optional, Union, List, Dict
+import asyncio
+
+from agent import ComputerAgent as BaseComputerAgent
+from agent.responses import make_failed_tool_call_items
+from hud.adapters import Adapter
+from hud.agent.base import Agent
+from hud.utils.common import Observation
+from hud.adapters.common.types import LogType
+from hud.types import Gym
+
+from .adapter import ComputerAgentAdapter
+from .computer_handler import HUDComputerHandler
+
+logger = logging.getLogger(__name__)
+
+BASE_SYSTEM_PROMPT = """
+You are an autonomous computer-using agent. Follow these guidelines:
+
+1. Be decisive and complete tasks without asking for confirmation unless absolutely necessary.
+2. Use the computer tools to complete the task and do not stop until the task is complete.
+3. Do NOT ask questions like "Should I proceed?" or "Would you like me to continue?" - just proceed with the task.
+4. When you find what you're looking for (e.g., a file to upload), proceed with the action directly.
+5. Only stop when the task is fully complete or if you encounter an error that prevents completion.
+6. Trust that the user wants you to complete the entire task they've requested.
+7. You must say "Task completed" when the task is complete.
+
+Remember: You have been given permission to complete the requested task autonomously.
+""".strip()
+
+class ComputerAgent(Agent[BaseComputerAgent, dict[str, Any]]):
+    """
+    A ComputerAgent wrapper for HUD integration.
+    
+    This agent wraps the base ComputerAgent to work with HUD environments,
+    providing the same interface as OperatorAgent but using ComputerAgent internally.
+    """
+    
+    transfer_gyms: dict[Gym, Gym] = {"qa": "hud-browser"}
+
+    def __init__(
+        self,
+        model: str = "anthropic/claude-3-5-sonnet-20241022",
+        environment: Literal["windows", "mac", "linux", "browser"] = "linux",
+        adapter: Optional[Adapter] = None,
+        name: Optional[str] = None,
+        **kwargs: Any,
+    ):
+        """
+        Initialize the ComputerAgent for HUD.
+
+        Args:
+            model: The model string for ComputerAgent (e.g., "anthropic/claude-3-5-sonnet-20241022")
+            environment: The environment type (windows, mac, linux, browser)
+            adapter: The adapter to use for preprocessing and postprocessing
+            name: The name of the agent
+            **kwargs: Additional arguments passed to ComputerAgent
+        """
+        # Create adapter if not provided
+        adapter = adapter or ComputerAgentAdapter()
+        
+        if name is None:
+            name = f"computeragent-{model.split('/')[-1]}"
+
+        # Initialize the base Agent class without client (we'll create it later)
+        super().__init__(client=None, adapter=adapter, name=name)
+
+        self.model = model
+        self.environment = environment
+        self.kwargs = kwargs
+
+        # Default dimensions
+        self.width = 1024
+        self.height = 768
+
+        # Update dimensions if adapter is provided
+        if self.adapter:
+            self.width = self.adapter.agent_width
+            self.height = self.adapter.agent_height
+
+        # Create HUD computer handler
+        self.hud_computer = HUDComputerHandler(
+            environment=environment,
+            dimensions=(self.width, self.height)
+        )
+
+        # Handle trajectory_dir by adding TrajectorySaverCallback
+        trajectory_dir = kwargs.pop("trajectory_dir", None)
+        callbacks = kwargs.get("callbacks", [])
+        
+        if trajectory_dir:
+            from agent.callbacks.trajectory_saver import TrajectorySaverCallback
+            trajectory_callback = TrajectorySaverCallback(trajectory_dir, reset_on_run=False)
+            callbacks = callbacks + [trajectory_callback]
+            kwargs["callbacks"] = callbacks
+
+        # Initialize ComputerAgent with HUD computer handler
+        self.computer_agent = BaseComputerAgent(
+            model=model,
+            tools=[self.hud_computer],
+            **kwargs
+        )
+        
+        # Set the client to the computer_agent for compatibility
+        self.client = self.computer_agent
+
+        # State tracking
+        self.conversation_history: List[Dict[str, Any]] = []
+        self.initial_prompt: Optional[str] = None
+
+        # System prompt for computer use tasks
+        self.base_system_prompt = BASE_SYSTEM_PROMPT
+
+    async def fetch_response(self, observation: Observation) -> tuple[list[dict[str, Any]], bool]:
+        """
+        Fetch a response from ComputerAgent based on the observation.
+
+        Args:
+            observation: The preprocessed observation, attributes: 
+                screenshot: Base64 encoded PNG string of the screen
+                text: Text observation, if available
+
+        Returns:
+            tuple[list[dict[str, Any]], bool, list[LogType] | None]: A tuple containing the list of raw actions,
+                                             boolean indicating if the agent believes the task is complete.
+        """
+        try:
+            # Update the computer handler with the current screenshot
+            if observation.screenshot:
+                self.hud_computer.update_screenshot(observation.screenshot)
+
+            # Set up action callback to capture actions
+            captured_actions = []
+            action_done = False
+
+            async def action_callback(action: Dict[str, Any]) -> None:
+                """Callback to capture actions from ComputerAgent."""
+                nonlocal captured_actions, action_done
+                captured_actions.append(action)
+
+            # Set the action callback
+            self.hud_computer.set_action_callback(action_callback)
+
+            # Prepare the message for ComputerAgent
+            if not self.conversation_history:
+                # First interaction - use the observation text as initial prompt
+                if observation.text:
+                    self.initial_prompt = observation.text
+                    message = f"{self.base_system_prompt}\n\nTask: {observation.text}"
+                else:
+                    message = f"{self.base_system_prompt}\n\nPlease analyze the current screen and determine what action to take."
+                
+                input_content = [
+                    {"type": "input_text", "text": message}
+                ]
+
+                # Add screenshot if present
+                if observation.screenshot:
+                    input_content.append(
+                        {
+                            "type": "input_image",
+                            "image_url": f"data:image/png;base64,{observation.screenshot}",
+                        }
+                    )
+
+                self.conversation_history.append({"role": "user", "content": input_content})                    
+            else:
+                # Subsequent interactions - check if last action was computer_call
+                # If so, add computer_call_output with screenshot instead of user message
+                last_computer_calls = []
+                for msg in reversed(self.conversation_history):
+                    if msg.get("type") == "computer_call":
+                        call_id = msg.get("call_id")
+                        if call_id:
+                            # Check if this call_id already has a computer_call_output
+                            has_output = any(
+                                m.get("type") == "computer_call_output" and m.get("call_id") == call_id
+                                for m in self.conversation_history
+                            )
+                            if not has_output:
+                                last_computer_calls.append(call_id)
+                
+                if last_computer_calls:
+                    if not observation.screenshot:
+                        print("No screenshot found, taking screenshot")
+                    screenshot_b64 = await self.hud_computer.screenshot()
+                    # Add computer_call_output for each unresponded computer_call
+                    for call_id in reversed(last_computer_calls):  # Maintain order
+                        self.conversation_history.append({
+                            "type": "computer_call_output",
+                            "call_id": call_id,
+                            "output": {
+                                "type": "input_image",
+                                "image_url": f"data:image/png;base64,{screenshot_b64}"
+                            }
+                        })
+                else:
+                    # No computer_call found, add regular user message
+                    message = "Continue with the task based on the current screen state."
+                    input_content = [
+                        {"type": "input_text", "text": message}
+                    ]
+
+                    # Add screenshot if present
+                    if observation.screenshot:
+                        input_content.append(
+                            {
+                                "type": "input_image",
+                                "image_url": f"data:image/png;base64,{observation.screenshot}",
+                            }
+                        )
+
+                    self.conversation_history.append({"role": "user", "content": input_content})                  
+
+                # If the last message is a reasoning message, change it to output_text
+                if (self.conversation_history and 
+                    self.conversation_history[-1].get("type") == "reasoning" and 
+                    self.conversation_history[-1].get("summary")):
+                    
+                    reasoning_msg = self.conversation_history[-1]
+                    summary_texts = []
+                    
+                    # Extract all summary_text entries
+                    for summary_item in reasoning_msg["summary"]:
+                        if summary_item.get("type") == "summary_text":
+                            summary_texts.append(summary_item.get("text", ""))
+                    
+                    # Convert to message format with output_text
+                    if summary_texts:
+                        converted_message = {
+                            "type": "message",
+                            "role": "assistant",
+                            "content": [
+                                {
+                                    "text": " ".join(summary_texts),
+                                    "type": "output_text"
+                                }
+                            ]
+                        }
+                        
+                        # Replace the reasoning message with the converted message
+                        self.conversation_history[-1] = converted_message
+
+            # Run ComputerAgent
+            try:
+                new_items = []
+
+                # ComputerAgent.run returns an async generator
+                try:
+                    async for result in self.computer_agent.run(self.conversation_history, stream=False):
+                        # if the result has computer_call_output, immediately exit
+                        if result.get("output", []) and result.get("output", [])[-1].get("type") == "computer_call_output":
+                            break
+                        # otherwise add agent output to conversation history
+                        new_items += result["output"]
+                except Exception as e:
+                    # if the last message is reasoning, change it to output_text
+                    if new_items and new_items[-1].get("type") == "reasoning":
+                        new_items[-1] = {
+                            "type": "message",
+                            "role": "assistant",
+                            "content": [
+                                {
+                                    "text": new_items[-1].get("summary", [{}])[0].get("text", ""),
+                                    "type": "output_text"
+                                }
+                            ]
+                        }
+                    # Check if there are any computer_call items in new_items
+                    computer_calls = [item for item in new_items if item.get("type") == "computer_call"]
+                    if computer_calls:
+                        # Remove computer_call items from new_items
+                        new_items = [item for item in new_items if item.get("type") != "computer_call"]
+                        
+                        # Add failed tool call items for each computer call
+                        for computer_call in computer_calls:
+                            tool_input = computer_call.get("action", {})
+                            call_id = computer_call.get("call_id")
+                            new_items.extend(make_failed_tool_call_items(
+                                tool_name="computer",
+                                tool_kwargs=tool_input,
+                                error_message=repr(e),
+                                call_id=call_id
+                            ))
+                    else:
+                        # add error message to conversation history (fallback for non-computer-call errors)
+                        new_items.append({
+                            "type": "user",
+                            "content": [
+                                {
+                                    "type": "input_text",
+                                    "text": f"Error during previous attempted action: {repr(e)}"
+                                }
+                            ]
+                        })
+
+                # Check if we captured any actions
+                if captured_actions:
+                    # Extract reasoning from the conversation history
+                    reasoning = ""
+                    # Look for the latest reasoning message
+                    for msg in reversed(new_items):
+                        if msg.get("type") == "reasoning" and msg.get("summary"):
+                            reasoning = " ".join([s.get("text", "") for s in msg["summary"] if s.get("type") == "summary_text"])
+                            break
+                        elif msg.get("type") == "message" and msg.get("role") == "assistant":
+                            content = msg.get("content", [])
+                            if isinstance(content, list):
+                                reasoning = " ".join([c.get("text", "") for c in content if c.get("type") == "output_text"])
+                            break
+                    
+                    # update conversation history
+                    self.conversation_history += new_items
+
+                    # Add reasoning and logs to each action
+                    for action in captured_actions:
+                        action["reasoning"] = reasoning
+                        action["logs"] = {"conversation_length": len(self.conversation_history)}
+                    
+                    return captured_actions, False
+                    
+                # Check if the last message is "Task completed"
+                response_text = ""
+                for msg in reversed(new_items):
+                    if msg.get("type") == "message" and msg.get("role") == "assistant":
+                        content = msg.get("content", [])
+                        for c in content:
+                            if c.get("type") == "output_text":
+                                response_text = c.get("text", response_text)
+                                break
+                        break
+                
+                done = "task completed" in response_text.lower()
+                
+                # update conversation history
+                self.conversation_history += new_items
+                
+                response_action = {
+                    "type": "response",
+                    "text": response_text,
+                    "reasoning": response_text,
+                    "logs": {"conversation_length": len(self.conversation_history)}
+                }
+                
+                # Check if this indicates task completion or failure
+                if "task is infeasible" in response_text.lower():
+                    response_action = {"type": "custom", "action": "FAIL"}
+                    done = True
+                
+                return [response_action], done
+            except Exception as e:
+                logger.error(f"Error running ComputerAgent: {e}")
+                # Return an error response
+                error_action = {
+                    "type": "response", 
+                    "text": f"Error occurred: {str(e)}",
+                    "reasoning": f"ComputerAgent encountered an error: {str(e)}",
+                    "logs": {"error": str(e)}
+                }
+                return [error_action], True
+
+        except Exception as e:
+            logger.error(f"Error in fetch_response: {e}")
+            error_action = {
+                "type": "response",
+                "text": f"Error in agent processing: {str(e)}",
+                "reasoning": f"Agent processing error: {str(e)}",
+                "logs": {"error": str(e)}
+            }
+            return [error_action], True