Skip to content

qwen-code.md

Latest commit

 

History

History
61 lines (44 loc) · 2.36 KB

qwen-code.md

File metadata and controls

61 lines (44 loc) · 2.36 KB
title Qwen Code
description Run Qwen Code inside an OpenSandbox container through an OpenAI-compatible endpoint.

Qwen Code Example

Run Qwen Code inside an OpenSandbox container through an OpenAI-compatible endpoint.

Start OpenSandbox server [local]

Pre-pull the code-interpreter image (includes Node.js):

docker pull sandbox-registry.cn-zhangjiakou.cr.aliyuncs.com/opensandbox/code-interpreter:v1.1.0

# use docker hub
# docker pull opensandbox/code-interpreter:v1.1.0

Then start the local OpenSandbox server, stdout logs will be visible in the terminal:

uv pip install opensandbox-server
opensandbox-server init-config ~/.sandbox.toml --example docker
opensandbox-server

Create and Access the Qwen Sandbox

# Install OpenSandbox package
uv pip install opensandbox

# Export provider settings
export API_KEY=your-api-key
export BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
export MODEL_NAME=qwen3-coder-plus

# Run the example
uv run python examples/qwen-code/main.py

The script installs Qwen Code (npm install -g @qwen-code/qwen-code@latest) at runtime, writes a project-local .qwen/settings.json inside the sandbox, and runs qwen -p "Compute 1+1 and reply with only the final number." in headless mode. The API key is injected only through the API_KEY environment variable and is not written into the repository.

Environment Variables

Variable Default Description
SANDBOX_DOMAIN localhost:8080 Sandbox service address
SANDBOX_API_KEY (optional for local) API key if your server requires authentication
SANDBOX_IMAGE sandbox-registry.cn-zhangjiakou.cr.aliyuncs.com/opensandbox/code-interpreter:v1.1.0 Sandbox image to use
API_KEY (required) API key for the OpenAI-compatible provider used by Qwen Code
BASE_URL https://dashscope.aliyuncs.com/compatible-mode/v1 OpenAI-compatible base URL
MODEL_NAME qwen3-coder-plus Model name for Qwen Code

References