DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Knowledge Canvas — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins

dsh-knowledge-canvas

Knowledge Canvas

Tree-shaped knowledge bases for DeepSeek Harness: per-session activation, a node graph view, and review markers for model edits.

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add dsh-knowledge-canvas@0.1.0
READMECompatibilityVersions

Compatibility and provenance

Knowledge Canvas is published as dsh-knowledge-canvas and currently resolves to version 0.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
npm
Registry updated
10/16/2026

Versions

0.1.0stable
10/16/2026

Related plugins

Loading related plugins…

Latest
0.1.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
505.8 kB
Files
25
Surface
web
License
Not declared
Source
npm
GitHub
★ 0
Weekly downloads
0
Last push
10/16/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in memory-context.

Hindsight Coding Agents@vectorize-io/hindsight-coding-agentsReflect-only Hindsight long-term memory for coding agents (harness-pluggable: opencode, …), with automatic background ingestion (no setup CLI).Ab Memorydsh-ab-memory--- description: "The dsh-ab-memory package: a cross-session, file-backed agent memory with five tools (remember / recall / forget / load_skill / distill) and an always-on light injection." kind: "package-reference" ---Memsearch Dsh@zilliz/memsearch-dshMemSearch plugin for DeepSeek Harness: shared markdown memory across agents, with capture, pre-step context injection, memory-recall skill, and a skill-candidate review panel.Archive Manager@michengai/dsh-archive-manager归档、恢复、收藏和永久删除会话，并诊断损坏的会话日志。 · Archive, restore, favorite, and permanently delete sessions, and diagnose damaged session logs.

README

dsh-knowledge-canvas

包名是 dsh-knowledge-canvas（dsh-knowledge-tree 在 npm 上已被别人占用）。 本机那个目录仍叫 dsh-knowledge-tree —— 它只是 link: 的目标路径，不是包名。

DeepSeek Harness 的树状知识库插件，支持会话选择、大纲注入、节点编辑与修改记录。

修改文件时的知识提醒

模型调用 write / edit 修改 lib/ 或 index.js 时，插件通过 tools/post-execute 的 additionalContexts 发送 o4、o10；修改 client.js 时发送 o4、o19。

**已验证送达：**使用已安装桌面版 0.2.0-rc.2 的真实 AgentLoop 和 edit 工具，为本插件 lib/inject.js 添加一行注释后，下一次模型请求包含“这个文件属于「改的是宿主那一半」——先看这两条”。提醒作为紧跟工具结果的独立补充消息送达，不拼接进工具结果正文；不能只靠工具卡片是否显示该文字判断成功。

验证使用本地确定性模型探针，没有调用付费模型 API。它证明消息送达，不证明模型一定遵守；对不知情新会话的行为盲测尚未进行。见 验证证据。

怎么关掉它（不用改代码）

在 <工作区>/.dsh-knowledge/ 下放一个空文件 .no-action-notes，这次工具调用就不附提醒；删掉即恢复。

它是按次读取的，不是启动时读的——所以切换两组实验可以跑在同一个进程里，除了这一个文件，其他条件完全一样。这也是它不做成常量的原因：要比较「有提醒」和「没提醒」，两组必须只差这一件事。

顺带记一条实验设计上的坑（2026-10-16 踩的）：拿「改 lib/ 后说不说要重启」当判据是失效的——那两条节点的摘要本来就在系统提示的大纲里，两组都有，所以这个判据量不出提醒的作用。见知识库 o21。

检查与重载

node check-client-loads.mjs   # 以及同目录下其余八条 check-*.mjs
node test-store.mjs           # 313 项断言
npm run check:all             # 上面两件一起

修改 index.js / lib/* 后必须重启 Harness；修改 client.js 后刷新页面。