安装
npx -y @deepseek-ai/dsh plugin --profile web add github:lincong1987/dsh-model-switch此安装命令根据 GitHub 仓库地址生成,是未经验证的安装起点。
README
维护者编写的文档快照。
dsh-model-switch
English | 中文
Use the right model for each stage of work in DeepSeek Harness.
The main conversation, subagents, and plan execution serve different purposes. dsh-model-switch lets each of them use a suitable model without changing the normal DSH workflow.
Why use it
- Match models to tasks — keep your preferred model in the main conversation and use another model for subagents or plan execution.
- Avoid repeated switching — save defaults once instead of changing models before every task.
- Confirm before execution — review or change the model directly in the plan approval panel.
- See what subagents use — display the model, context window, and reasoning effort, such as
GPT-5.6 Sol 1M Max. - Keep the main model unchanged — after plan execution, DSH restores the previous main-session model.
Preview
Configure model defaults
Choose the model for plan execution
![]() | ![]() |
See the model used by subagents
![]() | ![]() |
Install
dsh plugin --profile web add github:lincong1987/dsh-model-switch
Restart DSH after installation.
Use
- Open Settings → Model switch.
- Configure the Subagent model and Plan execution model:
- Follow main model uses the current conversation model.
- Custom lets you choose a model and reasoning effort.
- When reviewing a plan, confirm or change the execution model before selecting Approve.
The model selected in the plan review panel takes priority over the saved plan-execution setting.
Compatibility
Requires DeepSeek Harness 0.1.0-rc.7 or later. Settings are stored in the host settings document through the plugin's registered model-switch namespace.
Subagent model switching applies to in-process subagents such as spawn and fork. External-process agents may manage their models independently.
Community
Links
License
MIT
项目文件与信号
以下项目是目录快照中检测到的公开仓库信号。
仓库信息
- 开发语言
- TypeScript
- 许可证
- MIT
- 最后更新
- 2026年8月18日 10:27
谨慎安装
请检查源代码、权限、生命周期脚本、依赖与网络访问;不受信任的插件应先在隔离环境中测试。



