Connect GLM Via Telegram API

REMOTE_SETUP.md

@@ -0,0 +1,48 @@
+# Remote Control Setup Guide (Tailscale + ADB)
+
+This guide explains how to control your Android phone using Open-AutoGLM even when the phone is on a mobile network (4G/5G) and not on the same Wi-Fi as your PC.
+
+## 1. Prerequisites (Tailscale VPN)
+
+Since ADB (Android Debug Bridge) does not work over the public internet securely, we use **Tailscale** to create a private, secure link between your devices.
+
+### Step 1: Install Tailscale
+1.  **On PC**: Download and install [Tailscale for Windows](https://tailscale.com/download/windows).
+2.  **On Phone**: Install the **Tailscale** app from the Google Play Store.
+
+### Step 2: Configure Network
+1.  Open Tailscale on **both** devices.
+2.  Log in with the **same account** (e.g., your Google account) on both.
+3.  Ensure Tailscale is **Active** (Connected) on both.
+4.  On the phone app, find the **IP Address** assigned to your phone (it starts with `100.x.x.x`).
+
+## 2. Connect ADB Remotely
+
+To connect your PC to the phone securely over this new network:
+
+1.  **Open Terminal** in the `Open-AutoGLM` directory.
+2.  Run the connect command using the local `platform-tools`:
+
+    ```powershell
+    .\platform-tools\adb.exe connect <PHONE_TAILSCALE_IP>:5555
+    ```
+    *(Replace `<PHONE_TAILSCALE_IP>` with the address you found in Step 1, e.g., `100.76.226.33`)*
+
+3.  **Verify Connection**:
+    ```powershell
+    .\platform-tools\adb.exe devices
+    ```
+    You should see your device IP listed as `device`.
+
+## 3. Troubleshooting
+
+**"Target machine actively refused it"**
+*   This means ADB is not listening on port 5555 on the phone.
+*   **Fix**: You must enable TCP/IP mode *once* via USB.
+    1.  Plug phone into PC via USB.
+    2.  Run: `.\platform-tools\adb.exe tcpip 5555`
+    3.  Unplug phone.
+    4.  Try connecting again via Tailscale IP.
+
+**"Command not found"**
+*   PowerShell doesn't know where `adb` is. Always use `.\platform-tools\adb.exe` instead of just `adb`.

main.py

@@ -29,7 +29,7 @@
 from phone_agent.model import ModelConfig
 
 
-def check_system_requirements() -> bool:
+def check_system_requirements(device_id: str | None = None) -> bool:
     """
     Check system requirements before running the agent.
 
@@ -90,7 +90,7 @@ def check_system_requirements() -> bool:
     print("2. Checking connected devices...", end=" ")
     try:
         result = subprocess.run(
-            ["adb", "devices"], capture_output=True, text=True, timeout=10
+            ["adb", "devices"], capture_output=True, text=True, timeout=30
         )
         lines = result.stdout.strip().split("\n")
         # Filter out header and empty lines, look for 'device' status
@@ -125,11 +125,16 @@ def check_system_requirements() -> bool:
     # Check 3: ADB Keyboard installed
     print("3. Checking ADB Keyboard...", end=" ")
     try:
+        cmd = ["adb"]
+        if device_id:
+            cmd.extend(["-s", device_id])
+        cmd.extend(["shell", "ime", "list", "-s"])
+
         result = subprocess.run(
-            ["adb", "shell", "ime", "list", "-s"],
+            cmd,
             capture_output=True,
             text=True,
-            timeout=10,
+            timeout=30,
         )
         ime_list = result.stdout.strip()
 
@@ -368,9 +373,21 @@ def parse_args() -> argparse.Namespace:
         help="Language for system prompt (cn or en, default: cn)",
     )
 
+    parser.add_argument(
+        "--auto-confirm", 
+        action="store_true", 
+        help="Automatically confirm sensitive operations and suppress interactive prompts"
+    )
+
+    parser.add_argument(
+        "--skip-checks",
+        action="store_true",
+        help="Skip system requirements check",
+    )
+
     parser.add_argument(
         "task",
-        nargs="?",
+        nargs="*",
         type=str,
         help="Task to execute (interactive mode if not provided)",
     )
@@ -464,7 +481,7 @@ def main():
         return
 
     # Run system requirements check before proceeding
-    if not check_system_requirements():
+    if not args.skip_checks and not check_system_requirements(args.device_id):
         sys.exit(1)
 
     # Check model API connectivity and model availability
@@ -485,10 +502,27 @@ def main():
         lang=args.lang,
     )
 
+    # Define callbacks based on auto-confirm
+    confirmation_callback = None
+    takeover_callback = None
+
+    if args.auto_confirm:
+        def auto_confirmation(msg):
+            print(f"⚠️ Auto-confirming sensitive operation: {msg}")
+            return True
+
+        def auto_takeover(msg):
+            print(f"⚠️ Auto-takeover suppressed: {msg}")
+
+        confirmation_callback = auto_confirmation
+        takeover_callback = auto_takeover
+
     # Create agent
     agent = PhoneAgent(
         model_config=model_config,
         agent_config=agent_config,
+        confirmation_callback=confirmation_callback,
+        takeover_callback=takeover_callback,
     )
 
     # Print header
@@ -511,8 +545,14 @@ def main():
 
     # Run with provided task or enter interactive mode
     if args.task:
-        print(f"\nTask: {args.task}\n")
-        result = agent.run(args.task)
+        # Join task arguments into a single string if it's a list
+        if isinstance(args.task, list):
+            task_str = " ".join(args.task)
+        else:
+            task_str = args.task
+
+        print(f"\nTask: {task_str}\n")
+        result = agent.run(task_str)
         print(f"\nResult: {result}")
     else:
         # Interactive mode

phone_agent/adb/connection.py

@@ -51,7 +51,7 @@ def __init__(self, adb_path: str = "adb"):
         """
         self.adb_path = adb_path
 
-    def connect(self, address: str, timeout: int = 10) -> tuple[bool, str]:
+    def connect(self, address: str, timeout: int = 30) -> tuple[bool, str]:
         """
         Connect to a remote device via TCP/IP.
 
@@ -107,7 +107,7 @@ def disconnect(self, address: str | None = None) -> tuple[bool, str]:
             if address:
                 cmd.append(address)
 
-            result = subprocess.run(cmd, capture_output=True, text=True, timeout=5)
+            result = subprocess.run(cmd, capture_output=True, text=True, timeout=15)
 
             output = result.stdout + result.stderr
             return True, output.strip() or "Disconnected"
@@ -127,7 +127,7 @@ def list_devices(self) -> list[DeviceInfo]:
                 [self.adb_path, "devices", "-l"],
                 capture_output=True,
                 text=True,
-                timeout=5,
+                timeout=15,
             )
 
             devices = []
@@ -239,7 +239,7 @@ def enable_tcpip(
                 cmd.extend(["-s", device_id])
             cmd.extend(["tcpip", str(port)])
 
-            result = subprocess.run(cmd, capture_output=True, text=True, timeout=10)
+            result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
 
             output = result.stdout + result.stderr
 

phone_agent/adb/screenshot.py

@@ -22,7 +22,7 @@ class Screenshot:
     is_sensitive: bool = False
 
 
-def get_screenshot(device_id: str | None = None, timeout: int = 10) -> Screenshot:
+def get_screenshot(device_id: str | None = None, timeout: int = 30) -> Screenshot:
     """
     Capture a screenshot from the connected Android device.
 
@@ -59,7 +59,7 @@ def get_screenshot(device_id: str | None = None, timeout: int = 10) -> Screensho
             adb_prefix + ["pull", "/sdcard/tmp.png", temp_path],
             capture_output=True,
             text=True,
-            timeout=5,
+            timeout=30,
         )
 
         if not os.path.exists(temp_path):