Patch anti-bot-detection/stealth-mode into playwright browser

examples/browser_tool_example.py

@@ -48,6 +48,14 @@ async def test_browser_tool():
     logger.info("Testing Browser Tool...")
 
     try:
+        # Test 0: Take a screenshot (pre-init)
+        logger.info("Test 0: Taking a screenshot...")
+        screenshot_bytes = await browser.screenshot()
+        screenshot_path = Path(__file__).parent / "browser_screenshot_init.png"
+        with open(screenshot_path, "wb") as f:
+            f.write(screenshot_bytes)
+        logger.info(f"Screenshot captured: {len(screenshot_bytes)} bytes")
+
         # Test 1: Visit a URL
         logger.info("Test 1: Visiting a URL...")
         result = await browser.visit_url("https://www.trycua.com")
@@ -56,6 +64,22 @@ async def test_browser_tool():
         # Wait a bit for the page to load
         await asyncio.sleep(2)
 
+        # Test 2: Take a screenshot
+        logger.info("Test 2: Taking a screenshot...")
+        screenshot_bytes = await browser.screenshot()
+        screenshot_path = Path(__file__).parent / "browser_screenshot.png"
+        with open(screenshot_path, "wb") as f:
+            f.write(screenshot_bytes)
+        logger.info(f"Screenshot captured: {len(screenshot_bytes)} bytes")
+
+        # Wait a bit
+        await asyncio.sleep(1)
+
+        # Test 3: Visit bot detector
+        logger.info("Test 3: Visiting bot detector...")
+        result = await browser.visit_url("https://bot-detector.rebrowser.net/")
+        logger.info(f"Visit URL result: {result}")
+
         # Test 2: Web search
         logger.info("Test 2: Performing a web search...")
         result = await browser.web_search("Python programming")

libs/python/agent/agent/tools/browser_tool.py

@@ -114,3 +114,22 @@ class BrowserTool:
             Response dictionary with success status and current URL
         """
         return await self._execute_command("web_search", {"query": query})
+
+    async def screenshot(self) -> bytes:
+        """
+        Take a screenshot of the current browser page.
+
+        Returns:
+            Screenshot image data as bytes (PNG format)
+        """
+        import base64
+
+        result = await self._execute_command("screenshot", {})
+        if result.get("success") and result.get("screenshot"):
+            # Decode base64 screenshot to bytes
+            screenshot_b64 = result["screenshot"]
+            screenshot_bytes = base64.b64decode(screenshot_b64)
+            return screenshot_bytes
+        else:
+            error = result.get("error", "Unknown error")
+            raise RuntimeError(f"Failed to take screenshot: {error}")

libs/python/computer-server/computer_server/browser.py

@@ -109,6 +109,33 @@ class BrowserManager:
                     # Removed --kiosk to allow desktop visibility
                 )
 
+                # Add init script to make the browser less detectable
+                await self.context.add_init_script(
+                    """const defaultGetter = Object.getOwnPropertyDescriptor(
+      Navigator.prototype,
+      "webdriver"
+    ).get;
+    defaultGetter.apply(navigator);
+    defaultGetter.toString();
+    Object.defineProperty(Navigator.prototype, "webdriver", {
+      set: undefined,
+      enumerable: true,
+      configurable: true,
+      get: new Proxy(defaultGetter, {
+        apply: (target, thisArg, args) => {
+          Reflect.apply(target, thisArg, args);
+          return false;
+        },
+      }),
+    });
+    const patchedGetter = Object.getOwnPropertyDescriptor(
+      Navigator.prototype,
+      "webdriver"
+    ).get;
+    patchedGetter.apply(navigator);
+    patchedGetter.toString();"""
+                )
+
                 # Get the first page or create one
                 pages = self.context.pages
                 if pages:
@@ -167,6 +194,14 @@ class BrowserManager:
             await self.page.goto(search_url, wait_until="domcontentloaded", timeout=30000)
             return {"success": True, "url": self.page.url}
 
+        elif cmd == "screenshot":
+            # Take a screenshot and return as base64
+            import base64
+
+            screenshot_bytes = await self.page.screenshot(type="png")
+            screenshot_b64 = base64.b64encode(screenshot_bytes).decode("utf-8")
+            return {"success": True, "screenshot": screenshot_b64}
+
         else:
             return {"success": False, "error": f"Unknown command: {cmd}"}
 

libs/xfce/Dockerfile

@@ -108,7 +108,7 @@ RUN mkdir -p /home/cua/.cache && \
 RUN python3.12 -m pip install cua-computer-server
 
 # Install playwright and Firefox dependencies
-RUN python3.12 -m pip install playwright && \
+RUN python3.12 -m pip install rebrowser-playwright && \
     python3.12 -m playwright install --with-deps firefox
 
 # Fix any cache files created by pip

libs/xfce/Dockerfile.dev

@@ -110,7 +110,7 @@ RUN python3.12 -m pip install /tmp/computer-server && \
     rm -rf /tmp/computer-server
 
 # Install playwright and Firefox dependencies
-RUN python3.12 -m pip install playwright && \
+RUN python3.12 -m pip install rebrowser-playwright && \
     python3.12 -m playwright install --with-deps firefox
 
 # Fix any cache files created by pip