browser-pilot-cli - npm Package Compare versions

Comparing version 0.1.0 to 0.1.1

playwright.config.ts

+import { defineConfig } from '@playwright/test';
+
+export default defineConfig({
+  testDir: './tests',
+  timeout: 30_000,
+  retries: 0,
+  workers: 1, // bp uses a single browser session — must be serial
+  globalSetup: './tests/global-setup.ts',
+  globalTeardown: './tests/global-teardown.ts',
+  use: {
+    baseURL: 'http://127.0.0.1:18274',
+  },
+  webServer: {
+    command: 'node tests/server.mjs 18274',
+    port: 18274,
+    reuseExistingServer: true,
+  },
+  projects: [
+    {
+      name: 'core',
+      testMatch: /core\.spec/,
+    },
+    {
+      name: 'compat',
+      testMatch: /fill|click|snapshot/,
+    },
+    {
+      name: 'network',
+      testMatch: /network\.spec/,
+    },
+    {
+      name: 'integration',
+      testMatch: /real-site\.spec/,
+    },
+  ],
+});

test-results/.last-run.json

+{
+  "status": "passed",
+  "failedTests": []
+}

dist/cli.js

@@ -248,2 +248,10 @@ #!/usr/bin/env node
 }`;
+var IS_CONTENTEDITABLE = `function() {
+  return this.isContentEditable && !(this instanceof HTMLInputElement) && !(this instanceof HTMLTextAreaElement);
+}`;
+var CONTENTEDITABLE_CLEAR = `function() {
+  this.focus();
+  document.execCommand('selectAll');
+  document.execCommand('delete');
+}`;
 var PAGE_INFO = `JSON.stringify({title:document.title,url:location.href})`;
@@ -435,2 +443,13 @@ var PAGE_DIMENSIONS = `JSON.stringify({
 ]);
+var ALLOW_EMPTY_NAME = /* @__PURE__ */ new Set([
+  "textbox",
+  "searchbox",
+  "combobox",
+  "listbox",
+  "checkbox",
+  "radio",
+  "spinbutton",
+  "slider",
+  "switch"
+]);
 function saveRefs(targetId, entries) {
@@ -471,12 +490,16 @@ writeFileSync2(REFS_FILE, JSON.stringify({ targetId, entries }), { mode: 384 });
       const role = node.role?.value;
-      if (role && INTERACTIVE_ROLES.has(role) && node.backendDOMNodeId !== void 0) {
-        const props = Object.fromEntries(
-          (node.properties || []).map((p) => [p.name, p.value?.value])
-        );
+      const props = Object.fromEntries(
+        (node.properties || []).map((p) => [p.name, p.value?.value])
+      );
+      const isEditable = props.editable === "richtext";
+      const isInteractive = role && (INTERACTIVE_ROLES.has(role) || isEditable);
+      if (isInteractive && node.backendDOMNodeId !== void 0) {
         const name = node.name?.value || "";
         const value = node.value?.value;
-        if (!props.disabled && (name || value) && refs.length < limit) {
+        const effectiveRole = isEditable && role === "generic" ? "textbox" : role;
+        const hasIdentity = name || value || ALLOW_EMPTY_NAME.has(effectiveRole) || isEditable;
+        if (!props.disabled && hasIdentity && refs.length < limit) {
           const checked = props.checked === "true" || props.checked === true ? true : void 0;
-          refs.push({ backendNodeId: node.backendDOMNodeId, role, name });
-          elements.push({ ref: refs.length, backendNodeId: node.backendDOMNodeId, role, name, value, checked });
+          refs.push({ backendNodeId: node.backendDOMNodeId, role: effectiveRole, name });
+          elements.push({ ref: refs.length, backendNodeId: node.backendDOMNodeId, role: effectiveRole, name, value, checked });
         }
@@ -753,7 +776,32 @@ }
     try {
-      await transport.send("Runtime.callFunctionOn", {
+      const { result: ceResult } = await transport.send("Runtime.callFunctionOn", {
         objectId,
-        functionDeclaration: SET_VALUE,
-        arguments: [{ value: text }, { value: !!opts.clear }]
+        functionDeclaration: IS_CONTENTEDITABLE,
+        returnByValue: true
       }, sessionId);
+      if (ceResult.value) {
+        if (opts.clear) {
+          await transport.send("Runtime.callFunctionOn", {
+            objectId,
+            functionDeclaration: CONTENTEDITABLE_CLEAR
+          }, sessionId);
+        } else {
+          await transport.send("Runtime.callFunctionOn", {
+            objectId,
+            functionDeclaration: `function() {
+                this.focus();
+                const sel = window.getSelection();
+                sel.selectAllChildren(this);
+                sel.collapseToEnd();
+              }`
+          }, sessionId);
+        }
+        await transport.send("Input.insertText", { text }, sessionId);
+      } else {
+        await transport.send("Runtime.callFunctionOn", {
+          objectId,
+          functionDeclaration: SET_VALUE,
+          arguments: [{ value: text }, { value: !!opts.clear }]
+        }, sessionId);
+      }
       if (opts.submit) await dispatchKey(transport, sessionId, "Enter");
@@ -760,0 +808,0 @@ } finally {

package.json

 {
   "name": "browser-pilot-cli",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "CLI tool to control your browser via Chrome DevTools Protocol",
@@ -14,3 +14,5 @@ "type": "module",
     "start": "node dist/cli.js",
-    "test": "bash tests/run.sh"
+    "test": "tsup && npx playwright test --project core --project compat --project network",
+    "test:integration": "tsup && npx playwright test --project integration",
+    "test:all": "tsup && npx playwright test"
   },
@@ -22,2 +24,3 @@ "dependencies": {
   "devDependencies": {
+    "@playwright/test": "^1.59.1",
     "@types/node": "^22.0.0",
@@ -24,0 +27,0 @@ "@types/ws": "^8.5.0",

README.md

 # browser-pilot
 
-CLI tool that gives LLM agents control of your real browser — with your logins, cookies, and extensions intact.
+Give your AI agent control of your real browser — with your logins, cookies, and extensions intact. No extension needed.
 
 ```bash
-bp open https://github.com       # navigate — returns interactive elements
-bp click 3                        # click [3] — returns updated page
-bp type 5 "hello" --submit        # type + Enter — returns updated page
-bp eval "document.title"          # run any JavaScript
+npm install -g browser-pilot-cli
 ```
 
+## Agent Setup
+
+### 1. Enable Chrome remote debugging (one-time)
+
+Open `chrome://inspect/#remote-debugging` in Chrome (144+) and click Allow. No command-line flags, no restart needed.
+
+> Chrome 136 disabled the old `--remote-debugging-port` flag for security. Chrome 144 introduced this new UI toggle as the replacement — browser-pilot uses this.
+
+### 2. Install the plugin for your agent
+
+**Claude Code:**
+```
+/plugin marketplace add https://github.com/relixiaobo/browser-pilot.git
+/plugin install browser-pilot@browser-pilot-marketplace
+```
+
+**Codex CLI:**
+```bash
+npx skills add relixiaobo/browser-pilot
+```
+
+**OpenClaw:**
+```bash
+cp -r plugin/skills/browser-pilot ~/.agents/skills/
+```
+
+**Cursor / VS Code Copilot:**
+```bash
+npx skills add relixiaobo/browser-pilot
+```
+
+### 3. Use it
+
+Just tell your agent what you want to do:
+
+- "Open GitHub and check my notifications"
+- "Go to Hacker News and summarize the top 5 posts"
+- "Fill out the form on this page"
+
+The agent will use `bp` commands automatically. Your real login sessions are preserved — no need to re-authenticate.
+
+## Why browser-pilot?
+
+- **No extension required** — Uses Chrome 144's native remote debugging toggle, not the Extension Debugger API
+- **Real login sessions** — Operates your actual browser profile. Cookies, extensions, logins all intact
+- **CLI-native** — Any agent with bash access can use it. No MCP protocol, no SDK integration needed
+- **Auto-snapshot** — Every action returns page state with numbered `[ref]` elements, so the agent always knows what's on screen
+- **Lightweight** — 78KB npm package. No bundled Chromium (unlike Playwright's 400MB+)
+
 ## Comparison
@@ -18,54 +64,15 @@
 | **Login session reuse** | Yes | No | Depends | Yes |
+| **Extension required** | No | No | No | No |
 | **Element refs** | Numbered (accessibility tree) | Named refs (ARIA) | CSS selectors | Numbered (DOM) |
 | **Auto-snapshot after action** | Yes | Yes | No | Yes |
 | **Network interception** | Yes (block/mock/headers) | Yes | Yes | No |
-| **Drag and drop** | No | Yes | Yes | No |
-| **Mobile emulation** | No | Yes | Yes | Yes |
 | **Multi-browser** | Chromium-only | Chromium + Firefox + WebKit | Chromium-only | Chromium-only |
-| **Connection model** | Daemon (one-time Allow) | MCP server | MCP server | Python process |
 | **Dialog auto-handling** | Yes | Yes | No | Yes |
 | **JSON output** | Default | MCP structured | MCP structured | Python objects |
-| **Visual indicator** | Pulsing glow | None | None | None |
 | **File upload** | Auto-detect input | Yes | No | Yes |
-| **Autonomous agent** | No (tool, not agent) | No (tool) | No (tool) | Yes (plans + executes) |
 
-**browser-pilot is best when:**
-- You need your existing login sessions (paywalled content, internal tools)
-- Your LLM has bash access but no MCP support
-- You want every action to return page state automatically
-
-**Use Playwright MCP when:**
-- You need multi-browser or mobile emulation
-- Your LLM supports MCP natively
-- You don't need existing login sessions
-
-**Use browser-use when:**
-- You want an autonomous agent that plans and executes multi-step tasks
-- You're building in Python
-
-## Quick Start
-
-```bash
-# Install
-npm install -g browser-pilot
-
-# Enable debugging in Chrome (one-time)
-# Open chrome://inspect/#remote-debugging → toggle ON
-
-# Connect (click Allow in Chrome's dialog)
-bp connect
-
-# Use
-bp open https://github.com
-bp click 3
-bp type 5 "hello" --submit
-bp eval "document.title"
-bp screenshot page.png
-bp disconnect
-```
-
 ## How It Works
 
 ```
-LLM (bash tool)
+Agent (bash tool)
   │  bp open / bp click / bp eval ...
@@ -75,15 +82,13 @@ ▼
                                            │
-                                           │  WebSocket (CDP, one-time Allow)
+                                           │  WebSocket (CDP)
                                            ▼
                                        Chrome (your browser, your profile)
                                        ├── Your windows (untouched)
-                                       └── Pilot window (bp operates here)
+                                       └── Pilot window (agent operates here)
 ```
 
-The daemon maintains a single CDP WebSocket connection. Chrome's "Allow" dialog appears once per session. A pulsing blue glow around the Pilot window indicates the agent is active.
+The daemon maintains a single CDP WebSocket connection. A pulsing blue glow around the Pilot window indicates the agent is active.
 
 ## Commands
 
-Run `bp --help` for full details including workflow, refs, and eval examples.
-
 ### Core Loop
@@ -227,5 +232,5 @@
 
-- Chrome / Chromium / Edge / Brave (any Chromium-based browser)
+- Chrome 144+ / Edge / Brave (any Chromium-based browser)
 - Node.js >= 18
-- Chrome remote debugging enabled (`chrome://inspect/#remote-debugging`)
+- Remote debugging enabled (`chrome://inspect/#remote-debugging`)
 
@@ -232,0 +237,0 @@ ## License

New alerts

AI-detected potential code anomaly

Supply chain risk

AI has identified unusual behaviors that may pose a security risk.

URL strings

Supply chain risk

Package contains fragments of external URLs or IP addresses, which the package may be accessing at runtime.

Fixed alerts

AI-detected potential code anomaly

Supply chain risk

AI has identified unusual behaviors that may pose a security risk.

Found 2 instances

URL strings

Supply chain risk

Package contains fragments of external URLs or IP addresses, which the package may be accessing at runtime.

Improved metrics

Total package byte prevSize

292782

0.97%

Number of package files

8

33.33%

Lines of code

2566

3.47%

Number of lines in readme file

237

2.16%

Number of low supply chain risk alerts

13

-7.14%

Worsened metrics

Dev dependency count

5

25%

No dependency changes