CC19990113/dsh-plugin-codegraph
适用于DeepSeek Harness(dsh)的结构化代码智能——为代理提供codegraph和codegraph_index工具,用于查找符号的声明位置、调用对象以及变更影响范围,基于其自行构建的tree-sitter索引。与codegraph CLI的磁盘格式兼容。
Project Overview项目介绍
This is a native plugin built exclusively for DeepSeek Harness (DSH), designed to add structural code intelligence capabilities to DSH AI agents. It exposes two distinct tools to agents: codegraph for running 10 types of read-only queries against a pre-built symbol graph, and codegraph_index for building or refreshing the symbol index from scratch. To install the plugin, users just need to run the one-line command dsh plugin --profile <profile-name> add CC19990113/dsh-plugin-codegraph directly from the DSH CLI.
This plugin targets AI agent-assisted code editing workflows for large codebases, and fills gaps left by common existing tools. Unlike grep, which returns irrelevant matches from comments and strings and cannot answer call relationship questions, and unlike LSP, which requires a running per-language server and depends on cursor position for queries, this plugin delivers fast, accurate answers directly from the symbol index. The standard workflow starts with running codegraph_index to build the full project symbol graph, then uses codegraph operations to answer structural questions before any code changes are made.
This plugin is released under the permissive MIT open source license, and requires no external dependencies to function properly. It does not require users to install the standalone @colbymchenry/codegraph CLI separately, as the indexer and store run entirely in-process within DSH. It is fully interoperable with the standalone CLI: it can read existing indexes built by the CLI, and the CLI can also read indexes built by this plugin. Known limitations include partial gitignore syntax support, no semantic matching for queries, and potential breaks due to DSH’s developer preview status.
这是一款专为DeepSeek Harness(DSH)开发的原生插件,为DSH中的AI代理提供结构化代码情报能力。它为代理新增了codegraph和codegraph_index两个工具,让代理能够基于预构建的符号索引回答各类代码结构问题,包括符号声明位置、哪些函数调用了目标符号、修改符号会造成哪些影响等,相比文本搜索结果更精准。用户可通过DSH内置的插件命令一键完成安装。
这款插件面向需要修改大型代码仓库的AI代理开发场景,解决了常规工具的痛点:grep无法回答代码调用关系问题,结果还容易混入注释、字符串中的无关匹配;LSP需要为每种语言运行单独的服务器,且依赖光标位置而非符号名查询。典型工作流是先运行codegraph_index构建项目符号索引,再用codegraph查询结构问题。
该插件采用MIT许可开源,完全免费使用,不需要额外安装独立的codegraph CLI,索引器和存储都在进程内运行。它支持复用已有的@colbymchenry/codegraph CLI生成的索引,也兼容外部CLI读取本插件生成的索引。当前存在一定限制:不支持完整gitignore语法,不支持语义匹配,且DSH本身处于开发者预览版,可能存在不兼容变更。
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-plugin-codegraph(CC19990113/dsh-plugin-codegraph)
仓库:https://github.com/CC19990113/dsh-plugin-codegraph
本站详情页:https://www.yhbd.top/plugins/cc19990113-dsh-plugin-codegraph/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 13 · 最近提交 2026-08-24 · 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。
- 13 stars - an early-stage project星标 13,属于早期项目
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 dsh-plugin-codegraph
把 CC19990113/dsh-plugin-codegraph 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
dsh-plugin-codegraph
English | 中文
Structural code intelligence for DeepSeek Harness (dsh).
Gives the agent two tools — codegraph and codegraph_index — so it can ask where is this declared, who calls it, what breaks if I change it, and how does one symbol reach another, answered from a pre-built index instead of from text search.
dsh plugin --profile <name> add dsh-plugin-codegraph
Why
An agent editing code asks structural questions before it touches anything. The tools it usually has answer them badly or not at all:
- grep matches a name inside comments, strings, and unrelated identifiers, and cannot answer "who calls this" at all.
- LSP answers precisely, but needs a running server per language, a warm workspace index, and a cursor position rather than a name.
A symbol graph answers all of it from one cheap lookup. This plugin ships both halves: a store that serves queries from an on-disk graph, and an indexer that builds one, so a fresh workspace needs no external tooling.
What the model gets
Two tools, deliberately separate.
codegraph — ten read-only operations
| Operation | Answers | Required |
|---|---|---|
search |
Where is a symbol declared? | query |
node |
One symbol with its immediate callers and callees | symbol |
callers |
What calls this? | symbol |
callees |
What does this call? | symbol |
impact |
What can a change to this reach? | symbol |
trace |
How does one symbol reach another? | from, to |
files |
What is indexed, under a directory or glob? | — |
status |
How large and how fresh is the index? | — |
explore |
Several related declarations with their source | query |
context |
Everything relevant to a task | task |
codegraph_index — build or refresh the graph
Separate from codegraph rather than an eleventh operation, because indexing a large workspace takes minutes while a query takes milliseconds, and a tool's timeout budget is fixed per registration. Folding them together would force one budget that is either too tight for a real build or too loose to catch a hung query.
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 →
esengine/DeepSeek-Reasonix
strukto-ai/mirage
chuspeeism/dashi-taskboard
Aisland-SJL/dsh-worktable
ccch1mneyyy/working-activity
zhoushoujianwork/easyeda-agent
pulseaiclub/phi
Ikalus1988/MisakaNet