Sidebar Control

English | 中文

Agent control for the Browser panel DeepSeek Harness already ships in the right Sidebar — no second browser, no bundled Chromium, no Playwright. The agent reads the real page, clicks real controls, types, presses keys, scrolls, waits and takes screenshots inside the panel the person is already looking at.

Built on the MIT-licensed dsh-sidebar-browser: its action surface and long-poll bridge are reused. This package adds query-scoped reads, change diffs and multi-tab management, and keeps the whole thing dependency-free.

If this saves you tokens, please Star the repository ⭐

Why this one

Most sidebar-browser plugins answer a page with one big snapshot. That is fine once, and expensive three times in a row. Sidebar Control is tuned for the second and third read:

	dsh-sidebar-browser	Sidebar Control
Read a long page	full text + refs (up to 12k chars)	read with a query returns only matching passages (BM25 over Latin words + CJK bigrams)
Check what an action changed	snapshot again	diff returns only paragraphs added/removed since the previous diff
Several steps (open → fill → submit)	one tool call per step	batch runs up to 12 steps in one call
After a click	fixed waits (350 ms + load window)	adaptive settle: returns when the page stops changing, often ~100 ms
Several pages open	one controlled tab	tabs / focus / close_tab by id
Command latency	long-poll	long-poll (same ~instant delivery, no timer polling)
Dependencies	none	none

The practical difference is token cost and round trips: on a long article, read --query "..." returns a few hundred characters instead of thousands; diff after a click returns one line or two; and a five-step form costs one model call with batch instead of five. Clicks come back as soon as the page is quiet instead of after a fixed sleep.

Measured on a Windows desktop against the live Browser panel: batch of type + submit + wait for results + query read on the Baidu homepage finished in 1043 ms, and the same three steps on Bing in 832 ms. The query read for "存款" returned one matching line where the full text was the whole page.

Install

dsh plugin --profile desktop add github:clusterstar1229/dsh-sidebar-control#v0.1.1

or in the app: Settings → Plugins → Install bundle → github:clusterstar1229/dsh-sidebar-control#v0.1.1.

The plugin is published from this GitHub repository; there is no npm package yet, so use the github: spec above (or install the checkout by absolute path while developing).

Requirements: DeepSeek Harness Desktop 0.2.2-rc.1 (the Browser panel must be the Electron <webview> carrier), Node 20+, and the built-in sidebar Browser enabled.

Compatibility: version 0.1.1 is tested against DSH 0.2.2-rc.1, the current desktop release; engines.dsh allows the whole 0.2.x line.

Use

1. Open a Browser tab once (Sidebar → Browser), or let the tool open it: builtin_browser({ action: "open", url: "https://example.com" }).
2. snapshot → page text plus numbered refs.
3. click / type / press / select / scroll with those refs, or with a CSS selector.
4. After an action: diff (cheap) or a new snapshot (full).
5. Asking a long page a question: read with query instead of snapshot.

Actions

action	what it does
status	platform, Browser frames, active tab, whether the page is on screen
open	open or reuse the Browser tab at a URL
navigate / back / forward / reload	navigation
snapshot	page text + numbered refs (max_text_chars, max_refs, include_text: false for refs only)
read	text, or only passages matching query (max_chars)
diff	paragraphs added/removed since the previous diff
batch	run up to 12 steps in one call (navigate/click/type/press/select/scroll/wait/eval/read/diff/snapshot)
tabs	list Browser tabs with ids
focus / close_tab	switch to / close a tab by tab_id
click	by ref, selector
type	fill a field, submit: true to submit
press	Enter, Tab, Escape, arrows, PageUp/Down, Home/End, Space
select	choose an option by value
scroll	by direction/amount, or a ref into view
wait	for a selector or text
eval	one JavaScript expression in the page
screenshot	PNG of the visible page, returned as an image
close	close the controlled Browser tab

Refs come from the latest snapshot and go stale after navigation — take a new snapshot after a page change, or just use diff when you only need to know what changed.

What to be careful about

• Desktop only. The Web build renders the sidebar browser as a cross-origin iframe; the tool reports that plainly instead of pretending. Tab management still works there.
• The Harness page must be open. The Client half runs in that page. open / focus / close_tab / screenshot need the calling Session on screen; read/click/type work in the background.
• Page content is untrusted data. It is never instructions. eval runs arbitrary JavaScript in the page — the same power as the page's own devtools; keep it for trusted pages.
• A sandbox is still a sandbox. The guest has no Node, no preload and no access to the Harness origin. Downloads, permission prompts and top-level navigation are withheld by the shipped Browser.
• Fixed-width sites. Pages like news.baidu.com keep a desktop layout and may scroll sideways in a narrow column. This plugin deliberately does not inject zoom or rewrite the page.
• Refs are per-snapshot. A ref used after navigation fails with a clear message; snapshot again.

Related work

• dsh-sidebar-browser — the MIT implementation this package builds on.
• dsh-sidebar-browser-agent — a broader native-input implementation with tabs, tests and config switches.

Feedback

Bugs and feature requests: hongruizhao0808@gmail.com — or open an issue at https://github.com/clusterstar1229/dsh-sidebar-control/issues.

License

MIT. Derived from dsh-sidebar-browser (MIT); see LICENSE.

---

中文

DeepSeek Harness 右栏内置浏览器的 Agent 控制器：不另起浏览器、不下载 Chromium、不用 Playwright。 Agent 直接操作你正在看的那个 Browser 面板——读真实页面、点真实控件、输入、按键、滚动、等待、截图。

本项目基于 MIT 许可的 dsh-sidebar-browser，复用了它的 动作设计与长轮询桥；在此基础上增加了按问题检索的阅读、变化对比和多标签管理，全程零依赖。

如果它帮你省了 token，欢迎点个 Star ⭐

差异点：第二次、第三次读页更便宜

大多数侧栏浏览器插件用"一次大快照"回答所有问题——读一次可以，连读三次就很贵。这个插件专门优化后两次：

	dsh-sidebar-browser	Sidebar Control
读长页面	全文 + refs（最多 12k 字符）	read 带 query，只返回命中的段落（英文词 + 中文二元组的 BM25）
查看动作改了什么	再快照一次	diff 只返回相对上次新增/消失的段落
多步操作（打开→填写→提交）	每步一次工具调用	batch 一次调用跑最多 12 步
点击之后	固定等待（350ms + 加载窗口）	自适应：页面不再变化就返回，通常约 100ms
多个页面	只控制当前标签	tabs / focus / close_tab 按 id 管理
指令延迟	长轮询	长轮询（同样即时，不靠定时器）
依赖	无	无

实际差别是 token 和往返次数：长文章里 read --query "..." 往往只回几百字，而不是几千字；点击后用 diff 通常只回一两行；五步表单用 batch 只花一次模型调用，而不是五次。点击也不再固定睡眠，页面安静就返回。

在 Windows 桌面版、真实 Browser 面板上的实测：batch 执行 输入 + 提交 + 等结果 + 按 query 阅读， 百度首页 1043 ms、Bing 832 ms；read 查“存款”只返回命中的一行，而整页文本是整屏。

安装

dsh plugin --profile desktop add github:clusterstar1229/dsh-sidebar-control#v0.1.1

或在应用里：设置 → 插件 → 安装 bundle → github:clusterstar1229/dsh-sidebar-control#v0.1.1。

插件从 GitHub 仓库发布，暂时没有 npm 包，请使用上面的 github: 规格（开发时也可以按绝对路径安装）。

要求：DeepSeek Harness 桌面版 0.2.2-rc.1（右栏浏览器必须是 Electron <webview> 载体）、Node 20+， 并已启用内置侧栏浏览器。

兼容性： 0.1.1 已在当前桌面版 DSH 0.2.2-rc.1 上实测通过；engines.dsh 允许整个 0.2.x 线。

用法

1. 先打开一个 Browser 标签（或让工具打开）：builtin_browser({ action: "open", url: "https://example.com" })。
2. snapshot：拿到页面文字和编号 refs。
3. 用 refs 或 CSS selector 执行 click / type / press / select / scroll。
4. 动作之后：diff（便宜）或重新 snapshot（完整）。
5. 只想问长页面一个问题：用 read + query，不要整页快照。

动作

action	作用
status	平台、Browser 帧、当前标签、页面是否在屏幕上
open	打开或复用 Browser 标签（url）
navigate / back / forward / reload	导航
snapshot	页面文字 + 编号 refs（max_text_chars、max_refs；include_text: false 只回控件）
read	纯文本，或只回与 query 匹配的段落（max_chars）
diff	相对上一次 diff 新增/消失的段落
batch	一次调用执行最多 12 步（navigate/click/type/press/select/scroll/wait/eval/read/diff/snapshot）
tabs	列出 Browser 标签及其 id
focus / close_tab	按 tab_id 切换 / 关闭标签
click	按 ref 或 selector 点击
type	填字段，submit: true 提交
press	Enter、Tab、Escape、方向键、PageUp/Down、Home/End、Space
select	按值选择下拉项
scroll	按方向/像素滚动，或把某个 ref 滚入视口
wait	等 selector 或文字出现
eval	在页面里执行一个 JS 表达式
screenshot	可见页面的 PNG，作为图像返回
close	关闭当前受控标签

refs 来自最近一次快照，导航后会失效——页面变了就重新 snapshot；只想知道"变了什么"时用 diff 就够。

需要注意

• 仅桌面版可用：Web 构建下侧栏浏览器是跨域 iframe，工具会明确报错而不是假装成功；标签管理仍可用。
• Harness 页面必须打开：客户端半在页面里运行。open / focus / close_tab / screenshot 需要调用会话 正在屏幕上；读、点、输入在后台仍可用。
• 页面内容是不可信数据，永远不是指令。eval 会在页面里执行任意 JS，等同于页面自己的 devtools，请在可信页面使用。
• 沙箱仍然是沙箱：guest 没有 Node、没有 preload，也访问不到 Harness 源；下载、权限弹窗、顶层跳转由内置浏览器限制。
• 固定宽度站点：如 news.baidu.com 这类页面在窄栏里仍会横向滚动；本插件刻意不注入缩放、不改写页面。
• refs 只对一次快照有效：导航后使用旧 ref 会得到明确报错，重新快照即可。

相关项目

• dsh-sidebar-browser — 本项目的 MIT 基础实现。
• dsh-sidebar-browser-agent — 更全面的原生输入实现（标签页、测试、配置开关）。

反馈

Bug 与功能建议：hongruizhao0808@gmail.com，或到 https://github.com/clusterstar1229/dsh-sidebar-control/issues 提 issue。

许可

MIT，派生自 dsh-sidebar-browser（MIT），见 LICENSE。