wxxb789/dsh-legion

Name: wxxb789/dsh-legion
Author: wxxb789

Plugin插件 Native原生 ⭐ 2 MIT Subagents & Orchestration子代理与编排 Models & Routing模型与路由 Dev Workflow开发与代码工作流

DeepSeek Harness 的多代理团队、模型路由与声明式编排

Project Overview项目介绍

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

dsh-legion is a native multi-agent orchestration plugin built specifically for DeepSeek Harness (DSH), written in strictly typed TypeScript. To install it, users run the command dsh plugin --profile web add github:wxxb789/dsh-legion from the DSH CLI, then copy the provided configuration template into their personal agent preset and start a new DSH session. It adds a single legion tool to the coordinating root agent that handles delegation to pre-configured specialist subagents, without replacing DSH's existing runtime or adding extra heavy dependencies like external databases or standalone schedulers.

This plugin is designed for developers and deployment owners who already use DSH and want to implement reusable, policy-bound multi-agent delegation. Users can configure different specialists for different task types: fast models for quick summarization or extraction tasks, larger deeper models for complex debugging or architecture work, and read-only reviewers for independent code audits. Before relying on a custom configuration, users can run the built-in dsh-legion doctor command to validate their routing policy against test fixtures. Each specialist has its own model route, persona, tool permissions, and depth limits, so the root agent only needs to select the right specialist instead of handling model selection directly.

dsh-legion is released under the permissive MIT open source license, and requires Node.js version 22.19.0 or newer to build and run. All source code is hosted publicly on GitHub, and issue reports and contributions are welcome via the repository’s issue tracker. It relies entirely on DSH to provide core services like agent sessions, model adapters, subagent runtime, sandboxing, and approval workflows, so it does not need extra infrastructure to operate. Durable strategy runs are disabled by default, and currently do not support production-grade atomic run coordination, so users should test configurations thoroughly before deploying them for critical workflows.

dsh-legion 是专为 DeepSeek Harness (DSH) 开发的原生多智能体编排插件，基于 TypeScript 构建，提供可配置的专家智能体调度、LLM 模型路由、声明式群组与策略配置功能。它不会替换 DSH 原有运行时，而是通过添加一个 legion 工具让主协调智能体可以按预设策略将不同类型的任务分发给对应子智能体执行，整体架构轻量无额外依赖。安装方式十分简单，通过 DSH 官方 CLI 工具添加仓库地址即可完成部署。

它适合已经在使用 DSH 的开发者和部署管理员，帮助实现可复用、可审核的多智能体任务委托。典型工作流是，用户先将 Legion 配置模板复制到自己的代理预设中，重启新会话后，主智能体即可通过 legion 工具按任务类型选择对应专家。比如快速任务分配给轻量模型，复杂架构设计或调试任务分配给深度推理模型，还可以独立配置只读权限的评审专家。

本项目采用 MIT 许可证开源，依赖 Node.js 22.19.0 以上版本，不需要额外的调度器、数据库或独立运行时，仅依赖 DSH 本身提供的代理、会话、模型适配器和子智能体运行时能力。它默认关闭持久化策略运行，需要手动开启，并且当前不支持生产级的原子运行协调，仅提供验证和配置检查工具，用户可以使用内置的 doctor 命令验证路由策略配置。

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-legion（wxxb789/dsh-legion）
仓库：https://github.com/wxxb789/dsh-legion
本站详情页：https://www.yhbd.top/plugins/wxxb789-dsh-legion/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 2 · 最近提交 2026-09-02 · 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

Only 2 stars - very few users, little community feedback星标只有 2，几乎没人在用，遇到问题缺少社区反馈

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:wxxb789/dsh-legion

把 wxxb789/dsh-legion 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

38.7 KB · 缓存于 2026-09-02 19:41:06 · 38.7 KB

dsh-legion: Multi-Agent Orchestration and LLM Model Routing for DeepSeek Harness

English · 简体中文

dsh-legion is a TypeScript multi-agent orchestration plugin for DeepSeek Harness (DSH). It turns one AI coding agent into a bounded orchestration cohort: configurable AI agent Specialists, an exact LLM model router, declarative Cohorts and Strategies, structured results, and depth-limited subagent delegation — without replacing the DSH runtime.

TL;DR

What it is. A DeepSeek Harness plugin for multi-agent delegation policy — not a standalone agent framework.
What it adds. One model-facing legion tool whose choices are semantic Specialists such as quick, deep, and review. Each Specialist carries a deployment-owned model route, subagent backend, persona, tool filter, depth, and result contract.
Why it helps. The coordinating agent picks intent instead of model IDs, a prompt can never widen the policy behind a Specialist, and changing the model behind deep rewrites no prompts.
What it costs. One configuration row in a user-owned agent preset. No extra scheduler, session store, database, or agent runtime.
Who it is for. Developers and deployment owners already running DSH who want reviewable, reusable multi-agent delegation.

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 wxxb789/dsh-legion 的 README.md。在 GitHub 查看原文 →