xuanyuanluoxue/computer-use-vision ↗★ 0
dsh-computer-use-vision
Windows computer-use capability for DeepSeek Harness: screenshot → vision model → simulated mouse/keyboard input, with self-evolving knowledge base.
安装
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xuanyuanluoxue/computer-use-vision说明文档
阅读完整 README ↗配置
在 cordis.yml 中启用并配置:
plugins:
- name: dsh-computer-use-vision
config:
visionBaseUrl: "https://dashscope.aliyuncs.com/compatible-mode/v1" # OpenAI 兼容端点
visionModel: "qwen-vl-max" # 任意 OpenAI 兼容 vision 模型
visionApiKey: "" # 留空则读 VISION_API_KEY 环境变量
visionTimeoutMs: 30000
commandTimeoutMs: 10000
Key 读取优先级:config.visionApiKey > 环境变量 VISION_API_KEY > DASHSCOPE_API_KEY
支持任何 OpenAI 兼容的 vision 服务(阿里云百炼 / OpenAI / 中转等),改 visionBaseUrl 与 visionModel 即可。
配置 Vision Key
$env:VISION_API_KEY = "sk-xxx"