Apache-2.0 interactive terminal UI plugin for the official DeepSeek Harness (dsh): install into the tui profile with `dsh plugin add`, get session workspace, image pipeline and reasoning visualization as a pure presentation layer.
DSH integration
Compatible
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-21
License
Apache-2.0
01What can it help you accomplish?
Run DeepSeek Harness coding sessions in a full interactive terminal workspace
Real-time session rendering with resume, /fork branching, /rewind rollback, /export Markdown transcripts, slash menus, approval cards and live status/config/tasks/workflow panels
Developers using the official dsh CLI who want a rich in-terminal coding-agent experience instead of the plain CLI
Send images to the model end-to-end from the terminal
Clipboard-pasted images rendered inline (kitty / iTerm2), delivered via the harness attachment service, auto-described by a vision-bridge model when the main model cannot see
Users who paste screenshots or designs into coding sessions and need vision-capable models to actually see them
Watch and control the agent's reasoning and approvals in real time
Collapsible thinking blocks (Ctrl+O), pending approval cards with inline diff preview, mode cycling (normal → plan → always-approve)
Developers who want visible reasoning traces and structured approval flow during dsh coding sessions
02How to install into DeepSeek Harness
Prerequisites
- Official dsh CLI `@deepseek-ai/dsh` at `0.1.0-rc.8` — the package is not a standalone program and cannot run with just `npm i`
- Node.js `^22.19 || >=24`
- `pnpm` on PATH (the `dsh plugin` command forwards to it)
Installation steps
- 01
Install the plugin into the tui profile: `npx -y @deepseek-ai/dsh@0.1.0-rc.8 plugin --profile tui add @huiliyi37/dsh-tianshu-tui` (or from Git: `... add github:huiliyi37/dsh-tianshu-tui`)
$ npx -y @deepseek-ai/dsh@0.1.0-rc.8 plugin --profile tui add @huiliyi37/dsh-tianshu-tui
- 02
Launch: `npx -y @deepseek-ai/dsh@0.1.0-rc.8 --profile tui` (if the official CLI is globally installed at 0.1.0-rc.8, plain `dsh` works too)
$ npx -y @deepseek-ai/dsh@0.1.0-rc.8 --profile tui
Verify the integration
- Success when the welcome page shows the dsh-tianshu-tui brand; exit with `Ctrl+Q` or `/exit`
03DSH integration and capability boundaries
TUI plugin installed into the official dsh CLI's tui profile via `dsh plugin --profile tui add`; pure presentation layer over the official DeepSeek Harness session event stream
Full session workspace in the terminal
dsh coding sessions→real-time rendering, append-only scroll transcript, session resume on startup, /fork branching, /rewind rollback (session truncation + optional file restore), /export Markdown transcript
/rewind truncates the session event log and can roll files back to a pre-boundary snapshot/export writes a Markdown transcript fileEnd-to-end image pipeline with vision bridge
clipboard-pasted or attached images→inline rendering via kitty / iTerm2 graphics protocols, delivery through the harness attachment service, auto vision-model description when the main model is text-only
oversized images are compressed before sending (1568px long-edge cap, JPEG 0.82 → 0.55 → 1024px + 0.55)Complete input surface
user typing in the terminal→slash dropdown (fuzzy prefix match, MRU sort, ghost preview), @-path Tab completion, @mention expansion, bracketed paste, optional vim keys, external editor (Ctrl+E), history search (Ctrl+F), Ctrl+. keymap overlay
local preferences persisted to ~/.dsh-tui/prefs.jsoninput history persisted to ~/.dsh-tui/input-history.json (1000-entry cap; delete the file to clear)Auditable pure presentation layer
session event stream from the host harness→all rendered state derived from session events; user input becomes ordinary logged messages
04Who is it for? When not to use it?
Good for
- Developers using the official dsh CLI who want a rich in-terminal coding-agent experience instead of the plain CLI
- Users who paste screenshots or designs into coding sessions and need vision-capable models to actually see them
- Developers who want visible reasoning traces and structured approval flow during dsh coding sessions
Not for
- Not a standalone program: requires the official `@deepseek-ai/dsh` CLI pinned at `0.1.0-rc.8`, Node.js `^22.19 || >=24`, and pnpm on PATH. A stale `dsh` binary on PATH can cause ERR_FS_EISDIR errors.
- Must not be installed into oh-my-tianshu's (@huiliyi37 ecosystem) tui profile — mixing ecosystems creates fragile cross-ecosystem resolution of @deepseek-ai/* via stale symlinks in ~/.dsh/profiles/node_modules.
05Compatibility, maintenance and safety notes
- Not a standalone program: requires the official `@deepseek-ai/dsh` CLI pinned at `0.1.0-rc.8`, Node.js `^22.19 || >=24`, and pnpm on PATH. A stale `dsh` binary on PATH can cause ERR_FS_EISDIR errors.
- Must not be installed into oh-my-tianshu's (@huiliyi37 ecosystem) tui profile — mixing ecosystems creates fragile cross-ecosystem resolution of @deepseek-ai/* via stale symlinks in ~/.dsh/profiles/node_modules.
- On every launch the plugin checks npm `latest` for self-updates (network call; disable with DSH_TUI_SKIP_UPDATE=1). Image re-asking additionally requires the companion @deepseek-ai/dsh-vision-ask package, which the TUI bundle does not ship.
Apache-2.0 · actively maintained (latest release v0.1.2-rc.12, 2026-08-20)
06Frequently asked questions
How do I install dsh-tianshu-tui into DeepSeek Harness?
It's a dsh plugin, not a standalone program. First install the official CLI @deepseek-ai/dsh (0.1.0-rc.8), then run `npx -y @deepseek-ai/dsh@0.1.0-rc.8 plugin --profile tui add @huiliyi37/dsh-tianshu-tui`, and launch with `npx -y @deepseek-ai/dsh@0.1.0-rc.8 --profile tui`.
Is it native to dsh or an MCP server?
Neither MCP nor a standalone app: it's a TUI plugin running inside the official dsh's tui profile. The UI is a pure presentation layer — all agent state comes from the session event stream, and it registers no prompts, tools or context surfaces.
What prerequisites are needed?
Official @deepseek-ai/dsh at 0.1.0-rc.8, Node.js ^22.19 || >=24, and pnpm on PATH (the dsh plugin command forwards to it). Installing the package alone with npm i will not run it.
Does it auto-update or call the network?
After an npm install, each launch compares against npm latest and writes new versions into the profile (restart to apply). Set DSH_TUI_SKIP_UPDATE=1 to skip the network check; github:/link: installs are never rewritten.
Any known limits?
Image re-asking (ask_image) requires the companion @deepseek-ai/dsh-vision-ask package, not shipped in the bundle. LSP diagnostics are display-only (tool-card badges + /lsp panel) and are not exposed to the model. Do not install it into oh-my-tianshu's tui profile.
07Related DSH workflows
dsh-better-sidebar
by omdsh-dev
Full sidebar workbench with file rendering and editing, terminal, Git, and subagents; third-party plugins can register new tabs.
dsh-tui
by ccch1mneyyy
Claude Code 风格全屏终端 TUI：像素鲸鱼顶栏、双流光大字、实时工作状态行、思考流式展开、双击 Esc 时间回溯、上下文进度条 + TPS 仪表；接入 Agent preset（standard/code/minimal/cordis）、Skills、MCP、Goals、Todos、子代理，/ 命令注册表与随附技能（audit/bug/review/practice/pr_comments/release-notes/vuln-check）；纯插件挂载零核心改动。
dsh-popout-sidebar
by e2mcc
A sidebar can pop out a separate browser tab (drag it to another monitor)
tokenledger
by zh667
Relay-site attributed token usage for DeepSeek Harness — zero config, no credentials
08Data and sources
**dsh-tianshu-tui**（`@huiliyi37/dsh-tianshu-tui`）是官方 [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness)…
npx -y @deepseek-ai/dsh@0.1.0-rc.8 plugin --profile tui add @huiliyi37/dsh-tianshu-tui
UI 是纯展示层：所有 agent 状态都来自会话事件流。
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-21. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.