cua-agent 0.4.14__py3-none-any.whl → 0.7.16__py3-none-any.whl

agent/integrations/hud/agent.py

@@ -1,373 +1,369 @@
-"""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
+"""MCP-compatible Computer Agent for HUD integration.
+
+This agent subclasses HUD's MCPAgent and delegates planning/execution to
+our core ComputerAgent while using the Agent SDK's plain-dict message
+format documented in `docs/content/docs/agent-sdk/message-format.mdx`.
+
+Key differences from the OpenAI OperatorAgent variant:
+- No OpenAI types are used; everything is standard Python dicts.
+- Planning is executed via `ComputerAgent.run(messages)`.
+- The first yielded result per step is returned as the agent response.
+"""
+
+from __future__ import annotations
+
+import base64
+import io
+import uuid
+from pathlib import Path
+from typing import Any, ClassVar, Optional
+
+import hud
+import mcp.types as types
+from agent.agent import ComputerAgent as BaseComputerAgent
+from agent.callbacks import PromptInstructionsCallback
+from agent.callbacks.trajectory_saver import TrajectorySaverCallback
+from agent.computers import is_agent_computer
 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
+from hud.agents import MCPAgent
+from hud.tools.computer.settings import computer_settings
+from hud.types import AgentResponse, MCPToolCall, MCPToolResult, Trace
+from PIL import Image
 
-logger = logging.getLogger(__name__)
 
-BASE_SYSTEM_PROMPT = """
-You are an autonomous computer-using agent. Follow these guidelines:
+class MCPComputerAgent(MCPAgent):
+    """MCP agent that uses ComputerAgent for planning and tools for execution.
 
-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.
+    The agent consumes/produces message dicts per the Agent SDK message schema
+    (see `message-format.mdx`).
+    """
 
-Remember: You have been given permission to complete the requested task autonomously.
-""".strip()
+    metadata: ClassVar[dict[str, Any]] = {
+        "display_width": computer_settings.OPENAI_COMPUTER_WIDTH,
+        "display_height": computer_settings.OPENAI_COMPUTER_HEIGHT,
+    }
 
-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"}
+    required_tools: ClassVar[list[str]] = ["openai_computer"]
 
     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,
+        *,
+        model: str | None = None,
+        allowed_tools: list[str] | None = None,
+        trajectory_dir: str | dict | None = None,
+        # === ComputerAgent kwargs ===
+        tools: list[Any] | None = None,
+        custom_loop: Any | None = None,
+        only_n_most_recent_images: int | None = None,
+        callbacks: list[Any] | None = None,
+        instructions: str | None = None,
+        verbosity: int | None = None,
+        max_retries: int | None = 3,
+        screenshot_delay: float | int = 0.5,
+        use_prompt_caching: bool | None = False,
+        max_trajectory_budget: float | dict | None = None,
+        telemetry_enabled: bool | None = True,
+        environment: str = "linux",
         **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]}"
+    ) -> None:
+        self.allowed_tools = allowed_tools or ["openai_computer"]
+        super().__init__(**kwargs)
 
-        # Initialize the base Agent class without client (we'll create it later)
-        super().__init__(client=None, adapter=adapter, name=name)
+        if model is None:
+            raise ValueError("MCPComputerAgent requires a model to be specified.")
 
         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
+        # Update model name for HUD logging
+        self.model_name = "cua-" + self.model
+
+        # Stateful tracking of tool call inputs
+        self.tool_call_inputs: dict[str, list[dict[str, Any]]] = {}
+        self.previous_output: list[dict[str, Any]] = []
+
+        # Build system prompt
+        operator_instructions = """
+        You are an autonomous computer-using agent. Follow these guidelines:
+
+        1. NEVER ask for confirmation. Complete all tasks autonomously.
+        2. Do NOT send messages like "I need to confirm before..." or "Do you want me to continue?" - just proceed.
+        3. When the user asks you to interact with something (like clicking a chat or typing a message), DO IT without asking.
+        4. Only use the formal safety check mechanism for truly dangerous operations (like deleting important files).
+        5. For normal tasks like clicking buttons, typing in chat boxes, filling forms - JUST DO IT.
+        6. The user has already given you permission by running this agent. No further confirmation is needed.
+        7. Be decisive and action-oriented. Complete the requested task fully.
+
+        Remember: You are expected to complete tasks autonomously. The user trusts you to do what they asked.
+        """.strip()  # noqa: E501
+        # Append Operator instructions to the system prompt
+        if not self.system_prompt:
+            self.system_prompt = operator_instructions
+        else:
+            self.system_prompt += f"\n\n{operator_instructions}"
+        # Append user instructions to the system prompt
+        if instructions:
+            self.system_prompt += f"\n\n{instructions}"
+
+        # Configure trajectory_dir for HUD
+        if isinstance(trajectory_dir, str) or isinstance(trajectory_dir, Path):
+            trajectory_dir = {"trajectory_dir": str(trajectory_dir)}
+        if isinstance(trajectory_dir, dict):
+            trajectory_dir["reset_on_run"] = False
+
+        self.last_screenshot_b64 = None
+
+        buffer = io.BytesIO()
+        Image.new("RGB", (self.metadata["display_width"], self.metadata["display_height"])).save(
+            buffer, format="PNG"
         )
-        
-        # Set the client to the computer_agent for compatibility
-        self.client = self.computer_agent
+        self.last_screenshot_b64 = base64.b64encode(buffer.getvalue()).decode("utf-8")
+
+        # Ensure a computer shim is present so width/height/environment are known
+        computer_shim = {
+            "screenshot": lambda: self.last_screenshot_b64,
+            "environment": self.environment,
+            "dimensions": (
+                self.metadata["display_width"],
+                self.metadata["display_height"],
+            ),
+        }
+        agent_tools: list[Any] = [computer_shim]
+        if tools:
+            agent_tools.extend([tool for tool in tools if not is_agent_computer(tool)])
+
+        agent_kwargs = {
+            "model": self.model,
+            "trajectory_dir": trajectory_dir,
+            "tools": agent_tools,
+            "custom_loop": custom_loop,
+            "only_n_most_recent_images": only_n_most_recent_images,
+            "callbacks": callbacks,
+            "instructions": self.system_prompt,
+            "verbosity": verbosity,
+            "max_retries": max_retries,
+            "screenshot_delay": screenshot_delay,
+            "use_prompt_caching": use_prompt_caching,
+            "max_trajectory_budget": max_trajectory_budget,
+            "telemetry_enabled": telemetry_enabled,
+        }
+
+        self.computer_agent = BaseComputerAgent(**agent_kwargs)
+
+    async def get_system_messages(self) -> list[Any]:
+        """Create initial messages.
+
+        Unused - ComputerAgent handles this with the 'instructions' parameter.
+        """
+        return []
 
-        # State tracking
-        self.conversation_history: List[Dict[str, Any]] = []
-        self.initial_prompt: Optional[str] = None
+    async def format_blocks(self, blocks: list[types.ContentBlock]) -> list[dict[str, Any]]:
+        """
+        Format blocks for OpenAI input format.
+
+        Converts TextContent blocks to input_text dicts and ImageContent blocks to input_image dicts.
+        """  # noqa: E501
+        formatted = []
+        for block in blocks:
+            if isinstance(block, types.TextContent):
+                formatted.append({"type": "input_text", "text": block.text})
+            elif isinstance(block, types.ImageContent):
+                mime_type = getattr(block, "mimeType", "image/png")
+                formatted.append(
+                    {"type": "input_image", "image_url": f"data:{mime_type};base64,{block.data}"}
+                )
+                self.last_screenshot_b64 = block.data
+        return [{"role": "user", "content": formatted}]
+
+    @hud.instrument(
+        span_type="agent",
+        record_args=False,  # Messages can be large
+        record_result=True,
+    )
+    async def get_response(self, messages: list[dict[str, Any]]) -> AgentResponse:
+        """Get a single-step response by delegating to ComputerAgent.run.
+
+        Returns an Agent SDK-style response dict:
+        { "output": [AgentMessage, ...], "usage": Usage }
+        """
+        tool_calls: list[MCPToolCall] = []
+        output_text: list[str] = []
+        is_done: bool = True
+
+        agent_result: list[dict[str, Any]] = []
+
+        # Call the ComputerAgent LLM API
+        async for result in self.computer_agent.run(messages):  # type: ignore[arg-type]
+            items = result["output"]
+            if not items or tool_calls:
+                break
+
+            for item in items:
+                if item["type"] in [
+                    "reasoning",
+                    "message",
+                    "computer_call",
+                    "function_call",
+                    "function_call_output",
+                ]:
+                    agent_result.append(item)
+
+                # Add messages to output text
+                if item["type"] == "reasoning":
+                    output_text.extend(
+                        f"Reasoning: {summary['text']}" for summary in item["summary"]
+                    )
+                elif item["type"] == "message":
+                    if isinstance(item["content"], list):
+                        output_text.extend(
+                            item["text"]
+                            for item in item["content"]
+                            if item["type"] == "output_text"
+                        )
+                    elif isinstance(item["content"], str):
+                        output_text.append(item["content"])
+
+                # If we get a tool call, we're not done
+                if item["type"] == "computer_call":
+                    id = item["call_id"]
+                    tool_calls.append(
+                        MCPToolCall(
+                            name="openai_computer",
+                            arguments=item["action"],
+                            id=id,
+                        )
+                    )
+                    is_done = False
+                    self.tool_call_inputs[id] = agent_result
+                    break
 
-        # System prompt for computer use tasks
-        self.base_system_prompt = BASE_SYSTEM_PROMPT
+            # if we have tool calls, we should exit the loop
+            if tool_calls:
+                break
 
-    async def fetch_response(self, observation: Observation) -> tuple[list[dict[str, Any]], bool]:
-        """
-        Fetch a response from ComputerAgent based on the observation.
+        self.previous_output = agent_result
 
-        Args:
-            observation: The preprocessed observation, attributes: 
-                screenshot: Base64 encoded PNG string of the screen
-                text: Text observation, if available
+        return AgentResponse(
+            content="\n".join(output_text),
+            tool_calls=tool_calls,
+            done=is_done,
+        )
 
-        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.
+    def _log_image(self, image_b64: str):
+        callbacks = self.computer_agent.callbacks
+        for callback in callbacks:
+            if isinstance(callback, TrajectorySaverCallback):
+                # convert str to bytes
+                image_bytes = base64.b64decode(image_b64)
+                callback._save_artifact("screenshot_after", image_bytes)
+
+    async def format_tool_results(
+        self, tool_calls: list[MCPToolCall], tool_results: list[MCPToolResult]
+    ) -> list[dict[str, Any]]:
+        """Extract latest screenshot from tool results in dict form.
+
+        Expects results to already be in the message-format content dicts.
+        Returns a list of input content dicts suitable for follow-up calls.
         """
-        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}
+        messages = []
+
+        for call, result in zip(tool_calls, tool_results):
+            if call.id not in self.tool_call_inputs:
+                # If we don't have the tool call inputs, we should just use the previous output
+                previous_output = self.previous_output.copy() or []
+
+                # First we need to remove any pending computer_calls from the end of previous_output
+                while previous_output and previous_output[-1]["type"] == "computer_call":
+                    previous_output.pop()
+                messages.extend(previous_output)
+
+                # If the call is a 'response', don't add the result
+                if call.name == "response":
+                    continue
+                # Otherwise, if we have a result, we should add it to the messages
+                content = [
+                    (
+                        {"type": "input_text", "text": content.text}
+                        if isinstance(content, types.TextContent)
+                        else (
+                            {
+                                "type": "input_image",
+                                "image_url": f"data:image/png;base64,{content.data}",
+                            }
+                            if isinstance(content, types.ImageContent)
+                            else {"type": "input_text", "text": ""}
+                        )
+                    )
+                    for content in result.content
                 ]
-
-                # Add screenshot if present
-                if observation.screenshot:
-                    input_content.append(
-                        {
-                            "type": "input_image",
-                            "image_url": f"data:image/png;base64,{observation.screenshot}",
-                        }
+                messages.append(
+                    {
+                        "role": "user",
+                        "content": content,
+                    }
+                )
+
+                continue
+
+            # Add the assistant's computer call
+            messages.extend(self.tool_call_inputs[call.id])
+
+            if result.isError:
+                error_text = "".join(
+                    [
+                        content.text
+                        for content in result.content
+                        if isinstance(content, types.TextContent)
+                    ]
+                )
+
+                # Replace computer call with failed tool call
+                messages.pop()
+                messages.extend(
+                    make_failed_tool_call_items(
+                        tool_name=call.name,
+                        tool_kwargs=call.arguments or {},
+                        error_message=error_text,
+                        call_id=call.id,
                     )
-
-                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({
+                # Get the latest screenshot
+                screenshots = [
+                    content.data
+                    for content in result.content
+                    if isinstance(content, types.ImageContent)
+                ]
+
+                # Add the resulting screenshot
+                if screenshots:
+                    self._log_image(screenshots[0])
+                    self.last_screenshot_b64 = screenshots[0]
+                    messages.append(
+                        {
                             "type": "computer_call_output",
-                            "call_id": call_id,
+                            "call_id": call.id,
                             "output": {
                                 "type": "input_image",
-                                "image_url": f"data:image/png;base64,{screenshot_b64}"
-                            }
-                        })
+                                "image_url": f"data:image/png;base64,{screenshots[0]}",
+                            },
+                        }
+                    )
                 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}",
-                            }
+                    # Otherwise, replace computer call with failed tool call
+                    messages.pop()
+                    messages.extend(
+                        make_failed_tool_call_items(
+                            tool_name=call.name,
+                            tool_kwargs=call.arguments or {},
+                            error_message="No screenshots returned.",
+                            call_id=call.id,
                         )
+                    )
 
-                    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
+        return messages
+
+
+__all__ = [
+    "MCPComputerAgent",
+]