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.

Thinking Block — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins

@liuch0812/dsh-thinking-block

Thinking Block

Cherry-Studio-style reasoning (深度思考) display for the DSH web chat: a stable collapsible think block with spinner, elapsed seconds, a stabilized one-line preview, and an auto-following scroll body — no more per-token flicker.

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

npx -y @deepseek-ai/dsh plugin --profile web add @liuch0812/dsh-thinking-block@0.1.3
READMECompatibilityVersions

Compatibility and provenance

Thinking Block is published as @liuch0812/dsh-thinking-block and currently resolves to version 0.1.3. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
npm
Registry updated
9/20/2026

Versions

0.1.3stable
8/16/2026
0.1.2stable
8/16/2026
0.1.1stable
8/16/2026
Show 1 more versionCollapse versions
0.1.0stable
8/16/2026

Related plugins

Loading related plugins…

Latest
0.1.3
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
23.1 kB
Files
6
Surface
web
License
MIT
Source
npm
GitHub
★ 0
Weekly downloads
22
Last push
8/16/2026
View source ↗Project homepage ↗
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 ui-customization.

Web App@deepseek-ai/dsh-web-appThe dsh browser-surface bundle: the web patch layer over dsh-base plus the runtime glue plugin (frontend dist serving, web-surface prompt, bash runtime variables, URL line)Experimental Agent Team Web Profile@deepseek-ai/dsh-experimental-agent-team-web-profileExperimental Web profile layer for Agent Teams Remote and UI pluginsRemote Web Ui@linxin666/dsh-remote-web-uiScan-to-pair remote access for the dsh web GUI that shares one official interface: a QR beside the settings button pairs phones and PCs into the same Web GUI (a portrait-touch adaptation layer for phones, full desktop on PCs) through one-time tokens and rClient Ui Task Board@linxin666/dsh-client-ui-task-boardHost-authoritative task board for the DSH Web GUI with real session execution, Host cron scheduling, and optional cross-platform idle-sleep protection; mounted without DSH source changes.

README

dsh-thinking-block

DeepSeek Harness (dsh) Web 插件：把主对话里的 thinking（深度思考）消息从「一行快速闪烁」升级为 Cherry Studio 风格的思考块 —— 稳定头部（旋转图标 + 已思考 N 秒 + 稳定化单行预览）+ 可展开的自动跟随滚动正文。

效果

状态头部正文
思考中旋转图标 +「深度思考」+「思考中 / 已思考 N 秒」+ 稳定化单行预览点击展开：完整流式文本，max-height 320px 滚动区，自动跟随底部
结束思考图标 +「深度思考」+「已思考 N 秒」（冻结）+ 首行预览同上（用户自行展开）

关键机制（移植自 Cherry Studio ThinkingBlock）：

  • 稳定化单行预览：只提取最近一个完整句/行（scanReasoningPreview），且每个预览片段 至少停留 1 秒（useMinimumDisplayDuration）——句子没写完预览不变，从根上消除逐 token 闪烁；
  • 头部状态稳定：旋转图标、思考计时（tabular-nums 防宽度抖动）、预览都不再逐 token 重写；
  • 滚动正文：展开后完整思考文本在限高滚动区内流式追加，节流自动滚动跟随尾部。

其余渲染（markdown 文本、图片、代码块、工具调用）与官方行为完全一致——插件通过 conversation.chat.node keyed slot 替换 assistant-step 渲染器，并复用 shell 内置的 dsh-client-ui-primitives / dsh-client-ui-attachment 组件。

一键安装

需要 pnpm 在 PATH 上（dsh plugin 依赖它）。

dsh plugin --profile web add @liuch0812/dsh-thinking-block

然后重启 dsh web，刷新页面即可生效。

卸载：

dsh plugin --profile web remove @liuch0812/dsh-thinking-block

源码

https://github.com/liuchang0812/dsh-thinking-block

License

MIT