llm-sandbox copilot-instructions.md

GitHub Copilot Instructions for LLM Sandbox

Project Overview

LLM Sandbox is a lightweight and portable sandbox environment designed to run Large Language Model (LLM) generated code in a safe and isolated mode. The project provides secure execution environments for AI-generated code with:

• Multi-language support: Python, JavaScript/Node.js, Java, C++, Go, R, and Ruby
• Flexible backends: Docker, Kubernetes, Podman, and Micromamba
• Security-first design: Isolated execution, security policies, resource limits, and network isolation
• LLM framework integration: Works with LangChain, LangGraph, LlamaIndex, OpenAI, and more
• Model Context Protocol (MCP): Server implementation for MCP clients like Claude Desktop

Code Style and Formatting

Python Code Standards

• Python version: Support Python 3.10, 3.11, 3.12, and 3.13
• Style guide: Follow PEP 8 with Ruff enforced rules (see pyproject.toml)
• Line length: Maximum 120 characters
• Type hints: Always use type hints for function signatures and class attributes
• Docstrings: Use Google-style docstrings for all public functions, classes, and modules

Example:

def execute_code(code: str, timeout: int = 30) -> ExecutionResult:
    """Execute code in the sandbox environment.

    Args:
        code: The code to execute
        timeout: Maximum execution time in seconds

    Returns:
        ExecutionResult containing stdout, stderr, and exit code

    Raises:
        TimeoutError: If execution exceeds timeout
        SecurityError: If code violates security policy
    """
    pass

Code Organization

• Use Pydantic models for data structures and configuration
• Follow existing module structure:
  • llm_sandbox/core/: Core functionality and base classes
  • llm_sandbox/language_handlers/: Language-specific handlers
  • llm_sandbox/mcp_server/: MCP server implementation
  • Backend implementations: docker.py, kubernetes.py, podman.py, micromamba.py