Update docs plus init (#2073)

Co-authored-by: Shuchang Zheng <wintonzheng0325@gmail.com>

skyvern/webeye/browser_factory.py

@@ -2,6 +2,8 @@ from __future__ import annotations
 
 import asyncio
 import os
+import socket
+import subprocess
 import time
 import uuid
 from datetime import datetime
@@ -9,6 +11,7 @@ from pathlib import Path
 from typing import Any, Awaitable, Callable, Protocol
 
 import aiofiles
+import psutil
 import structlog
 from playwright.async_api import BrowserContext, ConsoleMessage, Download, Page, Playwright
 from pydantic import BaseModel, PrivateAttr
@@ -303,6 +306,31 @@ def _get_cdp_port(kwargs: dict) -> int | None:
     return None
 
 
+def _is_port_in_use(port: int) -> bool:
+    """Check if a port is already in use."""
+    with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
+        try:
+            s.bind(("localhost", port))
+            return False
+        except socket.error:
+            return True
+
+
+def _is_chrome_running() -> bool:
+    """Check if Chrome is already running."""
+    chrome_process_names = ["chrome", "google-chrome", "google chrome"]
+    for proc in psutil.process_iter(["name"]):
+        try:
+            proc_name = proc.info["name"].lower()
+            if proc_name == "chrome_crashpad_handler":
+                continue
+            if any(chrome_name in proc_name for chrome_name in chrome_process_names):
+                return True
+        except (psutil.NoSuchProcess, psutil.AccessDenied, psutil.ZombieProcess):
+            pass
+    return False
+
+
 async def _create_headless_chromium(
     playwright: Playwright, proxy_location: ProxyLocation | None = None, **kwargs: dict
 ) -> tuple[BrowserContext, BrowserArtifacts, BrowserCleanupFunc]:
@@ -352,6 +380,28 @@ async def _create_headful_chromium(
 async def _create_cdp_connection_browser(
     playwright: Playwright, proxy_location: ProxyLocation | None = None, **kwargs: dict
 ) -> tuple[BrowserContext, BrowserArtifacts, BrowserCleanupFunc]:
+    browser_type = settings.BROWSER_TYPE
+    browser_path = settings.CHROME_EXECUTABLE_PATH
+
+    if browser_type == "cdp-connect" and browser_path:
+        # First check if Chrome is already running
+        if _is_chrome_running():
+            raise Exception(
+                "Chrome is already running. Please close all Chrome instances before starting with remote debugging."
+            )
+
+        # Then check if the debugging port is already in use
+        if _is_port_in_use(9222):
+            raise Exception("Port 9222 is already in use. Another process may be using this port.")
+
+        browser_process = subprocess.Popen(
+            [browser_path, "--remote-debugging-port=9222"], stdout=subprocess.PIPE, stderr=subprocess.PIPE
+        )
+        # Add small delay to allow browser to start
+        time.sleep(1)
+        if browser_process.poll() is not None:
+            raise Exception(f"Failed to open browser. browser_path: {browser_path}")
+
     browser_args = BrowserContextFactory.build_browser_args()
 
     browser_artifacts = BrowserContextFactory.build_browser_artifacts(