merge: main from upstream

.gitignore

@@ -194,3 +194,6 @@ cython_debug/
 
 # Built Visual Studio Code Extensions
 *.vsix
+
+# OSX
+.DS_Store

app/agent/__init__.py

@@ -1,4 +1,5 @@
 from app.agent.base import BaseAgent
+from app.agent.browser import BrowserAgent
 from app.agent.planning import PlanningAgent
 from app.agent.react import ReActAgent
 from app.agent.swe import SWEAgent
@@ -7,6 +8,7 @@ from app.agent.toolcall import ToolCallAgent
 
 __all__ = [
     "BaseAgent",
+    "BrowserAgent",
     "PlanningAgent",
     "ReActAgent",
     "SWEAgent",

app/agent/base.py

@@ -6,6 +6,7 @@ from pydantic import BaseModel, Field, model_validator
 
 from app.llm import LLM
 from app.logger import logger
+from app.sandbox.client import SANDBOX_CLIENT
 from app.schema import ROLE_TYPE, AgentState, Memory, Message
 
 
@@ -149,7 +150,7 @@ class BaseAgent(BaseModel, ABC):
                 self.current_step = 0
                 self.state = AgentState.IDLE
                 results.append(f"Terminated: Reached max steps ({self.max_steps})")
-
+        await SANDBOX_CLIENT.cleanup()
         return "\n".join(results) if results else "No steps executed"
 
     @abstractmethod

app/agent/browser.py

@@ -0,0 +1,129 @@
+import json
+from typing import Any, Optional
+
+from pydantic import Field
+
+from app.agent.toolcall import ToolCallAgent
+from app.logger import logger
+from app.prompt.browser import NEXT_STEP_PROMPT, SYSTEM_PROMPT
+from app.schema import Message, ToolChoice
+from app.tool import BrowserUseTool, Terminate, ToolCollection
+
+
+class BrowserAgent(ToolCallAgent):
+    """
+    A browser agent that uses the browser_use library to control a browser.
+
+    This agent can navigate web pages, interact with elements, fill forms,
+    extract content, and perform other browser-based actions to accomplish tasks.
+    """
+
+    name: str = "browser"
+    description: str = "A browser agent that can control a browser to accomplish tasks"
+
+    system_prompt: str = SYSTEM_PROMPT
+    next_step_prompt: str = NEXT_STEP_PROMPT
+
+    max_observe: int = 10000
+    max_steps: int = 20
+
+    # Configure the available tools
+    available_tools: ToolCollection = Field(
+        default_factory=lambda: ToolCollection(BrowserUseTool(), Terminate())
+    )
+
+    # Use Auto for tool choice to allow both tool usage and free-form responses
+    tool_choices: ToolChoice = ToolChoice.AUTO
+    special_tool_names: list[str] = Field(default_factory=lambda: [Terminate().name])
+
+    _current_base64_image: Optional[str] = None
+
+    async def _handle_special_tool(self, name: str, result: Any, **kwargs):
+        if not self._is_special_tool(name):
+            return
+        else:
+            await self.available_tools.get_tool(BrowserUseTool().name).cleanup()
+            await super()._handle_special_tool(name, result, **kwargs)
+
+    async def get_browser_state(self) -> Optional[dict]:
+        """Get the current browser state for context in next steps."""
+        browser_tool = self.available_tools.get_tool(BrowserUseTool().name)
+        if not browser_tool:
+            return None
+
+        try:
+            # Get browser state directly from the tool
+            result = await browser_tool.get_current_state()
+
+            if result.error:
+                logger.debug(f"Browser state error: {result.error}")
+                return None
+
+            # Store screenshot if available
+            if hasattr(result, "base64_image") and result.base64_image:
+                self._current_base64_image = result.base64_image
+
+            # Parse the state info
+            return json.loads(result.output)
+
+        except Exception as e:
+            logger.debug(f"Failed to get browser state: {str(e)}")
+            return None
+
+    async def think(self) -> bool:
+        """Process current state and decide next actions using tools, with browser state info added"""
+        # Add browser state to the context
+        browser_state = await self.get_browser_state()
+
+        # Initialize placeholder values
+        url_info = ""
+        tabs_info = ""
+        content_above_info = ""
+        content_below_info = ""
+        results_info = ""
+
+        if browser_state and not browser_state.get("error"):
+            # URL and title info
+            url_info = f"\n   URL: {browser_state.get('url', 'N/A')}\n   Title: {browser_state.get('title', 'N/A')}"
+
+            # Tab information
+            if "tabs" in browser_state:
+                tabs = browser_state.get("tabs", [])
+                if tabs:
+                    tabs_info = f"\n   {len(tabs)} tab(s) available"
+
+            # Content above/below viewport
+            pixels_above = browser_state.get("pixels_above", 0)
+            pixels_below = browser_state.get("pixels_below", 0)
+
+            if pixels_above > 0:
+                content_above_info = f" ({pixels_above} pixels)"
+
+            if pixels_below > 0:
+                content_below_info = f" ({pixels_below} pixels)"
+
+            # Add screenshot as base64 if available
+            if self._current_base64_image:
+                # Create a message with image attachment
+                image_message = Message.user_message(
+                    content="Current browser screenshot:",
+                    base64_image=self._current_base64_image,
+                )
+                self.memory.add_message(image_message)
+
+        # Replace placeholders with actual browser state info
+        self.next_step_prompt = NEXT_STEP_PROMPT.format(
+            url_placeholder=url_info,
+            tabs_placeholder=tabs_info,
+            content_above_placeholder=content_above_info,
+            content_below_placeholder=content_below_info,
+            results_placeholder=results_info,
+        )
+
+        # Call parent implementation
+        result = await super().think()
+
+        # Reset the next_step_prompt to its original state
+        self.next_step_prompt = NEXT_STEP_PROMPT
+
+        return result

app/agent/manus.py

@@ -1,12 +1,8 @@
-import json
-import os
-from pathlib import Path
-from typing import Any, Optional
-
 from pydantic import Field
 
-from app.agent.toolcall import ToolCallAgent
-from app.logger import logger
+from app.agent.browser import BrowserAgent
+from app.config import config
+from app.prompt.browser import NEXT_STEP_PROMPT as BROWSER_NEXT_STEP_PROMPT
 from app.prompt.manus import NEXT_STEP_PROMPT, SYSTEM_PROMPT
 from app.tool import Terminate, ToolCollection
 from app.tool.browser_use_tool import BrowserUseTool
@@ -14,14 +10,11 @@ from app.tool.python_execute import PythonExecute
 from app.tool.str_replace_editor import StrReplaceEditor
 
 
-initial_working_directory = Path(os.getcwd()) / "workspace"
-
-
-class Manus(ToolCallAgent):
+class Manus(BrowserAgent):
     """
     A versatile general-purpose agent that uses planning to solve various tasks.
 
-    This agent extends PlanningAgent with a comprehensive set of tools and capabilities,
+    This agent extends BrowserAgent with a comprehensive set of tools and capabilities,
     including Python execution, web browsing, file operations, and information retrieval
     to handle a wide range of user requests.
     """
@@ -31,7 +24,7 @@ class Manus(ToolCallAgent):
         "A versatile agent that can solve various tasks using multiple tools"
     )
 
-    system_prompt: str = SYSTEM_PROMPT.format(directory=initial_working_directory)
+    system_prompt: str = SYSTEM_PROMPT.format(directory=config.workspace_root)
     next_step_prompt: str = NEXT_STEP_PROMPT
 
     max_observe: int = 10000
@@ -44,48 +37,24 @@ class Manus(ToolCallAgent):
         )
     )
 
-    async def _handle_special_tool(self, name: str, result: Any, **kwargs):
-        if not self._is_special_tool(name):
-            return
-        else:
-            await self.available_tools.get_tool(BrowserUseTool().name).cleanup()
-            await super()._handle_special_tool(name, result, **kwargs)
-
-    async def get_browser_state(self) -> Optional[dict]:
-        """Get the current browser state for context in next steps."""
-        browser_tool = self.available_tools.get_tool(BrowserUseTool().name)
-        if not browser_tool:
-            return None
-
-        try:
-            # Get browser state directly from the tool with no context parameter
-            result = await browser_tool.get_current_state()
-
-            if result.error:
-                logger.debug(f"Browser state error: {result.error}")
-                return None
-
-            # Store screenshot if available
-            if hasattr(result, "base64_image") and result.base64_image:
-                self._current_base64_image = result.base64_image
-
-            # Parse the state info
-            return json.loads(result.output)
-
-        except Exception as e:
-            logger.debug(f"Failed to get browser state: {str(e)}")
-            return None
-
     async def think(self) -> bool:
-        # Add your custom pre-processing here
-        browser_state = await self.get_browser_state()
-
-        # Modify the next_step_prompt temporarily
+        """Process current state and decide next actions with appropriate context."""
+        # Store original prompt
         original_prompt = self.next_step_prompt
-        if browser_state and not browser_state.get("error"):
-            self.next_step_prompt += f"\nCurrent browser state:\nURL: {browser_state.get('url', 'N/A')}\nTitle: {browser_state.get('title', 'N/A')}\n"
 
-        # Call parent implementation
+        # Only check recent messages (last 3) for browser activity
+        recent_messages = self.memory.messages[-3:] if self.memory.messages else []
+        browser_in_use = any(
+            "browser_use" in msg.content.lower()
+            for msg in recent_messages
+            if hasattr(msg, "content") and isinstance(msg.content, str)
+        )
+
+        if browser_in_use:
+            # Override with browser-specific prompt temporarily to get browser context
+            self.next_step_prompt = BROWSER_NEXT_STEP_PROMPT
+
+        # Call parent's think method
         result = await super().think()
 
         # Restore original prompt

app/config.py

@@ -25,7 +25,7 @@ class LLMSettings(BaseModel):
         description="Maximum input tokens to use across all requests (None for unlimited)",
     )
     temperature: float = Field(1.0, description="Sampling temperature")
-    api_type: str = Field(..., description="AzureOpenai or Openai")
+    api_type: str = Field(..., description="Azure, Openai, or Ollama")
     api_version: str = Field(..., description="Azure Openai version if AzureOpenai")
 
 
@@ -64,8 +64,25 @@ class BrowserSettings(BaseModel):
     )
 
 
+class SandboxSettings(BaseModel):
+    """Configuration for the execution sandbox"""
+
+    use_sandbox: bool = Field(False, description="Whether to use the sandbox")
+    image: str = Field("python:3.12-slim", description="Base image")
+    work_dir: str = Field("/workspace", description="Container working directory")
+    memory_limit: str = Field("512m", description="Memory limit")
+    cpu_limit: float = Field(1.0, description="CPU limit")
+    timeout: int = Field(300, description="Default command timeout (seconds)")
+    network_enabled: bool = Field(
+        False, description="Whether network access is allowed"
+    )
+
+
 class AppConfig(BaseModel):
     llm: Dict[str, LLMSettings]
+    sandbox: Optional[SandboxSettings] = Field(
+        None, description="Sandbox configuration"
+    )
     browser_config: Optional[BrowserSettings] = Field(
         None, description="Browser configuration"
     )
@@ -168,6 +185,11 @@ class Config:
         search_settings = None
         if search_config:
             search_settings = SearchSettings(**search_config)
+        sandbox_config = raw_config.get("sandbox", {})
+        if sandbox_config:
+            sandbox_settings = SandboxSettings(**sandbox_config)
+        else:
+            sandbox_settings = SandboxSettings()
 
         config_dict = {
             "llm": {
@@ -177,6 +199,7 @@ class Config:
                     for name, override_config in llm_overrides.items()
                 },
             },
+            "sandbox": sandbox_settings,
             "browser_config": browser_settings,
             "search_config": search_settings,
         }
@@ -187,6 +210,10 @@ class Config:
     def llm(self) -> Dict[str, LLMSettings]:
         return self._config.llm
 
+    @property
+    def sandbox(self) -> SandboxSettings:
+        return self._config.sandbox
+
     @property
     def browser_config(self) -> Optional[BrowserSettings]:
         return self._config.browser_config
@@ -195,5 +222,10 @@ class Config:
     def search_config(self) -> Optional[SearchSettings]:
         return self._config.search_config
 
+    @property
+    def workspace_root(self) -> Path:
+        """Get the workspace root directory"""
+        return WORKSPACE_ROOT
+
 
 config = Config()

app/llm.py

@@ -30,6 +30,14 @@ from app.schema import (
 
 
 REASONING_MODELS = ["o1", "o3-mini"]
+MULTIMODAL_MODELS = [
+    "gpt-4-vision-preview",
+    "gpt-4o",
+    "gpt-4o-mini",
+    "claude-3-opus-20240229",
+    "claude-3-sonnet-20240229",
+    "claude-3-haiku-20240307",
+]
 
 
 class TokenCounter:
@@ -196,6 +204,7 @@ class LLM:
 
             # Add token counting related attributes
             self.total_input_tokens = 0
+            self.total_completion_tokens = 0
             self.max_input_tokens = (
                 llm_config.max_input_tokens
                 if hasattr(llm_config, "max_input_tokens")
@@ -229,12 +238,15 @@ class LLM:
     def count_message_tokens(self, messages: List[dict]) -> int:
         return self.token_counter.count_message_tokens(messages)
 
-    def update_token_count(self, input_tokens: int) -> None:
+    def update_token_count(self, input_tokens: int, completion_tokens: int = 0) -> None:
         """Update token counts"""
         # Only track tokens if max_input_tokens is set
         self.total_input_tokens += input_tokens
+        self.total_completion_tokens += completion_tokens
         logger.info(
-            f"Token usage: Input={input_tokens}, Cumulative Input={self.total_input_tokens}"
+            f"Token usage: Input={input_tokens}, Completion={completion_tokens}, "
+            f"Cumulative Input={self.total_input_tokens}, Cumulative Completion={self.total_completion_tokens}, "
+            f"Total={input_tokens + completion_tokens}, Cumulative Total={self.total_input_tokens + self.total_completion_tokens}"
         )
 
     def check_token_limit(self, input_tokens: int) -> bool:
@@ -255,12 +267,15 @@ class LLM:
         return "Token limit exceeded"
 
     @staticmethod
-    def format_messages(messages: List[Union[dict, Message]]) -> List[dict]:
+    def format_messages(
+        messages: List[Union[dict, Message]], supports_images: bool = False
+    ) -> List[dict]:
         """
         Format messages for LLM by converting them to OpenAI message format.
 
         Args:
             messages: List of messages that can be either dict or Message objects
+            supports_images: Flag indicating if the target model supports image inputs
 
         Returns:
             List[dict]: List of formatted messages in OpenAI format
@@ -284,20 +299,20 @@ class LLM:
             if isinstance(message, Message):
                 message = message.to_dict()
 
-            if not isinstance(message, dict):
-                raise TypeError(f"Unsupported message type: {type(message)}")
-
-            # Validate required fields
+            if isinstance(message, dict):
+                # If message is a dict, ensure it has required fields
                 if "role" not in message:
                     raise ValueError("Message dict must contain 'role' field")
 
-            # Process base64 images if present
-            if message.get("base64_image"):
+                # Process base64 images if present and model supports images
+                if supports_images and message.get("base64_image"):
                     # Initialize or convert content to appropriate format
                     if not message.get("content"):
                         message["content"] = []
                     elif isinstance(message["content"], str):
-                    message["content"] = [{"type": "text", "text": message["content"]}]
+                        message["content"] = [
+                            {"type": "text", "text": message["content"]}
+                        ]
                     elif isinstance(message["content"], list):
                         # Convert string items to proper text objects
                         message["content"] = [
@@ -321,17 +336,21 @@ class LLM:
 
                     # Remove the base64_image field
                     del message["base64_image"]
+                # If model doesn't support images but message has base64_image, handle gracefully
+                elif not supports_images and message.get("base64_image"):
+                    # Just remove the base64_image field and keep the text content
+                    del message["base64_image"]
 
-            # Only include messages with content or tool_calls
                 if "content" in message or "tool_calls" in message:
                     formatted_messages.append(message)
+                # else: do not include the message
+            else:
+                raise TypeError(f"Unsupported message type: {type(message)}")
 
-        # Validate all roles
-        invalid_roles = [
-            msg for msg in formatted_messages if msg["role"] not in ROLE_VALUES
-        ]
-        if invalid_roles:
-            raise ValueError(f"Invalid role: {invalid_roles[0]['role']}")
+        # Validate all messages have required fields
+        for msg in formatted_messages:
+            if msg["role"] not in ROLE_VALUES:
+                raise ValueError(f"Invalid role: {msg['role']}")
 
         return formatted_messages
 
@@ -368,12 +387,15 @@ class LLM:
             Exception: For unexpected errors
         """
         try:
-            # Format system and user messages
+            # Check if the model supports images
+            supports_images = self.model in MULTIMODAL_MODELS
+
+            # Format system and user messages with image support check
             if system_msgs:
-                system_msgs = self.format_messages(system_msgs)
-                messages = system_msgs + self.format_messages(messages)
+                system_msgs = self.format_messages(system_msgs, supports_images)
+                messages = system_msgs + self.format_messages(messages, supports_images)
             else:
-                messages = self.format_messages(messages)
+                messages = self.format_messages(messages, supports_images)
 
             # Calculate input token count
             input_tokens = self.count_message_tokens(messages)
@@ -407,8 +429,9 @@ class LLM:
                     raise ValueError("Empty or invalid response from LLM")
 
                 # Update token counts
-                if response.usage:
-                    self.update_token_count(response.usage.prompt_tokens)
+                self.update_token_count(
+                    response.usage.prompt_tokens, response.usage.completion_tokens
+                )
 
                 return response.choices[0].message.content
 
@@ -418,9 +441,11 @@ class LLM:
             response = await self.client.chat.completions.create(**params, stream=True)
 
             collected_messages = []
+            completion_text = ""
             async for chunk in response:
                 chunk_message = chunk.choices[0].delta.content or ""
                 collected_messages.append(chunk_message)
+                completion_text += chunk_message
                 print(chunk_message, end="", flush=True)
 
             print()  # Newline after streaming
@@ -428,7 +453,12 @@ class LLM:
             if not full_response:
                 raise ValueError("Empty response from streaming LLM")
 
-            # TODO Update token counts
+            # estimate completion tokens for streaming response
+            completion_tokens = self.count_tokens(completion_text)
+            logger.info(
+                f"Estimated completion tokens for streaming response: {completion_tokens}"
+            )
+            self.total_completion_tokens += completion_tokens
 
             return full_response
 
@@ -486,8 +516,15 @@ class LLM:
             Exception: For unexpected errors
         """
         try:
-            # Format messages
-            formatted_messages = self.format_messages(messages)
+            # For ask_with_images, we always set supports_images to True because
+            # this method should only be called with models that support images
+            if self.model not in MULTIMODAL_MODELS:
+                raise ValueError(
+                    f"Model {self.model} does not support images. Use a model from {MULTIMODAL_MODELS}"
+                )
+
+            # Format messages with image support
+            formatted_messages = self.format_messages(messages, supports_images=True)
 
             # Ensure the last message is from the user to attach images
             if not formatted_messages or formatted_messages[-1]["role"] != "user":
@@ -526,7 +563,10 @@ class LLM:
 
             # Add system messages if provided
             if system_msgs:
-                all_messages = self.format_messages(system_msgs) + formatted_messages
+                all_messages = (
+                    self.format_messages(system_msgs, supports_images=True)
+                    + formatted_messages
+                )
             else:
                 all_messages = formatted_messages
 
@@ -640,12 +680,15 @@ class LLM:
             if tool_choice not in TOOL_CHOICE_VALUES:
                 raise ValueError(f"Invalid tool_choice: {tool_choice}")
 
+            # Check if the model supports images
+            supports_images = self.model in MULTIMODAL_MODELS
+
             # Format messages
             if system_msgs:
-                system_msgs = self.format_messages(system_msgs)
-                messages = system_msgs + self.format_messages(messages)
+                system_msgs = self.format_messages(system_msgs, supports_images)
+                messages = system_msgs + self.format_messages(messages, supports_images)
             else:
-                messages = self.format_messages(messages)
+                messages = self.format_messages(messages, supports_images)
 
             # Calculate input token count
             input_tokens = self.count_message_tokens(messages)
@@ -696,7 +739,9 @@ class LLM:
                 raise ValueError("Invalid or empty response from LLM")
 
             # Update token counts
-            self.update_token_count(response.usage.prompt_tokens)
+            self.update_token_count(
+                response.usage.prompt_tokens, response.usage.completion_tokens
+            )
 
             return response.choices[0].message
 

app/prompt/browser.py

@@ -0,0 +1,92 @@
+SYSTEM_PROMPT = """\
+You are an AI agent designed to automate browser tasks. Your goal is to accomplish the ultimate task following the rules.
+
+# Input Format
+Task
+Previous steps
+Current URL
+Open Tabs
+Interactive Elements
+[index]<type>text</type>
+- index: Numeric identifier for interaction
+- type: HTML element type (button, input, etc.)
+- text: Element description
+Example:
+[33]<button>Submit Form</button>
+
+- Only elements with numeric indexes in [] are interactive
+- elements without [] provide only context
+
+# Response Rules
+1. RESPONSE FORMAT: You must ALWAYS respond with valid JSON in this exact format:
+{{"current_state": {{"evaluation_previous_goal": "Success|Failed|Unknown - Analyze the current elements and the image to check if the previous goals/actions are successful like intended by the task. Mention if something unexpected happened. Shortly state why/why not",
+"memory": "Description of what has been done and what you need to remember. Be very specific. Count here ALWAYS how many times you have done something and how many remain. E.g. 0 out of 10 websites analyzed. Continue with abc and xyz",
+"next_goal": "What needs to be done with the next immediate action"}},
+"action":[{{"one_action_name": {{// action-specific parameter}}}}, // ... more actions in sequence]}}
+
+2. ACTIONS: You can specify multiple actions in the list to be executed in sequence. But always specify only one action name per item. Use maximum {{max_actions}} actions per sequence.
+Common action sequences:
+- Form filling: [{{"input_text": {{"index": 1, "text": "username"}}}}, {{"input_text": {{"index": 2, "text": "password"}}}}, {{"click_element": {{"index": 3}}}}]
+- Navigation and extraction: [{{"go_to_url": {{"url": "https://example.com"}}}}, {{"extract_content": {{"goal": "extract the names"}}}}]
+- Actions are executed in the given order
+- If the page changes after an action, the sequence is interrupted and you get the new state.
+- Only provide the action sequence until an action which changes the page state significantly.
+- Try to be efficient, e.g. fill forms at once, or chain actions where nothing changes on the page
+- only use multiple actions if it makes sense.
+
+3. ELEMENT INTERACTION:
+- Only use indexes of the interactive elements
+- Elements marked with "[]Non-interactive text" are non-interactive
+
+4. NAVIGATION & ERROR HANDLING:
+- If no suitable elements exist, use other functions to complete the task
+- If stuck, try alternative approaches - like going back to a previous page, new search, new tab etc.
+- Handle popups/cookies by accepting or closing them
+- Use scroll to find elements you are looking for
+- If you want to research something, open a new tab instead of using the current tab
+- If captcha pops up, try to solve it - else try a different approach
+- If the page is not fully loaded, use wait action
+
+5. TASK COMPLETION:
+- Use the done action as the last action as soon as the ultimate task is complete
+- Dont use "done" before you are done with everything the user asked you, except you reach the last step of max_steps.
+- If you reach your last step, use the done action even if the task is not fully finished. Provide all the information you have gathered so far. If the ultimate task is completly finished set success to true. If not everything the user asked for is completed set success in done to false!
+- If you have to do something repeatedly for example the task says for "each", or "for all", or "x times", count always inside "memory" how many times you have done it and how many remain. Don't stop until you have completed like the task asked you. Only call done after the last step.
+- Don't hallucinate actions
+- Make sure you include everything you found out for the ultimate task in the done text parameter. Do not just say you are done, but include the requested information of the task.
+
+6. VISUAL CONTEXT:
+- When an image is provided, use it to understand the page layout
+- Bounding boxes with labels on their top right corner correspond to element indexes
+
+7. Form filling:
+- If you fill an input field and your action sequence is interrupted, most often something changed e.g. suggestions popped up under the field.
+
+8. Long tasks:
+- Keep track of the status and subresults in the memory.
+
+9. Extraction:
+- If your task is to find information - call extract_content on the specific pages to get and store the information.
+Your responses must be always JSON with the specified format.
+"""
+
+NEXT_STEP_PROMPT = """
+What should I do next to achieve my goal?
+
+When you see [Current state starts here], focus on the following:
+- Current URL and page title{url_placeholder}
+- Available tabs{tabs_placeholder}
+- Interactive elements and their indices
+- Content above{content_above_placeholder} or below{content_below_placeholder} the viewport (if indicated)
+- Any action results or errors{results_placeholder}
+
+For browser interactions:
+- To navigate: browser_use with action="go_to_url", url="..."
+- To click: browser_use with action="click_element", index=N
+- To type: browser_use with action="input_text", index=N, text="..."
+- To extract: browser_use with action="extract_content", goal="..."
+- To scroll: browser_use with action="scroll_down" or "scroll_up"
+
+Consider both what's visible and what might be beyond the current viewport.
+Be methodical - remember your progress and what you've learned so far.
+"""

app/sandbox/__init__.py

@@ -0,0 +1,30 @@
+"""
+Docker Sandbox Module
+
+Provides secure containerized execution environment with resource limits
+and isolation for running untrusted code.
+"""
+from app.sandbox.client import (
+    BaseSandboxClient,
+    LocalSandboxClient,
+    create_sandbox_client,
+)
+from app.sandbox.core.exceptions import (
+    SandboxError,
+    SandboxResourceError,
+    SandboxTimeoutError,
+)
+from app.sandbox.core.manager import SandboxManager
+from app.sandbox.core.sandbox import DockerSandbox
+
+
+__all__ = [
+    "DockerSandbox",
+    "SandboxManager",
+    "BaseSandboxClient",
+    "LocalSandboxClient",
+    "create_sandbox_client",
+    "SandboxError",
+    "SandboxTimeoutError",
+    "SandboxResourceError",
+]

app/sandbox/client.py

@@ -0,0 +1,201 @@
+from abc import ABC, abstractmethod
+from typing import Dict, Optional, Protocol
+
+from app.config import SandboxSettings
+from app.sandbox.core.sandbox import DockerSandbox
+
+
+class SandboxFileOperations(Protocol):
+    """Protocol for sandbox file operations."""
+
+    async def copy_from(self, container_path: str, local_path: str) -> None:
+        """Copies file from container to local.
+
+        Args:
+            container_path: File path in container.
+            local_path: Local destination path.
+        """
+        ...
+
+    async def copy_to(self, local_path: str, container_path: str) -> None:
+        """Copies file from local to container.
+
+        Args:
+            local_path: Local source file path.
+            container_path: Destination path in container.
+        """
+        ...
+
+    async def read_file(self, path: str) -> str:
+        """Reads file content from container.
+
+        Args:
+            path: File path in container.
+
+        Returns:
+            str: File content.
+        """
+        ...
+
+    async def write_file(self, path: str, content: str) -> None:
+        """Writes content to file in container.
+
+        Args:
+            path: File path in container.
+            content: Content to write.
+        """
+        ...
+
+
+class BaseSandboxClient(ABC):
+    """Base sandbox client interface."""
+
+    @abstractmethod
+    async def create(
+        self,
+        config: Optional[SandboxSettings] = None,
+        volume_bindings: Optional[Dict[str, str]] = None,
+    ) -> None:
+        """Creates sandbox."""
+
+    @abstractmethod
+    async def run_command(self, command: str, timeout: Optional[int] = None) -> str:
+        """Executes command."""
+
+    @abstractmethod
+    async def copy_from(self, container_path: str, local_path: str) -> None:
+        """Copies file from container."""
+
+    @abstractmethod
+    async def copy_to(self, local_path: str, container_path: str) -> None:
+        """Copies file to container."""
+
+    @abstractmethod
+    async def read_file(self, path: str) -> str:
+        """Reads file."""
+
+    @abstractmethod
+    async def write_file(self, path: str, content: str) -> None:
+        """Writes file."""
+
+    @abstractmethod
+    async def cleanup(self) -> None:
+        """Cleans up resources."""
+
+
+class LocalSandboxClient(BaseSandboxClient):
+    """Local sandbox client implementation."""
+
+    def __init__(self):
+        """Initializes local sandbox client."""
+        self.sandbox: Optional[DockerSandbox] = None
+
+    async def create(
+        self,
+        config: Optional[SandboxSettings] = None,
+        volume_bindings: Optional[Dict[str, str]] = None,
+    ) -> None:
+        """Creates a sandbox.
+
+        Args:
+            config: Sandbox configuration.
+            volume_bindings: Volume mappings.
+
+        Raises:
+            RuntimeError: If sandbox creation fails.
+        """
+        self.sandbox = DockerSandbox(config, volume_bindings)
+        await self.sandbox.create()
+
+    async def run_command(self, command: str, timeout: Optional[int] = None) -> str:
+        """Runs command in sandbox.
+
+        Args:
+            command: Command to execute.
+            timeout: Execution timeout in seconds.
+
+        Returns:
+            Command output.
+
+        Raises:
+            RuntimeError: If sandbox not initialized.
+        """
+        if not self.sandbox:
+            raise RuntimeError("Sandbox not initialized")
+        return await self.sandbox.run_command(command, timeout)
+
+    async def copy_from(self, container_path: str, local_path: str) -> None:
+        """Copies file from container to local.
+
+        Args:
+            container_path: File path in container.
+            local_path: Local destination path.
+
+        Raises:
+            RuntimeError: If sandbox not initialized.
+        """
+        if not self.sandbox:
+            raise RuntimeError("Sandbox not initialized")
+        await self.sandbox.copy_from(container_path, local_path)
+
+    async def copy_to(self, local_path: str, container_path: str) -> None:
+        """Copies file from local to container.
+
+        Args:
+            local_path: Local source file path.
+            container_path: Destination path in container.
+
+        Raises:
+            RuntimeError: If sandbox not initialized.
+        """
+        if not self.sandbox:
+            raise RuntimeError("Sandbox not initialized")
+        await self.sandbox.copy_to(local_path, container_path)
+
+    async def read_file(self, path: str) -> str:
+        """Reads file from container.
+
+        Args:
+            path: File path in container.
+
+        Returns:
+            File content.
+
+        Raises:
+            RuntimeError: If sandbox not initialized.
+        """
+        if not self.sandbox:
+            raise RuntimeError("Sandbox not initialized")
+        return await self.sandbox.read_file(path)
+
+    async def write_file(self, path: str, content: str) -> None:
+        """Writes file to container.
+
+        Args:
+            path: File path in container.
+            content: File content.
+
+        Raises:
+            RuntimeError: If sandbox not initialized.
+        """
+        if not self.sandbox:
+            raise RuntimeError("Sandbox not initialized")
+        await self.sandbox.write_file(path, content)
+
+    async def cleanup(self) -> None:
+        """Cleans up resources."""
+        if self.sandbox:
+            await self.sandbox.cleanup()
+            self.sandbox = None
+
+
+def create_sandbox_client() -> LocalSandboxClient:
+    """Creates a sandbox client.
+
+    Returns:
+        LocalSandboxClient: Sandbox client instance.
+    """
+    return LocalSandboxClient()
+
+
+SANDBOX_CLIENT = create_sandbox_client()

app/sandbox/core/exceptions.py

@@ -0,0 +1,17 @@
+"""Exception classes for the sandbox system.
+
+This module defines custom exceptions used throughout the sandbox system to
+handle various error conditions in a structured way.
+"""
+
+
+class SandboxError(Exception):
+    """Base exception for sandbox-related errors."""
+
+
+class SandboxTimeoutError(SandboxError):
+    """Exception raised when a sandbox operation times out."""
+
+
+class SandboxResourceError(SandboxError):
+    """Exception raised for resource-related errors."""

app/sandbox/core/manager.py

@@ -0,0 +1,313 @@
+import asyncio
+import uuid
+from contextlib import asynccontextmanager
+from typing import Dict, Optional, Set
+
+import docker
+from docker.errors import APIError, ImageNotFound
+
+from app.config import SandboxSettings
+from app.logger import logger
+from app.sandbox.core.sandbox import DockerSandbox
+
+
+class SandboxManager:
+    """Docker sandbox manager.
+
+    Manages multiple DockerSandbox instances lifecycle including creation,
+    monitoring, and cleanup. Provides concurrent access control and automatic
+    cleanup mechanisms for sandbox resources.
+
+    Attributes:
+        max_sandboxes: Maximum allowed number of sandboxes.
+        idle_timeout: Sandbox idle timeout in seconds.
+        cleanup_interval: Cleanup check interval in seconds.
+        _sandboxes: Active sandbox instance mapping.
+        _last_used: Last used time record for sandboxes.
+    """
+
+    def __init__(
+        self,
+        max_sandboxes: int = 100,
+        idle_timeout: int = 3600,
+        cleanup_interval: int = 300,
+    ):
+        """Initializes sandbox manager.
+
+        Args:
+            max_sandboxes: Maximum sandbox count limit.
+            idle_timeout: Idle timeout in seconds.
+            cleanup_interval: Cleanup check interval in seconds.
+        """
+        self.max_sandboxes = max_sandboxes
+        self.idle_timeout = idle_timeout
+        self.cleanup_interval = cleanup_interval
+
+        # Docker client
+        self._client = docker.from_env()
+
+        # Resource mappings
+        self._sandboxes: Dict[str, DockerSandbox] = {}
+        self._last_used: Dict[str, float] = {}
+
+        # Concurrency control
+        self._locks: Dict[str, asyncio.Lock] = {}
+        self._global_lock = asyncio.Lock()
+        self._active_operations: Set[str] = set()
+
+        # Cleanup task
+        self._cleanup_task: Optional[asyncio.Task] = None
+        self._is_shutting_down = False
+
+        # Start automatic cleanup
+        self.start_cleanup_task()
+
+    async def ensure_image(self, image: str) -> bool:
+        """Ensures Docker image is available.
+
+        Args:
+            image: Image name.
+
+        Returns:
+            bool: Whether image is available.
+        """
+        try:
+            self._client.images.get(image)
+            return True
+        except ImageNotFound:
+            try:
+                logger.info(f"Pulling image {image}...")
+                await asyncio.get_event_loop().run_in_executor(
+                    None, self._client.images.pull, image
+                )
+                return True
+            except (APIError, Exception) as e:
+                logger.error(f"Failed to pull image {image}: {e}")
+                return False
+
+    @asynccontextmanager
+    async def sandbox_operation(self, sandbox_id: str):
+        """Context manager for sandbox operations.
+
+        Provides concurrency control and usage time updates.
+
+        Args:
+            sandbox_id: Sandbox ID.
+
+        Raises:
+            KeyError: If sandbox not found.
+        """
+        if sandbox_id not in self._locks:
+            self._locks[sandbox_id] = asyncio.Lock()
+
+        async with self._locks[sandbox_id]:
+            if sandbox_id not in self._sandboxes:
+                raise KeyError(f"Sandbox {sandbox_id} not found")
+
+            self._active_operations.add(sandbox_id)
+            try:
+                self._last_used[sandbox_id] = asyncio.get_event_loop().time()
+                yield self._sandboxes[sandbox_id]
+            finally:
+                self._active_operations.remove(sandbox_id)
+
+    async def create_sandbox(
+        self,
+        config: Optional[SandboxSettings] = None,
+        volume_bindings: Optional[Dict[str, str]] = None,
+    ) -> str:
+        """Creates a new sandbox instance.
+
+        Args:
+            config: Sandbox configuration.
+            volume_bindings: Volume mapping configuration.
+
+        Returns:
+            str: Sandbox ID.
+
+        Raises:
+            RuntimeError: If max sandbox count reached or creation fails.
+        """
+        async with self._global_lock:
+            if len(self._sandboxes) >= self.max_sandboxes:
+                raise RuntimeError(
+                    f"Maximum number of sandboxes ({self.max_sandboxes}) reached"
+                )
+
+            config = config or SandboxSettings()
+            if not await self.ensure_image(config.image):
+                raise RuntimeError(f"Failed to ensure Docker image: {config.image}")
+
+            sandbox_id = str(uuid.uuid4())
+            try:
+                sandbox = DockerSandbox(config, volume_bindings)
+                await sandbox.create()
+
+                self._sandboxes[sandbox_id] = sandbox
+                self._last_used[sandbox_id] = asyncio.get_event_loop().time()
+                self._locks[sandbox_id] = asyncio.Lock()
+
+                logger.info(f"Created sandbox {sandbox_id}")
+                return sandbox_id
+
+            except Exception as e:
+                logger.error(f"Failed to create sandbox: {e}")
+                if sandbox_id in self._sandboxes:
+                    await self.delete_sandbox(sandbox_id)
+                raise RuntimeError(f"Failed to create sandbox: {e}")
+
+    async def get_sandbox(self, sandbox_id: str) -> DockerSandbox:
+        """Gets a sandbox instance.
+
+        Args:
+            sandbox_id: Sandbox ID.
+
+        Returns:
+            DockerSandbox: Sandbox instance.
+
+        Raises:
+            KeyError: If sandbox does not exist.
+        """
+        async with self.sandbox_operation(sandbox_id) as sandbox:
+            return sandbox
+
+    def start_cleanup_task(self) -> None:
+        """Starts automatic cleanup task."""
+
+        async def cleanup_loop():
+            while not self._is_shutting_down:
+                try:
+                    await self._cleanup_idle_sandboxes()
+                except Exception as e:
+                    logger.error(f"Error in cleanup loop: {e}")
+                await asyncio.sleep(self.cleanup_interval)
+
+        self._cleanup_task = asyncio.create_task(cleanup_loop())
+
+    async def _cleanup_idle_sandboxes(self) -> None:
+        """Cleans up idle sandboxes."""
+        current_time = asyncio.get_event_loop().time()
+        to_cleanup = []
+
+        async with self._global_lock:
+            for sandbox_id, last_used in self._last_used.items():
+                if (
+                    sandbox_id not in self._active_operations
+                    and current_time - last_used > self.idle_timeout
+                ):
+                    to_cleanup.append(sandbox_id)
+
+        for sandbox_id in to_cleanup:
+            try:
+                await self.delete_sandbox(sandbox_id)
+            except Exception as e:
+                logger.error(f"Error cleaning up sandbox {sandbox_id}: {e}")
+
+    async def cleanup(self) -> None:
+        """Cleans up all resources."""
+        logger.info("Starting manager cleanup...")
+        self._is_shutting_down = True
+
+        # Cancel cleanup task
+        if self._cleanup_task:
+            self._cleanup_task.cancel()
+            try:
+                await asyncio.wait_for(self._cleanup_task, timeout=1.0)
+            except (asyncio.CancelledError, asyncio.TimeoutError):
+                pass
+
+        # Get all sandbox IDs to clean up
+        async with self._global_lock:
+            sandbox_ids = list(self._sandboxes.keys())
+
+        # Concurrently clean up all sandboxes
+        cleanup_tasks = []
+        for sandbox_id in sandbox_ids:
+            task = asyncio.create_task(self._safe_delete_sandbox(sandbox_id))
+            cleanup_tasks.append(task)
+
+        if cleanup_tasks:
+            # Wait for all cleanup tasks to complete, with timeout to avoid infinite waiting
+            try:
+                await asyncio.wait(cleanup_tasks, timeout=30.0)
+            except asyncio.TimeoutError:
+                logger.error("Sandbox cleanup timed out")
+
+        # Clean up remaining references
+        self._sandboxes.clear()
+        self._last_used.clear()
+        self._locks.clear()
+        self._active_operations.clear()
+
+        logger.info("Manager cleanup completed")
+
+    async def _safe_delete_sandbox(self, sandbox_id: str) -> None:
+        """Safely deletes a single sandbox.
+
+        Args:
+            sandbox_id: Sandbox ID to delete.
+        """
+        try:
+            if sandbox_id in self._active_operations:
+                logger.warning(
+                    f"Sandbox {sandbox_id} has active operations, waiting for completion"
+                )
+                for _ in range(10):  # Wait at most 10 times
+                    await asyncio.sleep(0.5)
+                    if sandbox_id not in self._active_operations:
+                        break
+                else:
+                    logger.warning(
+                        f"Timeout waiting for sandbox {sandbox_id} operations to complete"
+                    )
+
+            # Get reference to sandbox object
+            sandbox = self._sandboxes.get(sandbox_id)
+            if sandbox:
+                await sandbox.cleanup()
+
+                # Remove sandbox record from manager
+                async with self._global_lock:
+                    self._sandboxes.pop(sandbox_id, None)
+                    self._last_used.pop(sandbox_id, None)
+                    self._locks.pop(sandbox_id, None)
+                    logger.info(f"Deleted sandbox {sandbox_id}")
+        except Exception as e:
+            logger.error(f"Error during cleanup of sandbox {sandbox_id}: {e}")
+
+    async def delete_sandbox(self, sandbox_id: str) -> None:
+        """Deletes specified sandbox.
+
+        Args:
+            sandbox_id: Sandbox ID.
+        """
+        if sandbox_id not in self._sandboxes:
+            return
+
+        try:
+            await self._safe_delete_sandbox(sandbox_id)
+        except Exception as e:
+            logger.error(f"Failed to delete sandbox {sandbox_id}: {e}")
+
+    async def __aenter__(self) -> "SandboxManager":
+        """Async context manager entry."""
+        return self
+
+    async def __aexit__(self, exc_type, exc_val, exc_tb) -> None:
+        """Async context manager exit."""
+        await self.cleanup()
+
+    def get_stats(self) -> Dict:
+        """Gets manager statistics.
+
+        Returns:
+            Dict: Statistics information.
+        """
+        return {
+            "total_sandboxes": len(self._sandboxes),
+            "active_operations": len(self._active_operations),
+            "max_sandboxes": self.max_sandboxes,
+            "idle_timeout": self.idle_timeout,
+            "cleanup_interval": self.cleanup_interval,
+            "is_shutting_down": self._is_shutting_down,
+        }

app/sandbox/core/sandbox.py

@@ -0,0 +1,462 @@
+import asyncio
+import io
+import os
+import tarfile
+import tempfile
+import uuid
+from typing import Dict, Optional
+
+import docker
+from docker.errors import NotFound
+from docker.models.containers import Container
+
+from app.config import SandboxSettings
+from app.sandbox.core.exceptions import SandboxTimeoutError
+from app.sandbox.core.terminal import AsyncDockerizedTerminal
+
+
+class DockerSandbox:
+    """Docker sandbox environment.
+
+    Provides a containerized execution environment with resource limits,
+    file operations, and command execution capabilities.
+
+    Attributes:
+        config: Sandbox configuration.
+        volume_bindings: Volume mapping configuration.
+        client: Docker client.
+        container: Docker container instance.
+        terminal: Container terminal interface.
+    """
+
+    def __init__(
+        self,
+        config: Optional[SandboxSettings] = None,
+        volume_bindings: Optional[Dict[str, str]] = None,
+    ):
+        """Initializes a sandbox instance.
+
+        Args:
+            config: Sandbox configuration. Default configuration used if None.
+            volume_bindings: Volume mappings in {host_path: container_path} format.
+        """
+        self.config = config or SandboxSettings()
+        self.volume_bindings = volume_bindings or {}
+        self.client = docker.from_env()
+        self.container: Optional[Container] = None
+        self.terminal: Optional[AsyncDockerizedTerminal] = None
+
+    async def create(self) -> "DockerSandbox":
+        """Creates and starts the sandbox container.
+
+        Returns:
+            Current sandbox instance.
+
+        Raises:
+            docker.errors.APIError: If Docker API call fails.
+            RuntimeError: If container creation or startup fails.
+        """
+        try:
+            # Prepare container config
+            host_config = self.client.api.create_host_config(
+                mem_limit=self.config.memory_limit,
+                cpu_period=100000,
+                cpu_quota=int(100000 * self.config.cpu_limit),
+                network_mode="none" if not self.config.network_enabled else "bridge",
+                binds=self._prepare_volume_bindings(),
+            )
+
+            # Generate unique container name with sandbox_ prefix
+            container_name = f"sandbox_{uuid.uuid4().hex[:8]}"
+
+            # Create container
+            container = await asyncio.to_thread(
+                self.client.api.create_container,
+                image=self.config.image,
+                command="tail -f /dev/null",
+                hostname="sandbox",
+                working_dir=self.config.work_dir,
+                host_config=host_config,
+                name=container_name,
+                tty=True,
+                detach=True,
+            )
+
+            self.container = self.client.containers.get(container["Id"])
+
+            # Start container
+            await asyncio.to_thread(self.container.start)
+
+            # Initialize terminal
+            self.terminal = AsyncDockerizedTerminal(
+                container["Id"],
+                self.config.work_dir,
+                env_vars={"PYTHONUNBUFFERED": "1"}
+                # Ensure Python output is not buffered
+            )
+            await self.terminal.init()
+
+            return self
+
+        except Exception as e:
+            await self.cleanup()  # Ensure resources are cleaned up
+            raise RuntimeError(f"Failed to create sandbox: {e}") from e
+
+    def _prepare_volume_bindings(self) -> Dict[str, Dict[str, str]]:
+        """Prepares volume binding configuration.
+
+        Returns:
+            Volume binding configuration dictionary.
+        """
+        bindings = {}
+
+        # Create and add working directory mapping
+        work_dir = self._ensure_host_dir(self.config.work_dir)
+        bindings[work_dir] = {"bind": self.config.work_dir, "mode": "rw"}
+
+        # Add custom volume bindings
+        for host_path, container_path in self.volume_bindings.items():
+            bindings[host_path] = {"bind": container_path, "mode": "rw"}
+
+        return bindings
+
+    @staticmethod
+    def _ensure_host_dir(path: str) -> str:
+        """Ensures directory exists on the host.
+
+        Args:
+            path: Directory path.
+
+        Returns:
+            Actual path on the host.
+        """
+        host_path = os.path.join(
+            tempfile.gettempdir(),
+            f"sandbox_{os.path.basename(path)}_{os.urandom(4).hex()}",
+        )
+        os.makedirs(host_path, exist_ok=True)
+        return host_path
+
+    async def run_command(self, cmd: str, timeout: Optional[int] = None) -> str:
+        """Runs a command in the sandbox.
+
+        Args:
+            cmd: Command to execute.
+            timeout: Timeout in seconds.
+
+        Returns:
+            Command output as string.
+
+        Raises:
+            RuntimeError: If sandbox not initialized or command execution fails.
+            TimeoutError: If command execution times out.
+        """
+        if not self.terminal:
+            raise RuntimeError("Sandbox not initialized")
+
+        try:
+            return await self.terminal.run_command(
+                cmd, timeout=timeout or self.config.timeout
+            )
+        except TimeoutError:
+            raise SandboxTimeoutError(
+                f"Command execution timed out after {timeout or self.config.timeout} seconds"
+            )
+
+    async def read_file(self, path: str) -> str:
+        """Reads a file from the container.
+
+        Args:
+            path: File path.
+
+        Returns:
+            File contents as string.
+
+        Raises:
+            FileNotFoundError: If file does not exist.
+            RuntimeError: If read operation fails.
+        """
+        if not self.container:
+            raise RuntimeError("Sandbox not initialized")
+
+        try:
+            # Get file archive
+            resolved_path = self._safe_resolve_path(path)
+            tar_stream, _ = await asyncio.to_thread(
+                self.container.get_archive, resolved_path
+            )
+
+            # Read file content from tar stream
+            content = await self._read_from_tar(tar_stream)
+            return content.decode("utf-8")
+
+        except NotFound:
+            raise FileNotFoundError(f"File not found: {path}")
+        except Exception as e:
+            raise RuntimeError(f"Failed to read file: {e}")
+
+    async def write_file(self, path: str, content: str) -> None:
+        """Writes content to a file in the container.
+
+        Args:
+            path: Target path.
+            content: File content.
+
+        Raises:
+            RuntimeError: If write operation fails.
+        """
+        if not self.container:
+            raise RuntimeError("Sandbox not initialized")
+
+        try:
+            resolved_path = self._safe_resolve_path(path)
+            parent_dir = os.path.dirname(resolved_path)
+
+            # Create parent directory
+            if parent_dir:
+                await self.run_command(f"mkdir -p {parent_dir}")
+
+            # Prepare file data
+            tar_stream = await self._create_tar_stream(
+                os.path.basename(path), content.encode("utf-8")
+            )
+
+            # Write file
+            await asyncio.to_thread(
+                self.container.put_archive, parent_dir or "/", tar_stream
+            )
+
+        except Exception as e:
+            raise RuntimeError(f"Failed to write file: {e}")
+
+    def _safe_resolve_path(self, path: str) -> str:
+        """Safely resolves container path, preventing path traversal.
+
+        Args:
+            path: Original path.
+
+        Returns:
+            Resolved absolute path.
+
+        Raises:
+            ValueError: If path contains potentially unsafe patterns.
+        """
+        # Check for path traversal attempts
+        if ".." in path.split("/"):
+            raise ValueError("Path contains potentially unsafe patterns")
+
+        resolved = (
+            os.path.join(self.config.work_dir, path)
+            if not os.path.isabs(path)
+            else path
+        )
+        return resolved
+
+    async def copy_from(self, src_path: str, dst_path: str) -> None:
+        """Copies a file from the container.
+
+        Args:
+            src_path: Source file path (container).
+            dst_path: Destination path (host).
+
+        Raises:
+            FileNotFoundError: If source file does not exist.
+            RuntimeError: If copy operation fails.
+        """
+        try:
+            # Ensure destination file's parent directory exists
+            parent_dir = os.path.dirname(dst_path)
+            if parent_dir:
+                os.makedirs(parent_dir, exist_ok=True)
+
+            # Get file stream
+            resolved_src = self._safe_resolve_path(src_path)
+            stream, stat = await asyncio.to_thread(
+                self.container.get_archive, resolved_src
+            )
+
+            # Create temporary directory to extract file
+            with tempfile.TemporaryDirectory() as tmp_dir:
+                # Write stream to temporary file
+                tar_path = os.path.join(tmp_dir, "temp.tar")
+                with open(tar_path, "wb") as f:
+                    for chunk in stream:
+                        f.write(chunk)
+
+                # Extract file
+                with tarfile.open(tar_path) as tar:
+                    members = tar.getmembers()
+                    if not members:
+                        raise FileNotFoundError(f"Source file is empty: {src_path}")
+
+                    # If destination is a directory, we should preserve relative path structure
+                    if os.path.isdir(dst_path):
+                        tar.extractall(dst_path)
+                    else:
+                        # If destination is a file, we only extract the source file's content
+                        if len(members) > 1:
+                            raise RuntimeError(
+                                f"Source path is a directory but destination is a file: {src_path}"
+                            )
+
+                        with open(dst_path, "wb") as dst:
+                            src_file = tar.extractfile(members[0])
+                            if src_file is None:
+                                raise RuntimeError(
+                                    f"Failed to extract file: {src_path}"
+                                )
+                            dst.write(src_file.read())
+
+        except docker.errors.NotFound:
+            raise FileNotFoundError(f"Source file not found: {src_path}")
+        except Exception as e:
+            raise RuntimeError(f"Failed to copy file: {e}")
+
+    async def copy_to(self, src_path: str, dst_path: str) -> None:
+        """Copies a file to the container.
+
+        Args:
+            src_path: Source file path (host).
+            dst_path: Destination path (container).
+
+        Raises:
+            FileNotFoundError: If source file does not exist.
+            RuntimeError: If copy operation fails.
+        """
+        try:
+            if not os.path.exists(src_path):
+                raise FileNotFoundError(f"Source file not found: {src_path}")
+
+            # Create destination directory in container
+            resolved_dst = self._safe_resolve_path(dst_path)
+            container_dir = os.path.dirname(resolved_dst)
+            if container_dir:
+                await self.run_command(f"mkdir -p {container_dir}")
+
+            # Create tar file to upload
+            with tempfile.TemporaryDirectory() as tmp_dir:
+                tar_path = os.path.join(tmp_dir, "temp.tar")
+                with tarfile.open(tar_path, "w") as tar:
+                    # Handle directory source path
+                    if os.path.isdir(src_path):
+                        os.path.basename(src_path.rstrip("/"))
+                        for root, _, files in os.walk(src_path):
+                            for file in files:
+                                file_path = os.path.join(root, file)
+                                arcname = os.path.join(
+                                    os.path.basename(dst_path),
+                                    os.path.relpath(file_path, src_path),
+                                )
+                                tar.add(file_path, arcname=arcname)
+                    else:
+                        # Add single file to tar
+                        tar.add(src_path, arcname=os.path.basename(dst_path))
+
+                # Read tar file content
+                with open(tar_path, "rb") as f:
+                    data = f.read()
+
+                # Upload to container
+                await asyncio.to_thread(
+                    self.container.put_archive,
+                    os.path.dirname(resolved_dst) or "/",
+                    data,
+                )
+
+                # Verify file was created successfully
+                try:
+                    await self.run_command(f"test -e {resolved_dst}")
+                except Exception:
+                    raise RuntimeError(f"Failed to verify file creation: {dst_path}")
+
+        except FileNotFoundError:
+            raise
+        except Exception as e:
+            raise RuntimeError(f"Failed to copy file: {e}")
+
+    @staticmethod
+    async def _create_tar_stream(name: str, content: bytes) -> io.BytesIO:
+        """Creates a tar file stream.
+
+        Args:
+            name: Filename.
+            content: File content.
+
+        Returns:
+            Tar file stream.
+        """
+        tar_stream = io.BytesIO()
+        with tarfile.open(fileobj=tar_stream, mode="w") as tar:
+            tarinfo = tarfile.TarInfo(name=name)
+            tarinfo.size = len(content)
+            tar.addfile(tarinfo, io.BytesIO(content))
+        tar_stream.seek(0)
+        return tar_stream
+
+    @staticmethod
+    async def _read_from_tar(tar_stream) -> bytes:
+        """Reads file content from a tar stream.
+
+        Args:
+            tar_stream: Tar file stream.
+
+        Returns:
+            File content.
+
+        Raises:
+            RuntimeError: If read operation fails.
+        """
+        with tempfile.NamedTemporaryFile() as tmp:
+            for chunk in tar_stream:
+                tmp.write(chunk)
+            tmp.seek(0)
+
+            with tarfile.open(fileobj=tmp) as tar:
+                member = tar.next()
+                if not member:
+                    raise RuntimeError("Empty tar archive")
+
+                file_content = tar.extractfile(member)
+                if not file_content:
+                    raise RuntimeError("Failed to extract file content")
+
+                return file_content.read()
+
+    async def cleanup(self) -> None:
+        """Cleans up sandbox resources."""
+        errors = []
+        try:
+            if self.terminal:
+                try:
+                    await self.terminal.close()
+                except Exception as e:
+                    errors.append(f"Terminal cleanup error: {e}")
+                finally:
+                    self.terminal = None
+
+            if self.container:
+                try:
+                    await asyncio.to_thread(self.container.stop, timeout=5)
+                except Exception as e:
+                    errors.append(f"Container stop error: {e}")
+
+                try:
+                    await asyncio.to_thread(self.container.remove, force=True)
+                except Exception as e:
+                    errors.append(f"Container remove error: {e}")
+                finally:
+                    self.container = None
+
+        except Exception as e:
+            errors.append(f"General cleanup error: {e}")
+
+        if errors:
+            print(f"Warning: Errors during cleanup: {', '.join(errors)}")
+
+    async def __aenter__(self) -> "DockerSandbox":
+        """Async context manager entry."""
+        return await self.create()
+
+    async def __aexit__(self, exc_type, exc_val, exc_tb) -> None:
+        """Async context manager exit."""
+        await self.cleanup()

app/sandbox/core/terminal.py

@@ -0,0 +1,346 @@
+"""
+Asynchronous Docker Terminal
+
+This module provides asynchronous terminal functionality for Docker containers,
+allowing interactive command execution with timeout control.
+"""
+
+import asyncio
+import re
+import socket
+from typing import Dict, Optional, Tuple, Union
+
+import docker
+from docker import APIClient
+from docker.errors import APIError
+from docker.models.containers import Container
+
+
+class DockerSession:
+    def __init__(self, container_id: str) -> None:
+        """Initializes a Docker session.
+
+        Args:
+            container_id: ID of the Docker container.
+        """
+        self.api = APIClient()
+        self.container_id = container_id
+        self.exec_id = None
+        self.socket = None
+
+    async def create(self, working_dir: str, env_vars: Dict[str, str]) -> None:
+        """Creates an interactive session with the container.
+
+        Args:
+            working_dir: Working directory inside the container.
+            env_vars: Environment variables to set.
+
+        Raises:
+            RuntimeError: If socket connection fails.
+        """
+        startup_command = [
+            "bash",
+            "-c",
+            f"cd {working_dir} && "
+            "PROMPT_COMMAND='' "
+            "PS1='$ ' "
+            "exec bash --norc --noprofile",
+        ]
+
+        exec_data = self.api.exec_create(
+            self.container_id,
+            startup_command,
+            stdin=True,
+            tty=True,
+            stdout=True,
+            stderr=True,
+            privileged=True,
+            user="root",
+            environment={**env_vars, "TERM": "dumb", "PS1": "$ ", "PROMPT_COMMAND": ""},
+        )
+        self.exec_id = exec_data["Id"]
+
+        socket_data = self.api.exec_start(
+            self.exec_id, socket=True, tty=True, stream=True, demux=True
+        )
+
+        if hasattr(socket_data, "_sock"):
+            self.socket = socket_data._sock
+            self.socket.setblocking(False)
+        else:
+            raise RuntimeError("Failed to get socket connection")
+
+        await self._read_until_prompt()
+
+    async def close(self) -> None:
+        """Cleans up session resources.
+
+        1. Sends exit command
+        2. Closes socket connection
+        3. Checks and cleans up exec instance
+        """
+        try:
+            if self.socket:
+                # Send exit command to close bash session
+                try:
+                    self.socket.sendall(b"exit\n")
+                    # Allow time for command execution
+                    await asyncio.sleep(0.1)
+                except:
+                    pass  # Ignore sending errors, continue cleanup
+
+                # Close socket connection
+                try:
+                    self.socket.shutdown(socket.SHUT_RDWR)
+                except:
+                    pass  # Some platforms may not support shutdown
+
+                self.socket.close()
+                self.socket = None
+
+            if self.exec_id:
+                try:
+                    # Check exec instance status
+                    exec_inspect = self.api.exec_inspect(self.exec_id)
+                    if exec_inspect.get("Running", False):
+                        # If still running, wait for it to complete
+                        await asyncio.sleep(0.5)
+                except:
+                    pass  # Ignore inspection errors, continue cleanup
+
+                self.exec_id = None
+
+        except Exception as e:
+            # Log error but don't raise, ensure cleanup continues
+            print(f"Warning: Error during session cleanup: {e}")
+
+    async def _read_until_prompt(self) -> str:
+        """Reads output until prompt is found.
+
+        Returns:
+            String containing output up to the prompt.
+
+        Raises:
+            socket.error: If socket communication fails.
+        """
+        buffer = b""
+        while b"$ " not in buffer:
+            try:
+                chunk = self.socket.recv(4096)
+                if chunk:
+                    buffer += chunk
+            except socket.error as e:
+                if e.errno == socket.EWOULDBLOCK:
+                    await asyncio.sleep(0.1)
+                    continue
+                raise
+        return buffer.decode("utf-8")
+
+    async def execute(self, command: str, timeout: Optional[int] = None) -> str:
+        """Executes a command and returns cleaned output.
+
+        Args:
+            command: Shell command to execute.
+            timeout: Maximum execution time in seconds.
+
+        Returns:
+            Command output as string with prompt markers removed.
+
+        Raises:
+            RuntimeError: If session not initialized or execution fails.
+            TimeoutError: If command execution exceeds timeout.
+        """
+        if not self.socket:
+            raise RuntimeError("Session not initialized")
+
+        try:
+            # Sanitize command to prevent shell injection
+            sanitized_command = self._sanitize_command(command)
+            full_command = f"{sanitized_command}\necho $?\n"
+            self.socket.sendall(full_command.encode())
+
+            async def read_output() -> str:
+                buffer = b""
+                result_lines = []
+                command_sent = False
+
+                while True:
+                    try:
+                        chunk = self.socket.recv(4096)
+                        if not chunk:
+                            break
+
+                        buffer += chunk
+                        lines = buffer.split(b"\n")
+
+                        buffer = lines[-1]
+                        lines = lines[:-1]
+
+                        for line in lines:
+                            line = line.rstrip(b"\r")
+
+                            if not command_sent:
+                                command_sent = True
+                                continue
+
+                            if line.strip() == b"echo $?" or line.strip().isdigit():
+                                continue
+
+                            if line.strip():
+                                result_lines.append(line)
+
+                        if buffer.endswith(b"$ "):
+                            break
+
+                    except socket.error as e:
+                        if e.errno == socket.EWOULDBLOCK:
+                            await asyncio.sleep(0.1)
+                            continue
+                        raise
+
+                output = b"\n".join(result_lines).decode("utf-8")
+                output = re.sub(r"\n\$ echo \$\$?.*$", "", output)
+
+                return output
+
+            if timeout:
+                result = await asyncio.wait_for(read_output(), timeout)
+            else:
+                result = await read_output()
+
+            return result.strip()
+
+        except asyncio.TimeoutError:
+            raise TimeoutError(f"Command execution timed out after {timeout} seconds")
+        except Exception as e:
+            raise RuntimeError(f"Failed to execute command: {e}")
+
+    def _sanitize_command(self, command: str) -> str:
+        """Sanitizes the command string to prevent shell injection.
+
+        Args:
+            command: Raw command string.
+
+        Returns:
+            Sanitized command string.
+
+        Raises:
+            ValueError: If command contains potentially dangerous patterns.
+        """
+
+        # Additional checks for specific risky commands
+        risky_commands = [
+            "rm -rf /",
+            "rm -rf /*",
+            "mkfs",
+            "dd if=/dev/zero",
+            ":(){:|:&};:",
+            "chmod -R 777 /",
+            "chown -R",
+        ]
+
+        for risky in risky_commands:
+            if risky in command.lower():
+                raise ValueError(
+                    f"Command contains potentially dangerous operation: {risky}"
+                )
+
+        return command
+
+
+class AsyncDockerizedTerminal:
+    def __init__(
+        self,
+        container: Union[str, Container],
+        working_dir: str = "/workspace",
+        env_vars: Optional[Dict[str, str]] = None,
+        default_timeout: int = 60,
+    ) -> None:
+        """Initializes an asynchronous terminal for Docker containers.
+
+        Args:
+            container: Docker container ID or Container object.
+            working_dir: Working directory inside the container.
+            env_vars: Environment variables to set.
+            default_timeout: Default command execution timeout in seconds.
+        """
+        self.client = docker.from_env()
+        self.container = (
+            container
+            if isinstance(container, Container)
+            else self.client.containers.get(container)
+        )
+        self.working_dir = working_dir
+        self.env_vars = env_vars or {}
+        self.default_timeout = default_timeout
+        self.session = None
+
+    async def init(self) -> None:
+        """Initializes the terminal environment.
+
+        Ensures working directory exists and creates an interactive session.
+
+        Raises:
+            RuntimeError: If initialization fails.
+        """
+        await self._ensure_workdir()
+
+        self.session = DockerSession(self.container.id)
+        await self.session.create(self.working_dir, self.env_vars)
+
+    async def _ensure_workdir(self) -> None:
+        """Ensures working directory exists in container.
+
+        Raises:
+            RuntimeError: If directory creation fails.
+        """
+        try:
+            await self._exec_simple(f"mkdir -p {self.working_dir}")
+        except APIError as e:
+            raise RuntimeError(f"Failed to create working directory: {e}")
+
+    async def _exec_simple(self, cmd: str) -> Tuple[int, str]:
+        """Executes a simple command using Docker's exec_run.
+
+        Args:
+            cmd: Command to execute.
+
+        Returns:
+            Tuple of (exit_code, output).
+        """
+        result = await asyncio.to_thread(
+            self.container.exec_run, cmd, environment=self.env_vars
+        )
+        return result.exit_code, result.output.decode("utf-8")
+
+    async def run_command(self, cmd: str, timeout: Optional[int] = None) -> str:
+        """Runs a command in the container with timeout.
+
+        Args:
+            cmd: Shell command to execute.
+            timeout: Maximum execution time in seconds.
+
+        Returns:
+            Command output as string.
+
+        Raises:
+            RuntimeError: If terminal not initialized.
+        """
+        if not self.session:
+            raise RuntimeError("Terminal not initialized")
+
+        return await self.session.execute(cmd, timeout=timeout or self.default_timeout)
+
+    async def close(self) -> None:
+        """Closes the terminal session."""
+        if self.session:
+            await self.session.close()
+
+    async def __aenter__(self) -> "AsyncDockerizedTerminal":
+        """Async context manager entry."""
+        await self.init()
+        return self
+
+    async def __aexit__(self, exc_type, exc_val, exc_tb) -> None:
+        """Async context manager exit."""
+        await self.close()

app/tool/__init__.py

@@ -1,5 +1,6 @@
 from app.tool.base import BaseTool
 from app.tool.bash import Bash
+from app.tool.browser_use_tool import BrowserUseTool
 from app.tool.create_chat_completion import CreateChatCompletion
 from app.tool.planning import PlanningTool
 from app.tool.str_replace_editor import StrReplaceEditor
@@ -10,6 +11,7 @@ from app.tool.tool_collection import ToolCollection
 __all__ = [
     "BaseTool",
     "Bash",
+    "BrowserUseTool",
     "Terminate",
     "StrReplaceEditor",
     "ToolCollection",

app/tool/browser_use_tool.py

@@ -418,17 +418,7 @@ class BrowserUseTool(BaseTool, Generic[Context]):
 
                         # Create prompt for LLM
                         prompt_text = """
-Your task is to extract the content of the page. You will be given a page and a goal, and you should extract all relevant information around this goal from the page.
-
-Examples of extraction goals:
-- Extract all company names
-- Extract specific descriptions
-- Extract all information about a topic
-- Extract links with companies in structured format
-- Extract all links
-
-If the goal is vague, summarize the page. Respond in JSON format.
-
+Your task is to extract the content of the page. You will be given a page and a goal, and you should extract all relevant information around this goal from the page. If the goal is vague, summarize the page. Respond in json format.
 Extraction goal: {goal}
 
 Page content:
@@ -445,10 +435,54 @@ Page content:
 
                         messages = [Message.user_message(formatted_prompt)]
 
-                        # Use LLM to extract content based on the goal
-                        response = await self.llm.ask(messages)
+                        # Define extraction function for the tool
+                        extraction_function = {
+                            "type": "function",
+                            "function": {
+                                "name": "extract_content",
+                                "description": "Extract specific information from a webpage based on a goal",
+                                "parameters": {
+                                    "type": "object",
+                                    "properties": {
+                                        "extracted_content": {
+                                            "type": "object",
+                                            "description": "The content extracted from the page according to the goal",
+                                        }
+                                    },
+                                    "required": ["extracted_content"],
+                                },
+                            },
+                        }
+
+                        # Use LLM to extract content with required function calling
+                        response = await self.llm.ask_tool(
+                            messages,
+                            tools=[extraction_function],
+                            tool_choice="required",
+                        )
+
+                        # Extract content from function call response
+                        if (
+                            response
+                            and response.tool_calls
+                            and len(response.tool_calls) > 0
+                        ):
+                            # Get the first tool call arguments
+                            tool_call = response.tool_calls[0]
+                            # Parse the JSON arguments
+                            try:
+                                args = json.loads(tool_call.function.arguments)
+                                extracted_content = args.get("extracted_content", {})
+                                # Format extracted content as JSON string
+                                content_json = json.dumps(
+                                    extracted_content, indent=2, ensure_ascii=False
+                                )
+                                msg = f"Extracted from page:\n{content_json}\n"
+                            except Exception as e:
+                                msg = f"Error parsing extraction result: {str(e)}\nRaw response: {tool_call.function.arguments}"
+                        else:
+                            msg = "No content was extracted from the page."
 
-                        msg = f"Extracted from page:\n{response}\n"
                         return ToolResult(output=msg)
                     except Exception as e:
                         # Provide a more helpful error message

app/tool/file_operators.py

@@ -0,0 +1,156 @@
+"""File operation interfaces and implementations for local and sandbox environments."""
+
+import asyncio
+from pathlib import Path
+from typing import Optional, Protocol, Tuple, Union, runtime_checkable
+
+from app.config import SandboxSettings
+from app.exceptions import ToolError
+from app.sandbox.client import SANDBOX_CLIENT
+
+
+PathLike = Union[str, Path]
+
+
+@runtime_checkable
+class FileOperator(Protocol):
+    """Interface for file operations in different environments."""
+
+    async def read_file(self, path: PathLike) -> str:
+        """Read content from a file."""
+        ...
+
+    async def write_file(self, path: PathLike, content: str) -> None:
+        """Write content to a file."""
+        ...
+
+    async def is_directory(self, path: PathLike) -> bool:
+        """Check if path points to a directory."""
+        ...
+
+    async def exists(self, path: PathLike) -> bool:
+        """Check if path exists."""
+        ...
+
+    async def run_command(
+        self, cmd: str, timeout: Optional[float] = 120.0
+    ) -> Tuple[int, str, str]:
+        """Run a shell command and return (return_code, stdout, stderr)."""
+        ...
+
+
+class LocalFileOperator(FileOperator):
+    """File operations implementation for local filesystem."""
+
+    async def read_file(self, path: PathLike) -> str:
+        """Read content from a local file."""
+        try:
+            return Path(path).read_text()
+        except Exception as e:
+            raise ToolError(f"Failed to read {path}: {str(e)}") from None
+
+    async def write_file(self, path: PathLike, content: str) -> None:
+        """Write content to a local file."""
+        try:
+            Path(path).write_text(content)
+        except Exception as e:
+            raise ToolError(f"Failed to write to {path}: {str(e)}") from None
+
+    async def is_directory(self, path: PathLike) -> bool:
+        """Check if path points to a directory."""
+        return Path(path).is_dir()
+
+    async def exists(self, path: PathLike) -> bool:
+        """Check if path exists."""
+        return Path(path).exists()
+
+    async def run_command(
+        self, cmd: str, timeout: Optional[float] = 120.0
+    ) -> Tuple[int, str, str]:
+        """Run a shell command locally."""
+        process = await asyncio.create_subprocess_shell(
+            cmd, stdout=asyncio.subprocess.PIPE, stderr=asyncio.subprocess.PIPE
+        )
+
+        try:
+            stdout, stderr = await asyncio.wait_for(
+                process.communicate(), timeout=timeout
+            )
+            return (
+                process.returncode or 0,
+                stdout.decode(),
+                stderr.decode(),
+            )
+        except asyncio.TimeoutError as exc:
+            try:
+                process.kill()
+            except ProcessLookupError:
+                pass
+            raise TimeoutError(
+                f"Command '{cmd}' timed out after {timeout} seconds"
+            ) from exc
+
+
+class SandboxFileOperator(FileOperator):
+    """File operations implementation for sandbox environment."""
+
+    def __init__(self):
+        self.sandbox_client = SANDBOX_CLIENT
+
+    async def _ensure_sandbox_initialized(self):
+        """Ensure sandbox is initialized."""
+        if not self.sandbox_client.sandbox:
+            await self.sandbox_client.create(config=SandboxSettings())
+
+    async def read_file(self, path: PathLike) -> str:
+        """Read content from a file in sandbox."""
+        await self._ensure_sandbox_initialized()
+        try:
+            return await self.sandbox_client.read_file(str(path))
+        except Exception as e:
+            raise ToolError(f"Failed to read {path} in sandbox: {str(e)}") from None
+
+    async def write_file(self, path: PathLike, content: str) -> None:
+        """Write content to a file in sandbox."""
+        await self._ensure_sandbox_initialized()
+        try:
+            await self.sandbox_client.write_file(str(path), content)
+        except Exception as e:
+            raise ToolError(f"Failed to write to {path} in sandbox: {str(e)}") from None
+
+    async def is_directory(self, path: PathLike) -> bool:
+        """Check if path points to a directory in sandbox."""
+        await self._ensure_sandbox_initialized()
+        result = await self.sandbox_client.run_command(
+            f"test -d {path} && echo 'true' || echo 'false'"
+        )
+        return result.strip() == "true"
+
+    async def exists(self, path: PathLike) -> bool:
+        """Check if path exists in sandbox."""
+        await self._ensure_sandbox_initialized()
+        result = await self.sandbox_client.run_command(
+            f"test -e {path} && echo 'true' || echo 'false'"
+        )
+        return result.strip() == "true"
+
+    async def run_command(
+        self, cmd: str, timeout: Optional[float] = 120.0
+    ) -> Tuple[int, str, str]:
+        """Run a command in sandbox environment."""
+        await self._ensure_sandbox_initialized()
+        try:
+            stdout = await self.sandbox_client.run_command(
+                cmd, timeout=int(timeout) if timeout else None
+            )
+            return (
+                0,  # Always return 0 since we don't have explicit return code from sandbox
+                stdout,
+                "",  # No stderr capture in the current sandbox implementation
+            )
+        except TimeoutError as exc:
+            raise TimeoutError(
+                f"Command '{cmd}' timed out after {timeout} seconds in sandbox"
+            ) from exc
+        except Exception as exc:
+            return 1, "", f"Error executing command in sandbox: {str(exc)}"

app/tool/run.py

@@ -1,43 +0,0 @@
-"""Utility to run shell commands asynchronously with a timeout."""
-
-import asyncio
-
-
-TRUNCATED_MESSAGE: str = "<response clipped><NOTE>To save on context only part of this file has been shown to you. You should retry this tool after you have searched inside the file with `grep -n` in order to find the line numbers of what you are looking for.</NOTE>"
-MAX_RESPONSE_LEN: int = 16000
-
-
-def maybe_truncate(content: str, truncate_after: int | None = MAX_RESPONSE_LEN):
-    """Truncate content and append a notice if content exceeds the specified length."""
-    return (
-        content
-        if not truncate_after or len(content) <= truncate_after
-        else content[:truncate_after] + TRUNCATED_MESSAGE
-    )
-
-
-async def run(
-    cmd: str,
-    timeout: float | None = 120.0,  # seconds
-    truncate_after: int | None = MAX_RESPONSE_LEN,
-):
-    """Run a shell command asynchronously with a timeout."""
-    process = await asyncio.create_subprocess_shell(
-        cmd, stdout=asyncio.subprocess.PIPE, stderr=asyncio.subprocess.PIPE
-    )
-
-    try:
-        stdout, stderr = await asyncio.wait_for(process.communicate(), timeout=timeout)
-        return (
-            process.returncode or 0,
-            maybe_truncate(stdout.decode(), truncate_after=truncate_after),
-            maybe_truncate(stderr.decode(), truncate_after=truncate_after),
-        )
-    except asyncio.TimeoutError as exc:
-        try:
-            process.kill()
-        except ProcessLookupError:
-            pass
-        raise TimeoutError(
-            f"Command '{cmd}' timed out after {timeout} seconds"
-        ) from exc

app/tool/search/__init__.py

@@ -1,5 +1,6 @@
 from app.tool.search.baidu_search import BaiduSearchEngine
 from app.tool.search.base import WebSearchEngine
+from app.tool.search.bing_search import BingSearchEngine
 from app.tool.search.duckduckgo_search import DuckDuckGoSearchEngine
 from app.tool.search.google_search import GoogleSearchEngine
 
@@ -9,4 +10,5 @@ __all__ = [
     "BaiduSearchEngine",
     "DuckDuckGoSearchEngine",
     "GoogleSearchEngine",
+    "BingSearchEngine",
 ]

app/tool/search/bing_search.py

@@ -0,0 +1,146 @@
+from typing import List
+
+import requests
+from bs4 import BeautifulSoup
+
+from app.logger import logger
+from app.tool.search.base import WebSearchEngine
+
+
+ABSTRACT_MAX_LENGTH = 300
+
+USER_AGENTS = [
+    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36",
+    "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)",
+    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/49.0.2623.108 Chrome/49.0.2623.108 Safari/537.36",
+    "Mozilla/5.0 (Windows; U; Windows NT 5.1; pt-BR) AppleWebKit/533.3 (KHTML, like Gecko) QtWeb Internet Browser/3.7 http://www.QtWeb.net",
+    "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36",
+    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.2 (KHTML, like Gecko) ChromePlus/4.0.222.3 Chrome/4.0.222.3 Safari/532.2",
+    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.4pre) Gecko/20070404 K-Ninja/2.1.3",
+    "Mozilla/5.0 (Future Star Technologies Corp.; Star-Blade OS; x86_64; U; en-US) iNet Browser 4.7",
+    "Mozilla/5.0 (Windows; U; Windows NT 6.1; rv:2.2) Gecko/20110201",
+    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.13) Gecko/20080414 Firefox/2.0.0.13 Pogo/2.0.0.13.6866",
+]
+
+HEADERS = {
+    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
+    "Content-Type": "application/x-www-form-urlencoded",
+    "User-Agent": USER_AGENTS[0],
+    "Referer": "https://www.bing.com/",
+    "Accept-Encoding": "gzip, deflate",
+    "Accept-Language": "zh-CN,zh;q=0.9",
+}
+
+BING_HOST_URL = "https://www.bing.com"
+BING_SEARCH_URL = "https://www.bing.com/search?q="
+
+
+class BingSearchEngine(WebSearchEngine):
+    session: requests.Session = None
+
+    def __init__(self, **data):
+        """Initialize the BingSearch tool with a requests session."""
+        super().__init__(**data)
+        self.session = requests.Session()
+        self.session.headers.update(HEADERS)
+
+    def _search_sync(self, query: str, num_results: int = 10) -> List[str]:
+        """
+        Synchronous Bing search implementation to retrieve a list of URLs matching a query.
+
+        Args:
+            query (str): The search query to submit to Bing. Must not be empty.
+            num_results (int, optional): The maximum number of URLs to return. Defaults to 10.
+
+        Returns:
+            List[str]: A list of URLs from the search results, capped at `num_results`.
+                       Returns an empty list if the query is empty or no results are found.
+
+        Notes:
+            - Pagination is handled by incrementing the `first` parameter and following `next_url` links.
+            - If fewer results than `num_results` are available, all found URLs are returned.
+        """
+        if not query:
+            return []
+
+        list_result = []
+        first = 1
+        next_url = BING_SEARCH_URL + query
+
+        while len(list_result) < num_results:
+            data, next_url = self._parse_html(
+                next_url, rank_start=len(list_result), first=first
+            )
+            if data:
+                list_result.extend([item["url"] for item in data])
+            if not next_url:
+                break
+            first += 10
+
+        return list_result[:num_results]
+
+    def _parse_html(self, url: str, rank_start: int = 0, first: int = 1) -> tuple:
+        """
+        Parse Bing search result HTML synchronously to extract search results and the next page URL.
+
+        Args:
+            url (str): The URL of the Bing search results page to parse.
+            rank_start (int, optional): The starting rank for numbering the search results. Defaults to 0.
+            first (int, optional): Unused parameter (possibly legacy). Defaults to 1.
+        Returns:
+            tuple: A tuple containing:
+                - list: A list of dictionaries with keys 'title', 'abstract', 'url', and 'rank' for each result.
+                - str or None: The URL of the next results page, or None if there is no next page.
+        """
+        try:
+            res = self.session.get(url=url)
+            res.encoding = "utf-8"
+            root = BeautifulSoup(res.text, "lxml")
+
+            list_data = []
+            ol_results = root.find("ol", id="b_results")
+            if not ol_results:
+                return [], None
+
+            for li in ol_results.find_all("li", class_="b_algo"):
+                title = ""
+                url = ""
+                abstract = ""
+                try:
+                    h2 = li.find("h2")
+                    if h2:
+                        title = h2.text.strip()
+                        url = h2.a["href"].strip()
+
+                    p = li.find("p")
+                    if p:
+                        abstract = p.text.strip()
+
+                    if ABSTRACT_MAX_LENGTH and len(abstract) > ABSTRACT_MAX_LENGTH:
+                        abstract = abstract[:ABSTRACT_MAX_LENGTH]
+
+                    rank_start += 1
+                    list_data.append(
+                        {
+                            "title": title,
+                            "abstract": abstract,
+                            "url": url,
+                            "rank": rank_start,
+                        }
+                    )
+                except Exception:
+                    continue
+
+            next_btn = root.find("a", title="Next page")
+            if not next_btn:
+                return list_data, None
+
+            next_url = BING_HOST_URL + next_btn["href"]
+            return list_data, next_url
+        except Exception as e:
+            logger.warning(f"Error parsing HTML: {e}")
+            return [], None
+
+    def perform_search(self, query, num_results=10, *args, **kwargs):
+        """Bing search engine."""
+        return self._search_sync(query, num_results=num_results)

app/tool/str_replace_editor.py

@@ -1,11 +1,19 @@
+"""File and directory manipulation tool with sandbox support."""
+
 from collections import defaultdict
 from pathlib import Path
-from typing import Literal, get_args
+from typing import Any, DefaultDict, List, Literal, Optional, get_args
 
+from app.config import config
 from app.exceptions import ToolError
 from app.tool import BaseTool
 from app.tool.base import CLIResult, ToolResult
-from app.tool.run import run
+from app.tool.file_operators import (
+    FileOperator,
+    LocalFileOperator,
+    PathLike,
+    SandboxFileOperator,
+)
 
 
 Command = Literal[
@@ -15,12 +23,17 @@ Command = Literal[
     "insert",
     "undo_edit",
 ]
+
+# Constants
 SNIPPET_LINES: int = 4
-
 MAX_RESPONSE_LEN: int = 16000
+TRUNCATED_MESSAGE: str = (
+    "<response clipped><NOTE>To save on context only part of this file has been shown to you. "
+    "You should retry this tool after you have searched inside the file with `grep -n` "
+    "in order to find the line numbers of what you are looking for.</NOTE>"
+)
 
-TRUNCATED_MESSAGE: str = "<response clipped><NOTE>To save on context only part of this file has been shown to you. You should retry this tool after you have searched inside the file with `grep -n` in order to find the line numbers of what you are looking for.</NOTE>"
-
+# Tool description
 _STR_REPLACE_EDITOR_DESCRIPTION = """Custom editing tool for viewing, creating and editing files
 * State is persistent across command calls and discussions with the user
 * If `path` is a file, `view` displays the result of applying `cat -n`. If `path` is a directory, `view` lists non-hidden files and directories up to 2 levels deep
@@ -35,17 +48,17 @@ Notes for using the `str_replace` command:
 """
 
 
-def maybe_truncate(content: str, truncate_after: int | None = MAX_RESPONSE_LEN):
+def maybe_truncate(
+    content: str, truncate_after: Optional[int] = MAX_RESPONSE_LEN
+) -> str:
     """Truncate content and append a notice if content exceeds the specified length."""
-    return (
-        content
-        if not truncate_after or len(content) <= truncate_after
-        else content[:truncate_after] + TRUNCATED_MESSAGE
-    )
+    if not truncate_after or len(content) <= truncate_after:
+        return content
+    return content[:truncate_after] + TRUNCATED_MESSAGE
 
 
 class StrReplaceEditor(BaseTool):
-    """A tool for executing bash commands"""
+    """A tool for viewing, creating, and editing files with sandbox support."""
 
     name: str = "str_replace_editor"
     description: str = _STR_REPLACE_EDITOR_DESCRIPTION
@@ -85,8 +98,18 @@ class StrReplaceEditor(BaseTool):
         },
         "required": ["command", "path"],
     }
+    _file_history: DefaultDict[PathLike, List[str]] = defaultdict(list)
+    _local_operator: LocalFileOperator = LocalFileOperator()
+    _sandbox_operator: SandboxFileOperator = SandboxFileOperator()
 
-    _file_history: list = defaultdict(list)
+    # def _get_operator(self, use_sandbox: bool) -> FileOperator:
+    def _get_operator(self) -> FileOperator:
+        """Get the appropriate file operator based on execution mode."""
+        return (
+            self._sandbox_operator
+            if config.sandbox.use_sandbox
+            else self._local_operator
+        )
 
     async def execute(
         self,
@@ -98,24 +121,30 @@ class StrReplaceEditor(BaseTool):
         old_str: str | None = None,
         new_str: str | None = None,
         insert_line: int | None = None,
-        **kwargs,
+        **kwargs: Any,
     ) -> str:
-        _path = Path(path)
-        self.validate_path(command, _path)
+        """Execute a file operation command."""
+        # Get the appropriate file operator
+        operator = self._get_operator()
+
+        # Validate path and command combination
+        await self.validate_path(command, Path(path), operator)
+
+        # Execute the appropriate command
         if command == "view":
-            result = await self.view(_path, view_range)
+            result = await self.view(path, view_range, operator)
         elif command == "create":
             if file_text is None:
                 raise ToolError("Parameter `file_text` is required for command: create")
-            self.write_file(_path, file_text)
-            self._file_history[_path].append(file_text)
-            result = ToolResult(output=f"File created successfully at: {_path}")
+            await operator.write_file(path, file_text)
+            self._file_history[path].append(file_text)
+            result = ToolResult(output=f"File created successfully at: {path}")
         elif command == "str_replace":
             if old_str is None:
                 raise ToolError(
                     "Parameter `old_str` is required for command: str_replace"
                 )
-            result = self.str_replace(_path, old_str, new_str)
+            result = await self.str_replace(path, old_str, new_str, operator)
         elif command == "insert":
             if insert_line is None:
                 raise ToolError(
@@ -123,89 +152,145 @@ class StrReplaceEditor(BaseTool):
                 )
             if new_str is None:
                 raise ToolError("Parameter `new_str` is required for command: insert")
-            result = self.insert(_path, insert_line, new_str)
+            result = await self.insert(path, insert_line, new_str, operator)
         elif command == "undo_edit":
-            result = self.undo_edit(_path)
+            result = await self.undo_edit(path, operator)
         else:
+            # This should be caught by type checking, but we include it for safety
             raise ToolError(
                 f'Unrecognized command {command}. The allowed commands for the {self.name} tool are: {", ".join(get_args(Command))}'
             )
+
         return str(result)
 
-    def validate_path(self, command: str, path: Path):
-        """
-        Check that the path/command combination is valid.
-        """
-        # Check if its an absolute path
+    async def validate_path(
+        self, command: str, path: Path, operator: FileOperator
+    ) -> None:
+        """Validate path and command combination based on execution environment."""
+        # Check if path is absolute
         if not path.is_absolute():
             raise ToolError(f"The path {path} is not an absolute path")
-        # Check if path exists
-        if not path.exists() and command != "create":
+
+        # Only check if path exists for non-create commands
+        if command != "create":
+            if not await operator.exists(path):
                 raise ToolError(
                     f"The path {path} does not exist. Please provide a valid path."
                 )
-        if path.exists() and command == "create":
-            raise ToolError(
-                f"File already exists at: {path}. Cannot overwrite files using command `create`."
-            )
-        # Check if the path points to a directory
-        if path.is_dir():
-            if command != "view":
+
+            # Check if path is a directory
+            is_dir = await operator.is_directory(path)
+            if is_dir and command != "view":
                 raise ToolError(
                     f"The path {path} is a directory and only the `view` command can be used on directories"
                 )
 
-    async def view(self, path: Path, view_range: list[int] | None = None):
-        """Implement the view command"""
-        if path.is_dir():
+        # Check if file exists for create command
+        elif command == "create":
+            exists = await operator.exists(path)
+            if exists:
+                raise ToolError(
+                    f"File already exists at: {path}. Cannot overwrite files using command `create`."
+                )
+
+    async def view(
+        self,
+        path: PathLike,
+        view_range: Optional[List[int]] = None,
+        operator: FileOperator = None,
+    ) -> CLIResult:
+        """Display file or directory content."""
+        # Determine if path is a directory
+        is_dir = await operator.is_directory(path)
+
+        if is_dir:
+            # Directory handling
             if view_range:
                 raise ToolError(
                     "The `view_range` parameter is not allowed when `path` points to a directory."
                 )
 
-            _, stdout, stderr = await run(
-                rf"find {path} -maxdepth 2 -not -path '*/\.*'"
-            )
+            return await self._view_directory(path, operator)
+        else:
+            # File handling
+            return await self._view_file(path, operator, view_range)
+
+    @staticmethod
+    async def _view_directory(path: PathLike, operator: FileOperator) -> CLIResult:
+        """Display directory contents."""
+        find_cmd = f"find {path} -maxdepth 2 -not -path '*/\\.*'"
+
+        # Execute command using the operator
+        returncode, stdout, stderr = await operator.run_command(find_cmd)
+
         if not stderr:
-                stdout = f"Here's the files and directories up to 2 levels deep in {path}, excluding hidden items:\n{stdout}\n"
+            stdout = (
+                f"Here's the files and directories up to 2 levels deep in {path}, "
+                f"excluding hidden items:\n{stdout}\n"
+            )
+
         return CLIResult(output=stdout, error=stderr)
 
-        file_content = self.read_file(path)
+    async def _view_file(
+        self,
+        path: PathLike,
+        operator: FileOperator,
+        view_range: Optional[List[int]] = None,
+    ) -> CLIResult:
+        """Display file content, optionally within a specified line range."""
+        # Read file content
+        file_content = await operator.read_file(path)
         init_line = 1
+
+        # Apply view range if specified
         if view_range:
             if len(view_range) != 2 or not all(isinstance(i, int) for i in view_range):
                 raise ToolError(
                     "Invalid `view_range`. It should be a list of two integers."
                 )
+
             file_lines = file_content.split("\n")
             n_lines_file = len(file_lines)
             init_line, final_line = view_range
+
+            # Validate view range
             if init_line < 1 or init_line > n_lines_file:
                 raise ToolError(
-                    f"Invalid `view_range`: {view_range}. Its first element `{init_line}` should be within the range of lines of the file: {[1, n_lines_file]}"
+                    f"Invalid `view_range`: {view_range}. Its first element `{init_line}` should be "
+                    f"within the range of lines of the file: {[1, n_lines_file]}"
                 )
             if final_line > n_lines_file:
                 raise ToolError(
-                    f"Invalid `view_range`: {view_range}. Its second element `{final_line}` should be smaller than the number of lines in the file: `{n_lines_file}`"
+                    f"Invalid `view_range`: {view_range}. Its second element `{final_line}` should be "
+                    f"smaller than the number of lines in the file: `{n_lines_file}`"
                 )
             if final_line != -1 and final_line < init_line:
                 raise ToolError(
-                    f"Invalid `view_range`: {view_range}. Its second element `{final_line}` should be larger or equal than its first `{init_line}`"
+                    f"Invalid `view_range`: {view_range}. Its second element `{final_line}` should be "
+                    f"larger or equal than its first `{init_line}`"
                 )
 
+            # Apply range
             if final_line == -1:
                 file_content = "\n".join(file_lines[init_line - 1 :])
             else:
                 file_content = "\n".join(file_lines[init_line - 1 : final_line])
 
+        # Format and return result
         return CLIResult(
             output=self._make_output(file_content, str(path), init_line=init_line)
         )
 
-    def str_replace(self, path: Path, old_str: str, new_str: str | None):
-        """Implement the str_replace command, which replaces old_str with new_str in the file content"""
-        # Read the file content
-        file_content = self.read_file(path).expandtabs()
+    async def str_replace(
+        self,
+        path: PathLike,
+        old_str: str,
+        new_str: Optional[str] = None,
+        operator: FileOperator = None,
+    ) -> CLIResult:
+        """Replace a unique string in a file with a new string."""
+        # Read file content and expand tabs
+        file_content = (await operator.read_file(path)).expandtabs()
         old_str = old_str.expandtabs()
         new_str = new_str.expandtabs() if new_str is not None else ""
 
@@ -216,6 +301,7 @@ class StrReplaceEditor(BaseTool):
                 f"No replacement was performed, old_str `{old_str}` did not appear verbatim in {path}."
             )
         elif occurrences > 1:
+            # Find line numbers of occurrences
             file_content_lines = file_content.split("\n")
             lines = [
                 idx + 1
@@ -223,16 +309,17 @@ class StrReplaceEditor(BaseTool):
                 if old_str in line
             ]
             raise ToolError(
-                f"No replacement was performed. Multiple occurrences of old_str `{old_str}` in lines {lines}. Please ensure it is unique"
+                f"No replacement was performed. Multiple occurrences of old_str `{old_str}` "
+                f"in lines {lines}. Please ensure it is unique"
             )
 
         # Replace old_str with new_str
         new_file_content = file_content.replace(old_str, new_str)
 
         # Write the new content to the file
-        self.write_file(path, new_file_content)
+        await operator.write_file(path, new_file_content)
 
-        # Save the content to history
+        # Save the original content to history
         self._file_history[path].append(file_content)
 
         # Create a snippet of the edited section
@@ -250,36 +337,50 @@ class StrReplaceEditor(BaseTool):
 
         return CLIResult(output=success_msg)
 
-    def insert(self, path: Path, insert_line: int, new_str: str):
-        """Implement the insert command, which inserts new_str at the specified line in the file content."""
-        file_text = self.read_file(path).expandtabs()
+    async def insert(
+        self,
+        path: PathLike,
+        insert_line: int,
+        new_str: str,
+        operator: FileOperator = None,
+    ) -> CLIResult:
+        """Insert text at a specific line in a file."""
+        # Read and prepare content
+        file_text = (await operator.read_file(path)).expandtabs()
         new_str = new_str.expandtabs()
         file_text_lines = file_text.split("\n")
         n_lines_file = len(file_text_lines)
 
+        # Validate insert_line
         if insert_line < 0 or insert_line > n_lines_file:
             raise ToolError(
-                f"Invalid `insert_line` parameter: {insert_line}. It should be within the range of lines of the file: {[0, n_lines_file]}"
+                f"Invalid `insert_line` parameter: {insert_line}. It should be within "
+                f"the range of lines of the file: {[0, n_lines_file]}"
             )
 
+        # Perform insertion
         new_str_lines = new_str.split("\n")
         new_file_text_lines = (
             file_text_lines[:insert_line]
             + new_str_lines
             + file_text_lines[insert_line:]
         )
+
+        # Create a snippet for preview
         snippet_lines = (
             file_text_lines[max(0, insert_line - SNIPPET_LINES) : insert_line]
             + new_str_lines
             + file_text_lines[insert_line : insert_line + SNIPPET_LINES]
         )
 
+        # Join lines and write to file
         new_file_text = "\n".join(new_file_text_lines)
         snippet = "\n".join(snippet_lines)
 
-        self.write_file(path, new_file_text)
+        await operator.write_file(path, new_file_text)
         self._file_history[path].append(file_text)
 
+        # Prepare success message
         success_msg = f"The file {path} has been edited. "
         success_msg += self._make_output(
             snippet,
@@ -287,51 +388,43 @@ class StrReplaceEditor(BaseTool):
             max(1, insert_line - SNIPPET_LINES + 1),
         )
         success_msg += "Review the changes and make sure they are as expected (correct indentation, no duplicate lines, etc). Edit the file again if necessary."
+
         return CLIResult(output=success_msg)
 
-    def undo_edit(self, path: Path):
-        """Implement the undo_edit command."""
+    async def undo_edit(
+        self, path: PathLike, operator: FileOperator = None
+    ) -> CLIResult:
+        """Revert the last edit made to a file."""
         if not self._file_history[path]:
             raise ToolError(f"No edit history found for {path}.")
 
         old_text = self._file_history[path].pop()
-        self.write_file(path, old_text)
+        await operator.write_file(path, old_text)
 
         return CLIResult(
             output=f"Last edit to {path} undone successfully. {self._make_output(old_text, str(path))}"
         )
 
-    def read_file(self, path: Path):
-        """Read the content of a file from a given path; raise a ToolError if an error occurs."""
-        try:
-            return path.read_text()
-        except Exception as e:
-            raise ToolError(f"Ran into {e} while trying to read {path}") from None
-
-    def write_file(self, path: Path, file: str):
-        """Write the content of a file to a given path; raise a ToolError if an error occurs."""
-        try:
-            path.write_text(file)
-        except Exception as e:
-            raise ToolError(f"Ran into {e} while trying to write to {path}") from None
-
     def _make_output(
         self,
         file_content: str,
         file_descriptor: str,
         init_line: int = 1,
         expand_tabs: bool = True,
-    ):
-        """Generate output for the CLI based on the content of a file."""
+    ) -> str:
+        """Format file content for display with line numbers."""
         file_content = maybe_truncate(file_content)
         if expand_tabs:
             file_content = file_content.expandtabs()
+
+        # Add line numbers to each line
         file_content = "\n".join(
             [
                 f"{i + init_line:6}\t{line}"
                 for i, line in enumerate(file_content.split("\n"))
             ]
         )
+
         return (
             f"Here's the result of running `cat -n` on {file_descriptor}:\n"
             + file_content

app/tool/web_search.py

@@ -7,6 +7,7 @@ from app.config import config
 from app.tool.base import BaseTool
 from app.tool.search import (
     BaiduSearchEngine,
+    BingSearchEngine,
     DuckDuckGoSearchEngine,
     GoogleSearchEngine,
     WebSearchEngine,
@@ -37,6 +38,7 @@ class WebSearch(BaseTool):
         "google": GoogleSearchEngine(),
         "baidu": BaiduSearchEngine(),
         "duckduckgo": DuckDuckGoSearchEngine(),
+        "bing": BingSearchEngine(),
     }
 
     async def execute(self, query: str, num_results: int = 10) -> List[str]:

config/config.example.toml

@@ -65,3 +65,13 @@ temperature = 0.0                           # Controls randomness for vision mod
 # [search]
 # Search engine for agent to use. Default is "Google", can be set to "Baidu" or "DuckDuckGo".
 #engine = "Google"
+
+## Sandbox configuration
+#[sandbox]
+#use_sandbox = false
+#image = "python:3.12-slim"
+#work_dir = "/workspace"
+#memory_limit = "1g"  # 512m
+#cpu_limit = 2.0
+#timeout = 300
+#network_enabled = true

requirements.txt

@@ -23,3 +23,7 @@ aiofiles~=24.1.0
 pydantic_core~=2.27.2
 colorama~=0.4.6
 playwright~=1.50.0
+
+docker~=7.1.0
+pytest~=8.3.5
+pytest-asyncio~=0.25.3

tests/sandbox/test_client.py

@@ -0,0 +1,110 @@
+import tempfile
+from pathlib import Path
+from typing import AsyncGenerator
+
+import pytest
+import pytest_asyncio
+
+from app.config import SandboxSettings
+from app.sandbox.client import LocalSandboxClient, create_sandbox_client
+
+
+@pytest_asyncio.fixture(scope="function")
+async def local_client() -> AsyncGenerator[LocalSandboxClient, None]:
+    """Creates a local sandbox client for testing."""
+    client = create_sandbox_client()
+    try:
+        yield client
+    finally:
+        await client.cleanup()
+
+
+@pytest.fixture(scope="function")
+def temp_dir() -> Path:
+    """Creates a temporary directory for testing."""
+    with tempfile.TemporaryDirectory() as tmp_dir:
+        yield Path(tmp_dir)
+
+
+@pytest.mark.asyncio
+async def test_sandbox_creation(local_client: LocalSandboxClient):
+    """Tests sandbox creation with specific configuration."""
+    config = SandboxSettings(
+        image="python:3.12-slim",
+        work_dir="/workspace",
+        memory_limit="512m",
+        cpu_limit=0.5,
+    )
+
+    await local_client.create(config)
+    result = await local_client.run_command("python3 --version")
+    assert "Python 3.10" in result
+
+
+@pytest.mark.asyncio
+async def test_local_command_execution(local_client: LocalSandboxClient):
+    """Tests command execution in local sandbox."""
+    await local_client.create()
+
+    result = await local_client.run_command("echo 'test'")
+    assert result.strip() == "test"
+
+    with pytest.raises(Exception):
+        await local_client.run_command("sleep 10", timeout=1)
+
+
+@pytest.mark.asyncio
+async def test_local_file_operations(local_client: LocalSandboxClient, temp_dir: Path):
+    """Tests file operations in local sandbox."""
+    await local_client.create()
+
+    # Test write and read operations
+    test_content = "Hello, World!"
+    await local_client.write_file("/workspace/test.txt", test_content)
+    content = await local_client.read_file("/workspace/test.txt")
+    assert content.strip() == test_content
+
+    # Test copying file to container
+    src_file = temp_dir / "src.txt"
+    src_file.write_text("Copy to container")
+    await local_client.copy_to(str(src_file), "/workspace/copied.txt")
+    content = await local_client.read_file("/workspace/copied.txt")
+    assert content.strip() == "Copy to container"
+
+    # Test copying file from container
+    dst_file = temp_dir / "dst.txt"
+    await local_client.copy_from("/workspace/test.txt", str(dst_file))
+    assert dst_file.read_text().strip() == test_content
+
+
+@pytest.mark.asyncio
+async def test_local_volume_binding(local_client: LocalSandboxClient, temp_dir: Path):
+    """Tests volume binding in local sandbox."""
+    bind_path = str(temp_dir)
+    volume_bindings = {bind_path: "/data"}
+
+    await local_client.create(volume_bindings=volume_bindings)
+
+    test_file = temp_dir / "test.txt"
+    test_file.write_text("Volume test")
+
+    content = await local_client.read_file("/data/test.txt")
+    assert "Volume test" in content
+
+
+@pytest.mark.asyncio
+async def test_local_error_handling(local_client: LocalSandboxClient):
+    """Tests error handling in local sandbox."""
+    await local_client.create()
+
+    with pytest.raises(Exception) as exc:
+        await local_client.read_file("/nonexistent.txt")
+    assert "not found" in str(exc.value).lower()
+
+    with pytest.raises(Exception) as exc:
+        await local_client.copy_from("/nonexistent.txt", "local.txt")
+    assert "not found" in str(exc.value).lower()
+
+
+if __name__ == "__main__":
+    pytest.main(["-v", __file__])

tests/sandbox/test_docker_terminal.py

@@ -0,0 +1,104 @@
+"""Tests for the AsyncDockerizedTerminal implementation."""
+
+import docker
+import pytest
+import pytest_asyncio
+
+from app.sandbox.core.terminal import AsyncDockerizedTerminal
+
+
+@pytest.fixture(scope="module")
+def docker_client():
+    """Fixture providing a Docker client."""
+    return docker.from_env()
+
+
+@pytest_asyncio.fixture(scope="module")
+async def docker_container(docker_client):
+    """Fixture providing a test Docker container."""
+    container = docker_client.containers.run(
+        "python:3.12-slim",
+        "tail -f /dev/null",
+        name="test_container",
+        detach=True,
+        remove=True,
+    )
+    yield container
+    container.stop()
+
+
+@pytest_asyncio.fixture
+async def terminal(docker_container):
+    """Fixture providing an initialized AsyncDockerizedTerminal instance."""
+    terminal = AsyncDockerizedTerminal(
+        docker_container,
+        working_dir="/workspace",
+        env_vars={"TEST_VAR": "test_value"},
+        default_timeout=30,
+    )
+    await terminal.init()
+    yield terminal
+    await terminal.close()
+
+
+class TestAsyncDockerizedTerminal:
+    """Test cases for AsyncDockerizedTerminal."""
+
+    @pytest.mark.asyncio
+    async def test_basic_command_execution(self, terminal):
+        """Test basic command execution functionality."""
+        result = await terminal.run_command("echo 'Hello World'")
+        assert "Hello World" in result
+
+    @pytest.mark.asyncio
+    async def test_environment_variables(self, terminal):
+        """Test environment variable setting and access."""
+        result = await terminal.run_command("echo $TEST_VAR")
+        assert "test_value" in result
+
+    @pytest.mark.asyncio
+    async def test_working_directory(self, terminal):
+        """Test working directory setup."""
+        result = await terminal.run_command("pwd")
+        assert "/workspace" == result
+
+    @pytest.mark.asyncio
+    async def test_command_timeout(self, docker_container):
+        """Test command timeout functionality."""
+        terminal = AsyncDockerizedTerminal(docker_container, default_timeout=1)
+        await terminal.init()
+        try:
+            with pytest.raises(TimeoutError):
+                await terminal.run_command("sleep 5")
+        finally:
+            await terminal.close()
+
+    @pytest.mark.asyncio
+    async def test_multiple_commands(self, terminal):
+        """Test execution of multiple commands in sequence."""
+        cmd1 = await terminal.run_command("echo 'First'")
+        cmd2 = await terminal.run_command("echo 'Second'")
+        assert "First" in cmd1
+        assert "Second" in cmd2
+
+    @pytest.mark.asyncio
+    async def test_session_cleanup(self, docker_container):
+        """Test proper cleanup of resources."""
+        terminal = AsyncDockerizedTerminal(docker_container)
+        await terminal.init()
+        assert terminal.session is not None
+        await terminal.close()
+        # Verify session is properly cleaned up
+        # Note: session object still exists, but internal connection is closed
+        assert terminal.session is not None
+
+
+# Configure pytest-asyncio
+def pytest_configure(config):
+    """Configure pytest-asyncio."""
+    config.addinivalue_line("asyncio_mode", "strict")
+    config.addinivalue_line("asyncio_default_fixture_loop_scope", "function")
+
+
+if __name__ == "__main__":
+    pytest.main(["-v", __file__])

tests/sandbox/test_sandbox.py

@@ -0,0 +1,152 @@
+import pytest
+import pytest_asyncio
+
+from app.sandbox.core.sandbox import DockerSandbox, SandboxSettings
+
+
+@pytest.fixture(scope="module")
+def sandbox_config():
+    """Creates sandbox configuration for testing."""
+    return SandboxSettings(
+        image="python:3.12-slim",
+        work_dir="/workspace",
+        memory_limit="1g",
+        cpu_limit=0.5,
+        network_enabled=True,
+    )
+
+
+@pytest_asyncio.fixture(scope="module")
+async def sandbox(sandbox_config):
+    """Creates and manages a test sandbox instance."""
+    sandbox = DockerSandbox(sandbox_config)
+    await sandbox.create()
+    try:
+        yield sandbox
+    finally:
+        await sandbox.cleanup()
+
+
+@pytest.mark.asyncio
+async def test_sandbox_working_directory(sandbox):
+    """Tests sandbox working directory configuration."""
+    result = await sandbox.terminal.run_command("pwd")
+    assert result.strip() == "/workspace"
+
+
+@pytest.mark.asyncio
+async def test_sandbox_file_operations(sandbox):
+    """Tests sandbox file read/write operations."""
+    # Test file writing
+    test_content = "Hello from sandbox!"
+    await sandbox.write_file("/workspace/test.txt", test_content)
+
+    # Test file reading
+    content = await sandbox.read_file("/workspace/test.txt")
+    assert content.strip() == test_content
+
+
+@pytest.mark.asyncio
+async def test_sandbox_python_execution(sandbox):
+    """Tests Python code execution in sandbox."""
+    # Write test file
+    await sandbox.write_file("/workspace/test.txt", "Hello from file!")
+
+    # Write Python script
+    python_code = """
+print("Hello from Python!")
+with open('/workspace/test.txt') as f:
+    print(f.read())
+"""
+    await sandbox.write_file("/workspace/test.py", python_code)
+
+    # Execute script and verify output
+    result = await sandbox.terminal.run_command("python3 /workspace/test.py")
+    assert "Hello from Python!" in result
+    assert "Hello from file!" in result
+
+
+@pytest.mark.asyncio
+async def test_sandbox_file_persistence(sandbox):
+    """Tests file persistence in sandbox."""
+    # Create multiple files
+    files = {
+        "file1.txt": "Content 1",
+        "file2.txt": "Content 2",
+        "nested/file3.txt": "Content 3",
+    }
+
+    # Write files
+    for path, content in files.items():
+        await sandbox.write_file(f"/workspace/{path}", content)
+
+    # Verify file contents
+    for path, expected_content in files.items():
+        content = await sandbox.read_file(f"/workspace/{path}")
+        assert content.strip() == expected_content
+
+
+@pytest.mark.asyncio
+async def test_sandbox_python_environment(sandbox):
+    """Tests Python environment configuration."""
+    # Test Python version
+    result = await sandbox.terminal.run_command("python3 --version")
+    assert "Python 3.10" in result
+
+    # Test basic module imports
+    python_code = """
+import sys
+import os
+import json
+print("Python is working!")
+"""
+    await sandbox.write_file("/workspace/env_test.py", python_code)
+    result = await sandbox.terminal.run_command("python3 /workspace/env_test.py")
+    assert "Python is working!" in result
+
+
+@pytest.mark.asyncio
+async def test_sandbox_network_access(sandbox):
+    """Tests sandbox network access."""
+    if not sandbox.config.network_enabled:
+        pytest.skip("Network access is disabled")
+
+    # Test network connectivity
+    await sandbox.terminal.run_command("apt update && apt install curl -y")
+    result = await sandbox.terminal.run_command("curl -I https://www.example.com")
+    assert "HTTP/2 200" in result
+
+
+@pytest.mark.asyncio
+async def test_sandbox_cleanup(sandbox_config):
+    """Tests sandbox cleanup process."""
+    sandbox = DockerSandbox(sandbox_config)
+    await sandbox.create()
+
+    # Create test files
+    await sandbox.write_file("/workspace/test.txt", "test")
+    container_id = sandbox.terminal.container.id
+    # Perform cleanup
+    await sandbox.cleanup()
+
+    # Verify container has been removed
+    import docker
+
+    client = docker.from_env()
+    containers = client.containers.list(all=True)
+    assert not any(c.id == container_id for c in containers)
+
+
+@pytest.mark.asyncio
+async def test_sandbox_error_handling():
+    """Tests error handling with invalid configuration."""
+    # Test invalid configuration
+    invalid_config = SandboxSettings(image="nonexistent:latest", work_dir="/invalid")
+
+    sandbox = DockerSandbox(invalid_config)
+    with pytest.raises(Exception):
+        await sandbox.create()
+
+
+if __name__ == "__main__":
+    pytest.main(["-v", __file__])

tests/sandbox/test_sandbox_manager.py

@@ -0,0 +1,138 @@
+import asyncio
+import os
+import tempfile
+from typing import AsyncGenerator
+
+import pytest
+import pytest_asyncio
+
+from app.sandbox.core.manager import SandboxManager
+
+
+@pytest_asyncio.fixture(scope="function")
+async def manager() -> AsyncGenerator[SandboxManager, None]:
+    """Creates a sandbox manager instance.
+
+    Uses function scope to ensure each test case has its own manager instance.
+    """
+    manager = SandboxManager(max_sandboxes=2, idle_timeout=60, cleanup_interval=30)
+    try:
+        yield manager
+    finally:
+        # Ensure all resources are cleaned up
+        await manager.cleanup()
+
+
+@pytest.fixture
+def temp_file():
+    """Creates a temporary test file."""
+    with tempfile.NamedTemporaryFile(mode="w+", delete=False) as f:
+        f.write("test content")
+        path = f.name
+    try:
+        yield path
+    finally:
+        if os.path.exists(path):
+            os.unlink(path)
+
+
+@pytest.mark.asyncio
+async def test_create_sandbox(manager):
+    """Tests sandbox creation."""
+    # Create default sandbox
+    sandbox_id = await manager.create_sandbox()
+    assert sandbox_id in manager._sandboxes
+    assert sandbox_id in manager._last_used
+
+    # Verify sandbox functionality
+    sandbox = await manager.get_sandbox(sandbox_id)
+    result = await sandbox.run_command("echo 'test'")
+    assert result.strip() == "test"
+
+
+@pytest.mark.asyncio
+async def test_max_sandboxes_limit(manager):
+    """Tests maximum sandbox limit enforcement."""
+    created_sandboxes = []
+    try:
+        # Create maximum number of sandboxes
+        for _ in range(manager.max_sandboxes):
+            sandbox_id = await manager.create_sandbox()
+            created_sandboxes.append(sandbox_id)
+
+        # Verify created sandbox count
+        assert len(manager._sandboxes) == manager.max_sandboxes
+
+        # Attempting to create additional sandbox should fail
+        with pytest.raises(RuntimeError) as exc_info:
+            await manager.create_sandbox()
+
+        # Verify error message
+        expected_message = (
+            f"Maximum number of sandboxes ({manager.max_sandboxes}) reached"
+        )
+        assert str(exc_info.value) == expected_message
+
+    finally:
+        # Clean up all created sandboxes
+        for sandbox_id in created_sandboxes:
+            try:
+                await manager.delete_sandbox(sandbox_id)
+            except Exception as e:
+                print(f"Failed to cleanup sandbox {sandbox_id}: {e}")
+
+
+@pytest.mark.asyncio
+async def test_get_nonexistent_sandbox(manager):
+    """Tests retrieving a non-existent sandbox."""
+    with pytest.raises(KeyError, match="Sandbox .* not found"):
+        await manager.get_sandbox("nonexistent-id")
+
+
+@pytest.mark.asyncio
+async def test_sandbox_cleanup(manager):
+    """Tests sandbox cleanup functionality."""
+    sandbox_id = await manager.create_sandbox()
+    assert sandbox_id in manager._sandboxes
+
+    await manager.delete_sandbox(sandbox_id)
+    assert sandbox_id not in manager._sandboxes
+    assert sandbox_id not in manager._last_used
+
+
+@pytest.mark.asyncio
+async def test_idle_sandbox_cleanup(manager):
+    """Tests automatic cleanup of idle sandboxes."""
+    # Set short idle timeout
+    manager.idle_timeout = 0.1
+
+    sandbox_id = await manager.create_sandbox()
+    assert sandbox_id in manager._sandboxes
+
+    # Wait longer than idle timeout
+    await asyncio.sleep(0.2)
+
+    # Trigger cleanup
+    await manager._cleanup_idle_sandboxes()
+    assert sandbox_id not in manager._sandboxes
+
+
+@pytest.mark.asyncio
+async def test_manager_cleanup(manager):
+    """Tests manager cleanup functionality."""
+    # Create multiple sandboxes
+    sandbox_ids = []
+    for _ in range(2):
+        sandbox_id = await manager.create_sandbox()
+        sandbox_ids.append(sandbox_id)
+
+    # Clean up all resources
+    await manager.cleanup()
+
+    # Verify all sandboxes have been cleaned up
+    assert not manager._sandboxes
+    assert not manager._last_used
+
+
+if __name__ == "__main__":
+    pytest.main(["-v", __file__])