lincong1987/dsh-model-switch

Name: lincong1987/dsh-model-switch
Author: lincong1987

Desktop桌面端 Native原生 ⭐ 10 MIT Subagents & Orchestration子代理与编排 Models & Routing模型与路由 Productivity & Tasks效率与任务

dsh 插件：为子代理与计划执行提供灵活的模型切换。

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

This is a native plugin built exclusively for DeepSeek Harness that enables per-stage model routing for AI-assisted workflows. It lets users assign separate AI models to the main conversation, in-process subagents, and plan execution steps without altering DSH’s native workflow. It is not published as an npm package, so installation must be done via the direct GitHub reference. To install, users run the dsh plugin add command via the DSH CLI pointing to this GitHub repository, replace the profile argument to match their running DSH instance (usually desktop for DeepSeek Harness Desktop), then restart DSH to activate the plugin.

After installation, users navigate to the DSH settings panel to open the model switch configuration page. There, they can set default models for subagents and plan execution, either choosing to follow the main conversation model or set a custom model with specific reasoning effort. This tool is designed for DSH users who want to optimize model costs by using smaller, cheaper models for routine subagent tasks while keeping a more capable model for the main conversation. When reviewing a generated plan before approval, users can override the default execution model directly in the review panel. After plan execution completes, DSH automatically restores the original model for the main conversation, so users do not need to manually switch back.

The plugin requires DeepSeek Harness version 0.1.5-rc.1 or newer, and it only applies to in-process subagents like spawn and fork. External-process subagents manage their own models independently, so this plugin does not affect them. It is released under the open source MIT license, so it is free to use and modify. After upgrading DSH to a new compatible version, users need to reinstall this plugin with the --force flag to refresh the source code. Before upgrading major DSH versions, users should back up their local ~/.dsh directory to avoid data loss from incompatible storage format changes.

这是一个专为DeepSeek Harness打造的原生插件，核心功能是根据不同工作阶段自动路由切换AI模型。它允许用户为主会话、子代理、计划执行三个不同工作阶段分别分配合适的模型，无需改变原有的DSH工作流。安装需通过DSH命令行执行指定GitHub安装指令，根据你运行的DSH profile替换对应参数，安装完成后必须重启DSH才能生效。

用户可以先在DSH设置的模型切换面板配置各阶段的默认模型，保存一次默认设置后就无需在每次任务开始前重复手动切换模型。执行计划前，可以在计划审批面板直接查看或修改本次执行要用的模型，执行完成后DSH会自动恢复之前主会话的模型。还可以直接在界面上查看子代理使用的模型、上下文窗口和推理强度等信息。

本插件要求DSH版本不低于0.1.5-rc.1，仅对进程内子代理生效，外部进程代理可独立管理自身模型。插件采用MIT许可证开源，免费使用，升级DSH版本后需要重新安装插件才能保证兼容性。升级DSH前建议备份本地~/.dsh目录，避免格式不兼容导致数据丢失。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-model-switch（lincong1987/dsh-model-switch）
仓库：https://github.com/lincong1987/dsh-model-switch
本站详情页：https://www.yhbd.top/plugins/lincong1987-dsh-model-switch/
本站登记：类型 client · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 10 · 最近提交 2026-09-10 · 主语言 TypeScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意

10 stars - an early-stage project星标 10，属于早期项目
Desktop client: installation downloads an executable - verify the publisher and checksums桌面客户端：安装会下载可执行文件，请核对发布者与校验和

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile web add github:lincong1987/dsh-model-switch

把 lincong1987/dsh-model-switch 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

5.8 KB · 缓存于 2026-09-10 19:40:25 · 5.8 KB

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

Use the GitHub spec. This plugin is not published as an npm package, so do not use @lincong1987/dsh-model-switch.

dsh plugin --profile web add github:lincong1987/dsh-model-switch

Replace web with the profile DSH is actually running. DeepSeek Harness Desktop typically uses desktop.

Restart DSH after installation.

Update DSH

This plugin requires DeepSeek Harness 0.1.5-rc.1 or later. DSH has no dsh update command — install the version you want the same way you originally installed it.

Check the installed version and what npm currently publishes:

dsh --version
npm view @deepseek-ai/dsh dist-tags

As of 2026-09-10, latest points to 0.1.5-rc.1 (this plugin's current target), next points to 0.1.5-rc.2, and the alpha tag points to 0.1.5-alpha.2. Pin the exact version (@0.1.5-rc.1) when reproducibility matters.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 lincong1987/dsh-model-switch 的 README.md。在 GitHub 查看原文 →