drive9-ai/drive9-dsh
Project Overview项目介绍
Drive9 for DeepSeek Harness is a DSH plugin offering persistent agent workspaces and bounded tool evidence. Its core capability is a Drive9 revision-CAS filesystem backing Harness read/write/edit tools, an isolated backend for oversized tool results, and model-visible result_search and result_read tools with hard output caps. Use it on Linux when an agent needs durable workspace state plus a separate, unmounted evidence namespace. Caveat: the strong profile requires FUSE, while the eventual WebDAV profile can leave mounted process views stale beyond 30 seconds.
Drive9 for DeepSeek Harness 是 DSH 插件,提供持久化智能体工作区与有界工具证据。核心能力是 Drive9 revision-CAS 文件系统支持 Harness 的 read/write/edit 工具,独立的超额结果证据后端,以及 result_search、result_read 模型可见工具。适用于 Linux 上需要强一致性持久工作区与隔离证据存储的智能体场景。strong 模式需要 /dev/fuse,eventual 模式基于 WebDAV 且无读己写一致性保证。
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:drive9-dsh(drive9-ai/drive9-dsh)
仓库:https://github.com/drive9-ai/drive9-dsh
本站详情页:https://www.yhbd.top/plugins/drive9-ai-drive9-dsh/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 Apache-2.0 · ⭐ 2 · 最近提交 2026-08-14 · 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。
- 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 @drive9/drive9-dsh
把 drive9-ai/drive9-dsh 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
Drive9 for DeepSeek Harness
Persistent agent workspaces and durable, bounded tool evidence for DeepSeek Harness.
@drive9/drive9-dsh is a standard DSH bundle with four independent Cordis components:
- a Drive9 revision-CAS filesystem for Harness
read,write, andedittools; - an isolated evidence backend for oversized tool results;
- model-visible
result_searchandresult_readtools with hard output limits; - a model-visible runtime-context warning for the opt-in eventual mount profile.
The architecture keeps four lifecycles separate:
| Layer | Owner |
|---|---|
| Agent loop | DeepSeek Harness |
| Session and conversation history | DeepSeek Harness |
| Persistent workspace and immutable evidence | Drive9 |
| Shell, sandbox, language servers, and compute runtime | the user's DSH deployment |
The Drive9 mount only exposes the persistent workspace inside an existing runtime. It does not create, own, or keep that runtime alive. Evidence remains readable after the runtime or workspace disappears because it is stored under a separate, unmounted Drive9 root.
Drive9 does not provide a shell or sandbox. V1 exposes two explicit mount-consistency profiles:
strong(default and recommended) uses a Linux Drive9 FUSE mount in the same execution world as Harness process tools. Startup proves SDK-to-mount and mount-to-SDK coherence, and writes wait for exact mounted bytes before returning.eventualis an opt-in WebDAV profile. Model-facing reads, writes, revision CAS, and evidence still use the Drive9 SDK, but process tools may observe stale mounted bytes for more than 30 seconds after an SDK write.
The integration never silently downgrades strong to eventual. In real macOS
WebDAVFS validation, the Drive9 bridge observed an SDK write immediately while the
mounted open/stat view remained stale or blocked for more than 30 seconds.
Why
Agent work has two different kinds of state:
model filesystem tools ── Drive9 SDK + revision CAS ── persistent workspace
│
process tools ── /mnt/drive9 ─────┘
large tool output ── isolated Drive9 evidence root ── exact result_id
├─ result_search
└─ result_read
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 →
tt-a1i/archify
ZSeven-W/openpencil
omdsh-dev/dsh_workflow
zenx0x/allinluna
CheshireJCat/blender
limuyang2/agent-team
GZX2211/dsh-Visual-Workflow
sailoumili/novel-writer