BanboLee/banbo-dsh

Bundle捆绑包 ⭐ 2 MIT Runtime & Injection运行时与注入

Project Overview项目介绍

banbo-dsh is a curated bundle collection built specifically for the DeepSeek Harness (DSH) agent runtime. It publishes six ready-to-use plugins on npm under the @banbolee/dsh-* scope and ships them through the standard dsh plugin --profile <profile> add @banbolee/... command, so end users never have to clone the repository. Required host environment includes DSH 0.1.7-rc.2 family, Node.js ≥ 22, and pnpm 9.x; each bundle targets a distinct concern inside DSH and the README ships English plus Chinese variants.

The bundles cover concrete runtime gaps: @banbolee/dsh-rtk rewrites every mounted shell command through rtk rewrite and compresses model-facing grep output with rtk pipe; @banbolee/dsh-codegraph-mcp exposes the CodeGraph MCP server over stdio through the official DSH bridge plus an agent-instructions install helper; @banbolee/dsh-fish-shell provides Fish executors, a model-callable fish tool, and a per-agent policy that swaps bash for fish under any agent preset. @banbolee/dsh-lsp-diagnostics appends a persistent LSP diagnostics notice to the next model inference after write/edit/str_replace_editor mutations and exposes a lsp_diagnostics(file_path) tool, while @banbolee/dsh-llm-pi-ai-with-session is a thin session wrapper over llm-pi-ai that registers explicit session provider routes and injects a configurable session header (default x-session-id) on every LLM request, reusing gateway, credentials, model and reasoning effort. @banbolee/dsh-agents lets you define an Agent team in YAML with named agent_<id> tools, per-agent personas and tool surfaces, an explicit delegation graph, and absolute depth and concurrency budgets, then registers them as @deepseek-ai/dsh-agent-preset rows on the profile's preset registry.

External binaries — rtk, codegraph, fish, typescript-language-server, gopls, and optionally clangd, rust-analyzer, pyright-langserver — must be pre-installed by the user on PATH or pinned through bundle config; the bundles never download them, and a missing binary never blocks install or tests, it simply fails open to passthrough or disables the affected tool. Uninstall uses dsh plugin --profile <profile> remove @banbolee/...; a normal uninstall of @banbolee/dsh-agents preserves $DSH_HOME/banbo-agents/ data (YAML, personas, ABI manifest) so reinstalling restores everything, and a full wipe is an explicit destructive operation documented in the plugin README. Contributors clone the repo, run env NODE_ENV=development pnpm install (production skips devDependencies and breaks the dependency-graph assertions), and add bundles with dsh plugin --profile <profile> add -w ./plugins/<bundle> — fish-shell is the exception and uses no -w. Optional real headless E2E requires building sibling RTK and CodeGraph, then corepack pnpm test:e2e:headless, with overridable paths via DSH_REAL_E2E_DSH_BIN, DSH_REAL_E2E_NODE_BIN, DSH_REAL_E2E_RTK_BIN, and DSH_REAL_E2E_CODEGRAPH_BIN. License is MIT.

banbo-dsh 是面向 DeepSeek Harness(DSH)的插件集合,在 npm 上以 @banbolee/dsh-* 命名发布六个开箱即用的 bundle。用户无需克隆仓库,可通过 dsh plugin --profile <profile> add @banbolee/... 一条命令把任意 bundle 挂载到指定 profile。前置依赖为 dsh 0.1.7-rc.2 系列、Node.js ≥ 22 与 pnpm 9.x。

六个 bundle 各自承担不同职责:dsh-rtk 用 rtk rewrite 重写 shell 命令并以 rtk pipe 压缩 grep 输出;dsh-codegraph-mcp 通过 DSH 桥以 stdio 对外暴露 CodeGraph MCP;dsh-fish-shell 提供 Fish 执行器、模型可调用的 fish 工具,以及按 agent preset 切换 bash 为 fish 的策略;dsh-lsp-diagnostics 在写入/编辑文件后把 LSP 诊断追加到下次推理上下文,并暴露 lsp_diagnostics 工具;dsh-llm-pi-ai-with-session 在 llm-pi-ai 之上封装会话路由,自动注入默认 x-session-id 请求头;dsh-agents 允许以 YAML 定义 Agent 团队(命名工具、人设、工具面、委托图、深度与并发预算),并以 @deepseek-ai/dsh-agent-preset 行写入 preset 注册表。

rtk、codegraph、fish 以及 typescript-language-server、gopls(可选 clangd、rust-analyzer、pyright-langserver)等二进制必须由用户自行预装并加入 PATH,缺失时 bundle 安装与测试不会失败,仅对应特性 fail-open 退化为透传。卸载通过 dsh plugin --profile <profile> remove @banbolee/... 完成,普通卸载 @banbolee/dsh-agents 会保留 $DSH_HOME/banbo-agents/ 下的 YAML、人设与 ABI 清单,重装即可还原。贡献者可克隆仓库后在 NODE_ENV=development 下 pnpm install 与 pnpm test,可选 pnpm test:e2e:headless 需先构建同级 RTK 与 CodeGraph。仓库以 MIT 协议开源。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 2 warnings2 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
  • No DSH plugin manifest detected - it may only carry the dsh-plugin topic, so the install method must be confirmed on the spot未检测到 DSH 插件清单:可能只是打了 dsh-plugin 话题,安装方式要现场确认
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 @banbolee/dsh-rtk

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

READMEREADME

banbo-dsh

CI

English | 中文

A collection of DeepSeek Harness (DSH) plugins: six ready-to-use bundles published on npm under @banbolee/dsh-*, installable into any DSH profile with a single command — no need to clone this repository. MIT licensed.

Quick install (users)

Prerequisites: dsh (0.2.0-rc.1 family), Node.js >= 22, pnpm 9.x.

Install whichever bundles you need:

dsh plugin --profile <profile> add @banbolee/dsh-rtk
dsh plugin --profile <profile> add @banbolee/dsh-codegraph-mcp
dsh plugin --profile <profile> add @banbolee/dsh-fish-shell
dsh plugin --profile <profile> add @banbolee/dsh-lsp-diagnostics
dsh plugin --profile <profile> add @banbolee/dsh-llm-pi-ai-with-session
dsh plugin --profile <profile> add @banbolee/dsh-agents

Bundles

Bundle What it does Binary it needs
@banbolee/dsh-rtk Decorates the mounted shell executor: every command is rewritten through the rtk rewrite oracle, and model-facing grep output is compressed via rtk pipe rtk
@banbolee/dsh-codegraph-mcp Adds an mcp-codegraph row that serves the CodeGraph MCP server (codegraph serve --mcp) over stdio through the official DSH bridge, plus an agent-instructions install helper codegraph
@banbolee/dsh-fish-shell Fish executors (sandboxed and local) plus a model-facing fish tool and a per-agent policy that swaps bash for fish under any agent preset fish
@banbolee/dsh-lsp-diagnostics After write/edit/str_replace_editor mutations, appends a persistent LSP diagnostics notice to the next model inference; also registers a model-callable lsp_diagnostics(file_path) tool typescript-language-server, gopls (opt-in: clangd, rust-analyzer, pyright-langserver)
@banbolee/dsh-llm-pi-ai-with-session Generic session wrapper over llm-pi-ai: registers explicit session provider routes that carry a dynamic session id header (default x-session-id) on every LLM request none (reuses llm-pi-ai providers)
@banbolee/dsh-agents Define your own Agent team in YAML: named agent_<id> tools, a persona and a tool surface per Agent, an explicit delegation graph, and absolute depth/concurrency budgets; ships its presets as @deepseek-ai/dsh-agent-preset rows on the profile's preset registry none

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 →

← 上一个 Prev dsh-ivory 下一个 Next dsh-memory-search-plus →