deepseek-harness-tui
This fork — maintained by Auth Tecnologia as the base of a complete terminal
interface for the DeepSeek Harness: see ROADMAP.md. Originally
written by gxinxing, MIT;
the name is provisional.
An interactive terminal chat for DeepSeek Harness — terminal-native style, built with Ink (React for terminals).
Give it a TokenDance key and a dsh install; run dsh --profile tui and you get a zero-chrome terminal chat with DeepSeek models: bottom-anchored transcript, tool calls folded into cells, thinking folding, and a theme that adapts to your terminal via OSC 11. It's a thin, readable plugin (~800 lines of UI) — not a re-implementation of the harness.
English · 简体中文
Install
On Linux or macOS, one line — no sudo, everything in your home folder:
curl -fsSL https://auth-com-br.github.io/dsh-tui/install.sh | sh
It uses your Node.js 20+ (or puts the official one in ~/.local/share/dsh-tui), installs the
harness with it at the version this TUI is tested on (the harness's 0.2 series changed its API and
does not run it yet), wires its tui profile to this TUI, and adds two commands to ~/.local/bin:
dsh, which opens the TUI with no --profile (the harness's own dsh web, dsh plugin … and
dsh --profile … pass through), and dsh-tui. Run it again to update. Then dsh, and /models
to choose a model. The page: https://auth-com-br.github.io/dsh-tui/ — the installer:
docs/install.sh.
By hand
Requires Node.js ≥ 20 and the DeepSeek Harness CLI:
npm install -g @deepseek-ai/dsh # the harness (no Homebrew tap yet)
git clone https://github.com/gxinxing/deepseek-harness-tui
cd deepseek-harness-tui && pnpm install
Wire the plugin bundle into the tui profile (one-time):
dsh plugin --profile tui add @deepseek-ai/dsh-headless
dsh plugin --profile tui add /path/to/deepseek-harness-tui
Use
export TOKENDANCE_API_KEY=sk-... # or add it to ~/.dsh/.credentials.yaml (0600)
dsh --profile tui # open the TUI
In the TUI: a drag selects text in the conversation alone — not the side panel, not the composer — and copies it when you let go, as OpenCode does; ctrl + v attaches the image on the clipboard, and pasting or dropping an image file attaches it (for a model that takes images); /copy copies the last answer whole (/copy 2 the one before). The wheel and ↑/↓ scroll, ctrl + ↑/ctrl + ↓ recall earlier messages, a click (or ctrl + t) opens or folds a thought, esc interrupts the running turn, /help shows all keys and commands. /mouse off gives the mouse back to the terminal and its own selection.
What it does
- Terminal-native UI, not a re-skinned echo. The transcript is the surface — no boxes, no chrome. The DeepSeek brand banner (ANSI Shadow logo, gradient) greets you only on the empty state; model · cwd live in a dim footer.
- Tool calls fold into cells.
⠋ Running <cmd> while active → ✓ <cmd> • 1.2s (or ✗ on error), with output merged into the cell, dimmed, and truncated head + tail (… +N lines). No interleaved wall of raw output.
- Theme derived from your terminal. OSC 11 probes the real background: message tints and code chips are blended from it (12% white over dark, 4% black over light) — never hardcoded hex. Force a theme with
DSH_TUI_BG=#ffffff for testing.
- Thinking you can fold.
ctrl + t toggles the reasoning trace; esc aborts the turn at any time via agent.cancel({ kind: 'user' }).
- Markdown that keeps its shape. Headers keep their
#, fenced blocks keep their fences, inline code gets a subtle chip — and CJK/emoji wrap at correct character widths with an aligned gutter.
- A live viewport. The transcript is bottom-anchored; the tail is always visible. Busy state shows a braille spinner + compact elapsed timer (
Working 5s).
Learn more
Model routing (TokenDance)
The profile patch (cordis.patch.yml) routes llm-deepseek through the TokenDance gateway:
llm-deepseek:
apiKeyEnv: TOKENDANCE_API_KEY
baseURL: https://tokendance.space/gateway/v1
The provider is registered in ~/.dsh/settings.yaml (llm-pi-ai.providers.tokendance): OpenAI-compatible endpoint, thinkingFormat: deepseek, models deepseek-v4-flash (default) and deepseek-v4-pro. Switch models by editing the provider's models list or overriding llm-deepseek.model in your profile patch.
This is the beginning of the README. Read the rest at the original. Read the full README ↗
