dbgpt-sandbox

[ymx10086]

Sandbox for dbgpt code execute in future

Description

This PR introduces a sandbox environment for code execution in dbgpt, based on Docker containers.
It provides an asynchronous, multi-language, stateful execution environment that allows safe execution of untrusted code inside isolated Docker containers.

Key features:

• Multi-language support: Python, JavaScript, Java, C++, Go, Rust, and VNC-based environments.
• Asynchronous runtime: All Docker API calls are wrapped with asyncio.to_thread to avoid blocking the event loop.
• Stateful sessions: Each session maps to a dedicated container with persistent working directory and environment.
• Dependency installation: Supports runtime installation of Python (pip) and JavaScript (npm) dependencies.
• File operations: Upload, download, and retrieve container file contents in base64 format.
• Execution monitoring: Collects stdout, stderr, exit code, execution time, and container resource usage.
• Session management: Lifecycle management (create, destroy, cleanup expired sessions).
• VNC/NoVNC support: For interactive GUI-based languages/environments.
• This lays the foundation for safe, reproducible, and extensible code execution in dbgpt.

How Has This Been Tested?

• Start the Docker daemon and ensure required language images exist (python:3.11-slim, node:lts-slim, etc.).
• Create a session via DockerRuntime.create_session.
• Execute code (execute with Python/JS code).
• install dependencies dynamically.
• Fetch file content with get_file_content.
• Run health_check to verify Docker runtime state.

Snapshots:

Checklist:

• My code follows the style guidelines of this project
• I have already rebased the commits and make the commit message conform to the project standard.
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• Any dependent changes have been merged and published in downstream modules