kimi-webbridge-dsh 1.1.0 → 1.3.0

package/README.md

@@ -1,59 +1,53 @@
 # kimi-webbridge-dsh
 
-Kimi WebBridge 的 dsh 插件：通过本机 kimi-webbridge 守护进程（`127.0.0.1:10086`）驱动用户的真实浏览器（保留登录态）。
+Kimi WebBridge 的 dsh 插件：通过本机 kimi-webbridge 守护进程（`127.0.0.1:10086`）驱动用户的真实浏览器（保留登录态与 Cookie）。注册一个模型工具 `kimi_webbridge`，覆盖导航、点击、输入、读取页面（accessibility tree + @e 引用）、截图、JS 求值、CDP、网络、上传、PDF 导出、标签页与会话管理。
 
-注册一个模型工具 `kimi_webbridge`，覆盖导航、点击、输入、读取页面（accessibility tree + @e 引用）、截图、JS 求值、CDP、网络、上传、PDF 导出、标签页与会话管理。
+## 功能
 
-## 依赖
+| 能力 | 说明 |
+|---|---|
+| 浏览真实页面 | 在用户已登录的浏览器中导航、点击、填表、滚动 |
+| 读页面 | `snapshot` 返回 accessibility tree 与 `@e` 元素引用 |
+| 截图 / 导出 PDF | 结果写入本地文件，返回路径 |
+| JS 求值 / CDP | `evaluate`（页面上下文）、`cdp`（chrome.debugger 直通） |
+| 网络 / 上传 | 请求捕获与文件上传 |
+| 会话分组 | 一个任务 = 一个 session = 一个标签页组，可一键清理 |
 
-- Kimi WebBridge 守护进程已安装并运行（`irm https://cdn.kimi.com/webbridge/install.ps1 | iex`）
-- 浏览器扩展已连接（`kimi-webbridge status` 显示 `extension_connected: true`）
+## 依赖
 
-## 安装（一次性）
+- **浏览器扩展**：需安装并连接 Kimi WebBridge 浏览器扩展 —— 从 [Chrome Web Store](https://chromewebstore.google.com/detail/kimi-webbridge/fldmhceldgbpfpkbgopacenieobmligc) 安装（`kimi-webbridge status` 显示 `extension_connected: true`；扩展版本应与守护进程一致）。
+- **守护进程**：无需预装。插件在守护进程不可达时会自动启动它；二进制缺失时会自动从官方 CDN（cdn.kimi.com，与官方安装器同源）下载安装——全程无需手动运行任何安装命令。
 
-**方式 A：从 npm registry 安装（发布后）**
+## 安装（一次性，零手工配置）
 
 ```powershell
 dsh plugin --profile web add kimi-webbridge-dsh
 ```
 
-**方式 B：本地源码安装（开发时）**
+本包声明了 `dsh.bundle.patch`：`dsh plugin add` 会自动把它登记进 profile 的 bundle 层（`dsh.profile.bundles`），**无需手动编辑任何 cordis.patch.yml**。安装后重启一次 dsh web 即生效（bundle 在启动时加载）：
 
 ```powershell
-dsh plugin --profile web add E:\deepseek\kimi-webbridge-dsh
-```
-
-两种方式安装后，都需要把下面这段追加到 `~/.dsh/profiles/web/cordis.patch.yml`（用户补丁层，热重载生效，无需重启服务）：
-
-```yaml
-- insert:
-    - id: kimi-webbridge
-      name: kimi-webbridge-dsh
+dsh web
 ```
 
 ## 用法
 
 模型在新会话中可直接调用 `kimi_webbridge` 工具。核心规则：
 
-- **一个任务 = 一个 session = 一个标签页组**：任务开始时选一个 session 名，之后每次调用都带上。
+- **一个任务 = 一个 session = 一个标签页组**：任务开始时选一个 session 名，之后每次调用都带上（如 `camping-research`）。
 - **读页面用 snapshot**：返回 accessibility tree 和 `@e` 引用，点击/输入优先用 `@e` 引用而非手写 CSS。
 - **截图返回文件路径**：用 read 工具打开查看。
-- 守护进程不可达时工具会自动尝试启动它；若二进制缺失，会自动从官方 CDN（cdn.kimi.com，与官方安装器同源）下载并安装——**用户无需手动运行任何外部安装命令**。
+- **守护进程不可达**：工具会自动启动；二进制缺失时自动从官方 CDN 下载安装。
 
 ## 配置（可选）
 
-在 `cordis.patch.yml` 的插入行里加 `config:`：
+在 profile 的用户补丁层（`~/.dsh/profiles/web/cordis.patch.yml`）按 id 覆盖配置（替换整份 config，未给出的键取默认值）：
 
 ```yaml
-- insert:
-    - id: kimi-webbridge
-      name: kimi-webbridge-dsh
-      config:
-        baseUrl: http://127.0.0.1:10086
-        requestTimeoutMs: 120000
-        autoStartDaemon: true
-        autoInstallDaemon: true
-        daemonVersion: latest
+- id: kimi-webbridge
+  config:
+    autoInstallDaemon: false
+    daemonVersion: 0.3.0
 ```
 
 | 配置项 | 默认值 | 说明 |
@@ -61,7 +55,7 @@ dsh plugin --profile web add E:\deepseek\kimi-webbridge-dsh
 | `baseUrl` | `http://127.0.0.1:10086` | 守护进程地址 |
 | `requestTimeoutMs` | `120000` | 单次请求超时（毫秒） |
 | `autoStartDaemon` | `true` | 守护进程未运行时自动启动 |
-| `autoInstallDaemon` | `true` | 二进制缺失时自动从官方 CDN 下载安装（关闭后需手动运行 `irm https://cdn.kimi.com/webbridge/install.ps1 \| iex`） |
+| `autoInstallDaemon` | `true` | 二进制缺失时自动从官方 CDN 下载安装（关闭后需手动运行 `irm https://cdn.kimi.com/webbridge/install.ps1 | iex`） |
 | `daemonVersion` | `latest` | 自动安装时的版本（可固定如 `0.3.0`） |
 
 ## 移除
@@ -69,4 +63,5 @@ dsh plugin --profile web add E:\deepseek\kimi-webbridge-dsh
 ```powershell
 dsh plugin --profile web remove kimi-webbridge-dsh
 ```
-并把 `cordis.patch.yml` 里的插入行删掉。
+
+自动从 bundle 层移除（无需手动删补丁行），重启后生效。

package/cordis.patch.yml

@@ -0,0 +1,7 @@
+# kimi-webbridge-dsh bundle patch: applied automatically by the dsh profile
+# loader once this package is registered as a bundle via
+#   dsh plugin --profile <name> add kimi-webbridge-dsh
+# No manual cordis.patch.yml editing is required.
+- insert:
+    - id: kimi-webbridge
+      name: kimi-webbridge-dsh

package/lib/index.js

@@ -253,7 +253,13 @@ function canonicalResult(result) {
  * section in the system prompt.
  */
 function apply(ctx, config = {}) {
-  const { baseUrl, requestTimeoutMs, autoStartDaemon, autoInstallDaemon, daemonVersion } = config;
+  const {
+    baseUrl = "http://127.0.0.1:10086",
+    requestTimeoutMs = 120000,
+    autoStartDaemon = true,
+    autoInstallDaemon = true,
+    daemonVersion = "latest"
+  } = config;
 
   ctx.systemPrompt.section({
     name: "tool:kimi-webbridge",
@@ -263,7 +269,7 @@ function apply(ctx, config = {}) {
 
   ctx.tools.register(defineTool({
     name: "kimi_webbridge",
-    description: "Drive the user's real browser (with their login sessions) via the local kimi-webbridge daemon at " + baseUrl + ". The browser extension must be connected (status shows extension_connected). One task = one session = one tab group: pick a session name at the start of a task and pass it on every call. Actions: status (daemon + extension health); navigate {url, newTab?, group_title?} (first call opens a tab); find_tab {url, active?} (re-select a session tab, or borrow the user's active tab); snapshot (accessibility tree with @e refs — use it to read content and locate elements); click {selector} (@e ref or CSS); fill {selector, value} (inputs, textareas, and contenteditable editors; clear-and-insert); evaluate {code} (async JS in the page realm; wrap re-declarations in an IIFE; return compact JSON); cdp {method, params} (raw chrome.debugger passthrough); screenshot {format?, quality?, selector?, path?} (returns a file path — open it with the read tool to see it); network {cmd, filter?, requestId?}; upload {selector, files}; save_as_pdf {paper_format?, landscape?, scale?, print_background?, path?}; list_tabs; close_tab; close_session (only when the user asks to close the tabs). Prefer @e refs from snapshot over hand-written CSS selectors. When the daemon is unreachable the plugin starts it automatically; if the daemon binary is missing it is downloaded from the official Kimi CDN (config autoInstallDaemon:false disables this).",
+    description: "Drive the user's real browser (with their login sessions) via the local kimi-webbridge daemon at " + baseUrl + ". The browser extension must be connected (status shows extension_connected). One task = one session = one tab group: pick a session name at the start of a task and pass it on every call. Actions: status (daemon + extension health); navigate {url, newTab?, group_title?} (first call opens a tab); find_tab {url, active?} (re-select a session tab, or borrow the user's active tab); snapshot (accessibility tree with @e refs — use it to read content and locate elements); click {selector} (@e ref or CSS); fill {selector, value} (inputs, textareas, and contenteditable editors; clear-and-insert); evaluate {code} (async JS in the page realm; wrap re-declarations in an IIFE; return compact JSON); cdp {method, params} (raw chrome.debugger passthrough); screenshot {format?, quality?, selector?, path?} (returns a file path — open it with the read tool to see it); network {cmd, filter?, requestId?}; upload {selector, files}; save_as_pdf {paper_format?, landscape?, scale?, print_background?, path?}; list_tabs; close_tab; close_session (only when the user asks to close the tabs). Prefer @e refs from snapshot over hand-written CSS selectors. When the daemon is unreachable the plugin starts it automatically; if the daemon binary is missing it is downloaded from the official Kimi CDN (config autoInstallDaemon:false disables this). Limits: sites that strictly check event.isTrusted (some banking portals, captchas) ignore click/fill — tell the user the page needs manual interaction; cross-origin iframes are not covered by fill/click/snapshot/evaluate — navigate to the iframe URL directly; if an error says 'Please update the Kimi WebBridge extension', the extension is outdated — ask the user to update it and retry.",
     parameters: {
       action: {
         type: "string",

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "kimi-webbridge-dsh",
   "description": "Kimi WebBridge plugin for dsh: drive the user's real browser (their login sessions) through the local kimi-webbridge daemon at 127.0.0.1:10086. Registers a single kimi_webbridge tool covering navigate, click, fill, snapshot, screenshot, evaluate, cdp, network, upload, save_as_pdf, tab and session management.",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "license": "MIT",
   "type": "module",
   "keywords": [
@@ -24,9 +24,15 @@
     },
     "./package.json": "./package.json"
   },
+  "dsh": {
+    "bundle": {
+      "patch": "./cordis.patch.yml"
+    }
+  },
   "files": [
     "lib/index.js",
-    "README.md"
+    "README.md",
+    "cordis.patch.yml"
   ],
   "dependencies": {
     "@deepseek-ai/schemastery": "^3.18.1",