dsh-plugin-window-input

A self-contained DeepSeek Harness plugin that lets the agent attach to a window on the local Windows desktop and type text into it — no core modifications needed.

Load it into a stock DSH via --patch. Works on Windows only.

What you get

Tool	What it does
window_list	Enumerate visible top-level windows (title, class, process name, hwnd), optionally filtered by a query.
window_focus	Bring a window to the foreground by title (substring) or hwnd.
window_type	Type text into a window's input control — the control is auto-detected (focused control → UI Automation → Scintilla → SendInput).

Example flows

window_list                    → find the "Notepad" window
window_type title="Notepad" text="hello" pressEnter=true

How window_type finds the input box

Typing into a window needs more than its top-level handle — it needs the control that is waiting for keyboard input. The engine resolves it in layers:

1. Focused control — GetGUIThreadInfo returns the thread's focused child, the authoritative keyboard target. Works for any app.
2. UI Automation ValuePattern — for standard controls (Notepad, editors, chat inputs) it sets the value directly, no focus needed.
3. Scintilla editors (Notepad++, many code editors) — text is inserted cross-process via clipboard + SCI_PASTE (pointer-free and safe; the pointer-based SCI_REPLACESEL/SCI_INSERTTEXT do NOT work cross-process).
4. SendInput (opt-in method="sendinput") — for terminals/apps that only accept keyboard injection. Some environments (remote desktop, security software, restricted tokens) block synthetic input injection.

pressEnter inserts a newline via \n (UI Automation) or SCI_NEWLINE (Scintilla), so it works even where SendInput is blocked.

Requirements

• Windows
• A DeepSeek Harness checkout (pnpm dsh web)

Installation

# 1. clone this repo anywhere
git clone https://github.com/linxsy-code/dsh-plugin-window-input.git

# 2. edit cordis.yml — point name at YOUR clone path (a file:// URL)
#    e.g.  name: 'file:///C:/path/to/dsh-plugin-window-input/src/index.ts'

# 3. from the DeepSeek Harness checkout root:
pnpm dsh web --patch 
/cordis.yml

Open http://127.0.0.1:3080. In a new session, ask the agent e.g. "use window_type to type 'hello' into Notepad and press Enter" — or if you also use the @ window menu, pick a window with @窗口.

Files

• src/index.ts — the plugin (registers the three tools, spawns win-agent.ps1).
• win-agent.ps1 — the engine (Win32 P/Invoke + UI Automation + Scintilla messages, emits JSON).
• cordis.yml — the --patch overlay.

Known limitations

• SendInput may be blocked in remote-desktop / sandboxed / restricted-token environments (Win32 error 87) — prefer the default UI Automation / Scintilla paths.
• UI Automation SetValue only reaches controls that expose ValuePattern; canvas-only or exotic controls fall back to the focused-control path.
• Windows only.

@窗口 mention (optional, requires the fork)

A companion feature adds a 窗口 (Windows) category to the @ mention menu in the DSH Web composer: type @, pick a window, and it inserts @窗口 that the agent resolves through window_type. Because it touches the client Remote assembly, it lives in a fork of DSH rather than a --patch plugin:

https://github.com/linxsy-code/deepseek-harness   (branch master)

License

MIT © 2026 linxs

---

dsh-plugin-window-input（中文）

让 DeepSeek Harness 的 Agent 能「附着到某个 Windows 窗口并往里输入文字」，无需改动核心代码。

工具

• window_list：枚举可见顶层窗口（标题/类名/进程/hwnd），可按关键字过滤。
• window_focus：按标题（子串）或 hwnd 把窗口切到前台。
• window_type：向窗口输入文字，自动识别输入框（焦点控件 → UI Automation → Scintilla → SendInput）。

安装

git clone https://github.com/linxsy-code/dsh-plugin-window-input.git
# 编辑 cordis.yml，把 name 改成你本机克隆路径（file:// URL）
cd 
pnpm dsh web --patch /cordis.yml

打开 http://127.0.0.1:3080，新会话里 Agent 就能用 window_list / window_focus / window_type。

已知限制

• SendInput 在远程桌面/受限令牌等环境下可能被拦截（Win32 87），请用默认的 UIA/Scintilla 路径。
• 仅支持 Windows。

@窗口 提及（可选，需 fork）

配套功能可在 @ 弹出菜单里加「窗口」类别列出所有窗口、选中插入 @窗口 供 Agent 解析。因涉及客户端 Remote 装配，只提供在 fork 里：github.com/linxsy-code/deepseek-harness（master 分支）。