update README.md and app

Author: mannaandpoem

README.md

@@ -62,15 +62,15 @@ api_key = "sk-..."  # Replace with your actual API key
 ```
 
 ## Quick Start
-One line for run OpenManus:  
+One line for run OpenManus:
 
 ```bash
 python main.py
 ```
 
 Then input your idea via terminal!
 
-## How to contribute 
+## How to contribute
 We welcome any friendly suggestions and helpful contributions! Just create issues or submit pull requests.
 
 Or contact @mannaandpoem via 📧email: [email protected]
@@ -84,6 +84,6 @@ Or contact @mannaandpoem via 📧email: [email protected]
 
 ## Acknowledgement
 
-Thanks to [broswer use](https://github.com/browser-use/browser-use) for providing basic support for this project!
+Thanks to [anthropic-computer-use](https://github.com/anthropics/anthropic-quickstarts/tree/main/computer-use-demo) and [broswer-use](https://github.com/browser-use/browser-use) for providing basic support for this project!
 
 OpenManus is built by contributors from MetaGPT. Huge thanks to this agent community!

app/agent/manus.py

@@ -1,15 +1,12 @@
-from pydantic import Field, model_validator
+from pydantic import Field
 
-from app.agent.planning import PlanningAgent
 from app.agent.toolcall_en import ToolCallAgent
-from app.tool import ToolCollection, Bash, Terminate
-from app.tool.planning import PlanningTool
+from app.prompt.manus import NEXT_STEP_PROMPT, SYSTEM_PROMPT
+from app.tool import Terminate, ToolCollection
 from app.tool.browser_use_tool import BrowserUseTool
+from app.tool.file_saver import FileSaver
 from app.tool.google_search import GoogleSearch
 from app.tool.python_execute import PythonExecute
-from app.tool.file_saver import FileSaver
-
-from app.prompt.manus import SYSTEM_PROMPT, NEXT_STEP_PROMPT
 
 
 class Manus(ToolCallAgent):
@@ -22,7 +19,9 @@ class Manus(ToolCallAgent):
     """
 
     name: str = "Manus"
-    description: str = "A versatile agent that can solve various tasks using multiple tools"
+    description: str = (
+        "A versatile agent that can solve various tasks using multiple tools"
+    )
 
     system_prompt: str = SYSTEM_PROMPT
     next_step_prompt: str = NEXT_STEP_PROMPT
@@ -33,4 +32,3 @@ class Manus(ToolCallAgent):
             PythonExecute(), GoogleSearch(), BrowserUseTool(), FileSaver(), Terminate()
         )
     )
-

app/agent/planning.py

@@ -5,37 +5,11 @@
 
 from app.agent.toolcall import ToolCallAgent
 from app.logger import logger
+from app.prompt.planning import NEXT_STEP_PROMPT, PLANNING_SYSTEM_PROMPT
 from app.schema import Message, ToolCall
 from app.tool import PlanningTool, Terminate, ToolCollection
 
 
-PLANNING_SYSTEM_PROMPT = """
-You are an expert Planning Agent tasked with solving complex problems by creating and managing structured plans.
-Your job is:
-1. Analyze requests to understand the task scope
-2. Create clear, actionable plans with the `planning` tool
-3. Execute steps using available tools as needed
-4. Track progress and adapt plans dynamically
-5. Use `finish` to conclude when the task is complete
-
-Available tools will vary by task but may include:
-- `planning`: Create, update, and track plans (commands: create, update, mark_step, etc.)
-- `finish`: End the task when complete
-
-Break tasks into logical, sequential steps. Think about dependencies and verification methods.
-"""
-
-NEXT_STEP_PROMPT = """
-Based on the current state, what's your next step?
-Consider:
-1. Do you need to create or refine a plan?
-2. Are you ready to execute a specific step?
-3. Have you completed the task?
-
-Provide reasoning, then select the appropriate tool or action.
-"""
-
-
 class PlanningAgent(ToolCallAgent):
     """
     An agent that creates and manages plans to solve tasks.

app/agent/toolcall_en.py

@@ -9,6 +9,7 @@
 from app.schema import AgentState, Message, ToolCall
 from app.tool import CreateChatCompletion, Terminate, ToolCollection
 
+
 TOOL_CALL_REQUIRED = "Tool calls required but none provided"
 
 
@@ -40,23 +41,31 @@ async def think(self) -> bool:
         # Get response with tool options
         response = await self.llm.ask_tool(
             messages=self.messages,
-            system_msgs=[Message.system_message(self.system_prompt)] if self.system_prompt else None,
+            system_msgs=[Message.system_message(self.system_prompt)]
+            if self.system_prompt
+            else None,
             tools=self.available_tools.to_params(),
             tool_choice=self.tool_choices,
         )
         self.tool_calls = response.tool_calls
 
         # Log response info in a more engaging way
         logger.info(f"✨ AI's thoughts: {response.content}")
-        logger.info(f"🛠️ AI selected {len(response.tool_calls) if response.tool_calls else 0} tools to use")
+        logger.info(
+            f"🛠️ AI selected {len(response.tool_calls) if response.tool_calls else 0} tools to use"
+        )
         if response.tool_calls:
-            logger.info(f"🧰 Tools being prepared: {[call.function.name for call in response.tool_calls]}")
+            logger.info(
+                f"🧰 Tools being prepared: {[call.function.name for call in response.tool_calls]}"
+            )
 
         try:
             # Handle different tool_choices modes
             if self.tool_choices == "none":
                 if response.tool_calls:
-                    logger.warning("🤔 Hmm, AI tried to use tools when they weren't available!")
+                    logger.warning(
+                        "🤔 Hmm, AI tried to use tools when they weren't available!"
+                    )
                 if response.content:
                     self.memory.add_message(Message.assistant_message(response.content))
                     return True
@@ -82,9 +91,11 @@ async def think(self) -> bool:
             return bool(self.tool_calls)
         except Exception as e:
             logger.error(f"🚨 Oops! The AI's thinking process hit a snag: {e}")
-            self.memory.add_message(Message.assistant_message(
-                f"Error encountered while processing: {str(e)}"
-            ))
+            self.memory.add_message(
+                Message.assistant_message(
+                    f"Error encountered while processing: {str(e)}"
+                )
+            )
             return False
 
     async def act(self) -> str:
@@ -94,9 +105,7 @@ async def act(self) -> str:
                 raise ValueError(TOOL_CALL_REQUIRED)
 
             # Return last message content if no tool calls
-            return (
-                self.messages[-1].content or "No content or commands to execute"
-            )
+            return self.messages[-1].content or "No content or commands to execute"
 
         results = []
         for command in self.tool_calls:
@@ -144,7 +153,9 @@ async def execute_tool(self, command: ToolCall) -> str:
             return observation
         except json.JSONDecodeError:
             error_msg = f"Error parsing arguments for {name}: Invalid JSON format"
-            logger.error(f"📝 Oops! The arguments for '{name}' don't make sense - invalid JSON")
+            logger.error(
+                f"📝 Oops! The arguments for '{name}' don't make sense - invalid JSON"
+            )
             return f"Error: {error_msg}"
         except Exception as e:
             error_msg = f"Error executing tool {name}: {str(e)}"

app/agent/toolcall_zh.py

@@ -9,6 +9,7 @@
 from app.schema import AgentState, Message, ToolCall
 from app.tool import CreateChatCompletion, Terminate, ToolCollection
 
+
 TOOL_CALL_REQUIRED = "Tool calls required but none provided"
 
 
@@ -40,17 +41,23 @@ async def think(self) -> bool:
         # Get response with tool options
         response = await self.llm.ask_tool(
             messages=self.messages,
-            system_msgs=[Message.system_message(self.system_prompt)] if self.system_prompt else None,
+            system_msgs=[Message.system_message(self.system_prompt)]
+            if self.system_prompt
+            else None,
             tools=self.available_tools.to_params(),
             tool_choice=self.tool_choices,
         )
         self.tool_calls = response.tool_calls
 
         # Log response info in a more engaging way
         logger.info(f"✨ AI的思考过程：{response.content}")
-        logger.info(f"🛠️ AI选择了 {len(response.tool_calls) if response.tool_calls else 0} 个工具来解决问题")
+        logger.info(
+            f"🛠️ AI选择了 {len(response.tool_calls) if response.tool_calls else 0} 个工具来解决问题"
+        )
         if response.tool_calls:
-            logger.info(f"🧰 准备使用的工具箱：{[call.function.name for call in response.tool_calls]}")
+            logger.info(
+                f"🧰 准备使用的工具箱：{[call.function.name for call in response.tool_calls]}"
+            )
 
         try:
             # Handle different tool_choices modes
@@ -82,9 +89,11 @@ async def think(self) -> bool:
             return bool(self.tool_calls)
         except Exception as e:
             logger.error(f"🚨 糟糕！AI思考时遇到了一点小问题：{e}")
-            self.memory.add_message(Message.assistant_message(
-                f"Error encountered while processing: {str(e)}"
-            ))
+            self.memory.add_message(
+                Message.assistant_message(
+                    f"Error encountered while processing: {str(e)}"
+                )
+            )
             return False
 
     async def act(self) -> str:
@@ -94,9 +103,7 @@ async def act(self) -> str:
                 raise ValueError(TOOL_CALL_REQUIRED)
 
             # Return last message content if no tool calls
-            return (
-                self.messages[-1].content or "No content or commands to execute"
-            )
+            return self.messages[-1].content or "No content or commands to execute"
 
         results = []
         for command in self.tool_calls:

app/config.py

@@ -1,7 +1,7 @@
 import threading
 import tomllib
 from pathlib import Path
-from typing import Dict, Optional
+from typing import Dict
 
 from pydantic import BaseModel, Field
 
@@ -23,14 +23,8 @@ class LLMSettings(BaseModel):
     temperature: float = Field(1.0, description="Sampling temperature")
 
 
-class ScreenshotSettings(BaseModel):
-    api_key: Optional[str] = Field(None, description="Screenshot API key")
-    base_url: Optional[str] = Field(None, description="Screenshot service URL")
-
-
 class AppConfig(BaseModel):
     llm: Dict[str, LLMSettings]
-    screenshot: Optional[ScreenshotSettings] = None
 
 
 class Config:
@@ -94,16 +88,8 @@ def _load_initial_config(self):
             }
         }
 
-        # Add screenshot config if present
-        if screenshot_config := raw_config.get("screenshot"):
-            config_dict["screenshot"] = screenshot_config
-
         self._config = AppConfig(**config_dict)
 
-    @property
-    def screenshot(self) -> Optional[ScreenshotSettings]:
-        return self._config.screenshot
-
     @property
     def llm(self) -> Dict[str, LLMSettings]:
         return self._config.llm

app/exceptions.py

@@ -3,10 +3,3 @@ class ToolError(Exception):
 
     def __init__(self, message):
         self.message = message
-
-
-class BrowserException(Exception):
-    """Base exception for browser-related errors."""
-
-    def __init__(self, message):
-        super().__init__(message)

app/logger.py

@@ -22,7 +22,7 @@ def define_log_level(print_level="INFO", logfile_level="DEBUG", name: str = None
 
     _logger.remove()
     _logger.add(sys.stderr, level=print_level)
-    _logger.add(PROJECT_ROOT / f"logs/{log_name}.txt", level=logfile_level)
+    _logger.add(PROJECT_ROOT / f"logs/{log_name}.log", level=logfile_level)
     return _logger
 
 

app/loop.py

@@ -11,4 +11,4 @@
 GoogleSearch: Perform web information retrieval
 
 Based on user needs, proactively select the most appropriate tool or combination of tools. For complex tasks, you can break down the problem and use different tools step by step to solve it. After using each tool, clearly explain the execution results and suggest the next steps.
-"""
+"""

app/prompt/manus.py

@@ -0,0 +1,25 @@
+PLANNING_SYSTEM_PROMPT = """
+You are an expert Planning Agent tasked with solving complex problems by creating and managing structured plans.
+Your job is:
+1. Analyze requests to understand the task scope
+2. Create clear, actionable plans with the `planning` tool
+3. Execute steps using available tools as needed
+4. Track progress and adapt plans dynamically
+5. Use `finish` to conclude when the task is complete
+
+Available tools will vary by task but may include:
+- `planning`: Create, update, and track plans (commands: create, update, mark_step, etc.)
+- `finish`: End the task when complete
+
+Break tasks into logical, sequential steps. Think about dependencies and verification methods.
+"""
+
+NEXT_STEP_PROMPT = """
+Based on the current state, what's your next step?
+Consider:
+1. Do you need to create or refine a plan?
+2. Are you ready to execute a specific step?
+3. Have you completed the task?
+
+Provide reasoning, then select the appropriate tool or action.
+"""