dsh-terminal-vision
适用于 DeepSeek Harness 的终端语义视觉插件：基于 @xterm/headless 提供带结构化屏幕模型（文本、光标、活动行）的持久 PTY 会话，使代理能够操作类似 vim/htop/lazygit 的交互式 TUI 程序，而不是读取原始字节流。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:fdfdfdfgbfdgfdg-star/dsh-terminal-vision#2e1763a69a5caebe19cc3919193ae12926a17a7aTerminal Vision 以 dsh-terminal-vision 发布，当前版本为 0.1.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
Terminal semantic vision plugin for DeepSeek Harness (DSH).
Gives the agent "semantic vision" over interactive terminal programs — vim, htop, lazygit, less, setup TUIs — instead of a raw escape-sequence byte stream. Every PTY session is continuously parsed by @xterm/headless (the headless JS port of xterm.js) into a structured screen model: visible text lines, cursor position, active line. The agent can then read the screen, send keys, read again — a perception/action loop over any TUI.
| Tool | Purpose |
|---|---|
terminal_open(session_name, shell?, cwd?, cols?, rows?) | Open a persistent PTY session, returns session_id. shell may be a shell name (bash, pwsh, cmd) or a TUI program to run directly (htop, vim file.txt). |
terminal_get_screen(session_id) | Structured screen model: lines[], cursor {x, y}, active_line, terminal title. |
terminal_send_keys(session_id, keys, wait_ms?) | Send a key sequence and wait for the screen to change (readiness wait, default 500 ms), then return the new screen. Accepts plain text, named keys (Enter, Esc, Up…), modifiers (Ctrl+C, Alt+b), space-separated sequences (":wq Enter"). |
terminal_read_output(session_id, lines?) | Last N lines of the scrollback buffer (history above the viewport). |
terminal_close(session_id) | Close the session and free the PTY. |
terminal_list_sessions() | List active sessions with id, name, shell, cwd, alive status. |
src/) — Cordis plugin: apply(ctx) registers the tools on ctx.tools, manages persistent sessions via node-pty (prebuilt ConPTY binaries on Windows — no compiler needed).src/screen-model.ts) — Variant A: @xterm/headless builds the screen model natively in Node. Raw PTY output is written into a headless xterm Terminal; the buffer is read out on demand (buffer.active, translateToString). No Python, no long-lived bridge process, works offline.encodeKeys() (friendly names → terminal bytes, including Ctrl/Alt modifiers, arrows, F-keys).terminal_send_keys, the tool waits until the screen revision changes (data arrives) or the timeout elapses — preventing "blind" sends.# from a local checkout
dsh plugin --profile web add file:./dsh-terminal-vision
# or from GitHub
dsh plugin --profile web add github:fdfdfdfgbfdgfdg-star/dsh-terminal-vision
Windows note: pnpm blocks native-module install scripts by default. If the
add step fails with ERR_PNPM_IGNORED_BUILDS: node-pty, run the blocked build
step manually (node-pty ships prebuilt ConPTY binaries — no compiler needed):
cd ~/.dsh/profiles/web
pnpm rebuild node-pty # runs the postinstall that copies conpty.dll
Then restart DSH (relaunch the DeepSeek Harness app, or re-run dsh --profile web)
and check the boot log for:
[terminal-vision] loaded: tools=6
Verify in a chat: "Какие инструменты терминала тебе доступны?" — the agent
should list the six terminal_* tools.
The package declares a dsh.bundle.patch (cordis.patch.yml), so dsh plugin add wires the plugin into the profile automatically — no manual cordis.patch.yml edits needed.
terminal_open(session_name="htop", shell="htop") → session_id
terminal_get_screen(session_id) → lines[] of the htop interface, cursor
terminal_send_keys(session_id, "F10") → quit htop, new screen
terminal_close(session_id)
Driving a shell:
terminal_open(session_name="work", shell="bash")
terminal_send_keys(session_id, "ls -la\n")
terminal_get_screen(session_id) → the ls output
terminal_read_output(session_id, lines=200) → anything that scrolled off
npm install
npm run build # tsc → lib/
npm test # node --test test/integration.test.js
lib/ (compiled JS) is committed, so a plain dsh plugin add needs no build step.
node-pty ^1.1.0 — ships prebuilt Windows ConPTY binaries; no Visual Studio Build Tools required on Windows 11@xterm/headless ^6.0.0 — pure JS, no native codecursorHidden is advisory (xterm.js does not expose the DECTCEM state); most TUIs keep the cursor visible.Alt+<letter> sends ESC-prefixed bytes (application keypad mode not negotiated per-program).cmd.exe (ConPTY); bash works if Git Bash / WSL bash is on PATH.