支持鸿蒙OSNEXT_HDC

phone_agent/hdc/__init__.py

@@ -0,0 +1,53 @@
+"""HDC utilities for HarmonyOS device interaction."""
+
+from phone_agent.hdc.connection import (
+    HDCConnection,
+    ConnectionType,
+    DeviceInfo,
+    list_devices,
+    quick_connect,
+    set_hdc_verbose,
+)
+from phone_agent.hdc.device import (
+    back,
+    double_tap,
+    get_current_app,
+    home,
+    launch_app,
+    long_press,
+    swipe,
+    tap,
+)
+from phone_agent.hdc.input import (
+    clear_text,
+    detect_and_set_adb_keyboard,
+    restore_keyboard,
+    type_text,
+)
+from phone_agent.hdc.screenshot import get_screenshot
+
+__all__ = [
+    # Screenshot
+    "get_screenshot",
+    # Input
+    "type_text",
+    "clear_text",
+    "detect_and_set_adb_keyboard",
+    "restore_keyboard",
+    # Device control
+    "get_current_app",
+    "tap",
+    "swipe",
+    "back",
+    "home",
+    "double_tap",
+    "long_press",
+    "launch_app",
+    # Connection management
+    "HDCConnection",
+    "DeviceInfo",
+    "ConnectionType",
+    "quick_connect",
+    "list_devices",
+    "set_hdc_verbose",
+]

phone_agent/hdc/connection.py

@@ -0,0 +1,381 @@
+"""HDC connection management for HarmonyOS devices."""
+
+import os
+import subprocess
+import time
+from dataclasses import dataclass
+from enum import Enum
+from typing import Optional
+
+from phone_agent.config.timing import TIMING_CONFIG
+
+
+# Global flag to control HDC command output
+_HDC_VERBOSE = os.getenv("HDC_VERBOSE", "false").lower() in ("true", "1", "yes")
+
+
+def _run_hdc_command(cmd: list, **kwargs) -> subprocess.CompletedProcess:
+    """
+    Run HDC command with optional verbose output.
+
+    Args:
+        cmd: Command list to execute.
+        **kwargs: Additional arguments for subprocess.run.
+
+    Returns:
+        CompletedProcess result.
+    """
+    if _HDC_VERBOSE:
+        print(f"[HDC] Running command: {' '.join(cmd)}")
+
+    result = subprocess.run(cmd, **kwargs)
+
+    if _HDC_VERBOSE and result.returncode != 0:
+        print(f"[HDC] Command failed with return code {result.returncode}")
+        if hasattr(result, 'stderr') and result.stderr:
+            print(f"[HDC] Error: {result.stderr}")
+
+    return result
+
+
+def set_hdc_verbose(verbose: bool):
+    """Set HDC verbose mode globally."""
+    global _HDC_VERBOSE
+    _HDC_VERBOSE = verbose
+
+
+class ConnectionType(Enum):
+    """Type of HDC connection."""
+
+    USB = "usb"
+    WIFI = "wifi"
+    REMOTE = "remote"
+
+
+@dataclass
+class DeviceInfo:
+    """Information about a connected device."""
+
+    device_id: str
+    status: str
+    connection_type: ConnectionType
+    model: str | None = None
+    harmony_version: str | None = None
+
+
+class HDCConnection:
+    """
+    Manages HDC connections to HarmonyOS devices.
+
+    Supports USB, WiFi, and remote TCP/IP connections.
+
+    Example:
+        >>> conn = HDCConnection()
+        >>> # Connect to remote device
+        >>> conn.connect("192.168.1.100:5555")
+        >>> # List devices
+        >>> devices = conn.list_devices()
+        >>> # Disconnect
+        >>> conn.disconnect("192.168.1.100:5555")
+    """
+
+    def __init__(self, hdc_path: str = "hdc"):
+        """
+        Initialize HDC connection manager.
+
+        Args:
+            hdc_path: Path to HDC executable.
+        """
+        self.hdc_path = hdc_path
+
+    def connect(self, address: str, timeout: int = 10) -> tuple[bool, str]:
+        """
+        Connect to a remote device via TCP/IP.
+
+        Args:
+            address: Device address in format "host:port" (e.g., "192.168.1.100:5555").
+            timeout: Connection timeout in seconds.
+
+        Returns:
+            Tuple of (success, message).
+
+        Note:
+            The remote device must have TCP/IP debugging enabled.
+        """
+        # Validate address format
+        if ":" not in address:
+            address = f"{address}:5555"  # Default HDC port
+
+        try:
+            result = _run_hdc_command(
+                [self.hdc_path, "tconn", address],
+                capture_output=True,
+                text=True,
+                timeout=timeout,
+            )
+
+            output = result.stdout + result.stderr
+
+            if "Connect OK" in output or "connected" in output.lower():
+                return True, f"Connected to {address}"
+            elif "already connected" in output.lower():
+                return True, f"Already connected to {address}"
+            else:
+                return False, output.strip()
+
+        except subprocess.TimeoutExpired:
+            return False, f"Connection timeout after {timeout}s"
+        except Exception as e:
+            return False, f"Connection error: {e}"
+
+    def disconnect(self, address: str | None = None) -> tuple[bool, str]:
+        """
+        Disconnect from a remote device.
+
+        Args:
+            address: Device address to disconnect. If None, disconnects all.
+
+        Returns:
+            Tuple of (success, message).
+        """
+        try:
+            if address:
+                cmd = [self.hdc_path, "tdisconn", address]
+            else:
+                # HDC doesn't have a "disconnect all" command, so we need to list and disconnect each
+                devices = self.list_devices()
+                for device in devices:
+                    if ":" in device.device_id:  # Remote device
+                        _run_hdc_command(
+                            [self.hdc_path, "tdisconn", device.device_id],
+                            capture_output=True,
+                            text=True,
+                            timeout=5
+                        )
+                return True, "Disconnected all remote devices"
+
+            result = _run_hdc_command(cmd, capture_output=True, text=True, encoding="utf-8", timeout=5)
+
+            output = result.stdout + result.stderr
+            return True, output.strip() or "Disconnected"
+
+        except Exception as e:
+            return False, f"Disconnect error: {e}"
+
+    def list_devices(self) -> list[DeviceInfo]:
+        """
+        List all connected devices.
+
+        Returns:
+            List of DeviceInfo objects.
+        """
+        try:
+            result = _run_hdc_command(
+                [self.hdc_path, "list", "targets"],
+                capture_output=True,
+                text=True,
+                timeout=5,
+            )
+
+            devices = []
+            for line in result.stdout.strip().split("\n"):
+                if not line.strip():
+                    continue
+
+                # HDC output format: device_id (status)
+                # Example: "192.168.1.100:5555" or "FMR0223C13000649"
+                device_id = line.strip()
+
+                # Determine connection type
+                if ":" in device_id:
+                    conn_type = ConnectionType.REMOTE
+                else:
+                    conn_type = ConnectionType.USB
+
+                # HDC doesn't provide detailed status in list command
+                # We assume "Connected" status for devices that appear
+                devices.append(
+                    DeviceInfo(
+                        device_id=device_id,
+                        status="device",
+                        connection_type=conn_type,
+                        model=None,
+                    )
+                )
+
+            return devices
+
+        except Exception as e:
+            print(f"Error listing devices: {e}")
+            return []
+
+    def get_device_info(self, device_id: str | None = None) -> DeviceInfo | None:
+        """
+        Get detailed information about a device.
+
+        Args:
+            device_id: Device ID. If None, uses first available device.
+
+        Returns:
+            DeviceInfo or None if not found.
+        """
+        devices = self.list_devices()
+
+        if not devices:
+            return None
+
+        if device_id is None:
+            return devices[0]
+
+        for device in devices:
+            if device.device_id == device_id:
+                return device
+
+        return None
+
+    def is_connected(self, device_id: str | None = None) -> bool:
+        """
+        Check if a device is connected.
+
+        Args:
+            device_id: Device ID to check. If None, checks if any device is connected.
+
+        Returns:
+            True if connected, False otherwise.
+        """
+        devices = self.list_devices()
+
+        if not devices:
+            return False
+
+        if device_id is None:
+            return len(devices) > 0
+
+        return any(d.device_id == device_id for d in devices)
+
+    def enable_tcpip(
+        self, port: int = 5555, device_id: str | None = None
+    ) -> tuple[bool, str]:
+        """
+        Enable TCP/IP debugging on a USB-connected device.
+
+        This allows subsequent wireless connections to the device.
+
+        Args:
+            port: TCP port for HDC (default: 5555).
+            device_id: Device ID. If None, uses first available device.
+
+        Returns:
+            Tuple of (success, message).
+
+        Note:
+            The device must be connected via USB first.
+            After this, you can disconnect USB and connect via WiFi.
+        """
+        try:
+            cmd = [self.hdc_path]
+            if device_id:
+                cmd.extend(["-t", device_id])
+            cmd.extend(["tmode", "port", str(port)])
+
+            result = _run_hdc_command(cmd, capture_output=True, text=True, encoding="utf-8", timeout=10)
+
+            output = result.stdout + result.stderr
+
+            if result.returncode == 0 or "success" in output.lower():
+                time.sleep(TIMING_CONFIG.connection.adb_restart_delay)
+                return True, f"TCP/IP mode enabled on port {port}"
+            else:
+                return False, output.strip()
+
+        except Exception as e:
+            return False, f"Error enabling TCP/IP: {e}"
+
+    def get_device_ip(self, device_id: str | None = None) -> str | None:
+        """
+        Get the IP address of a connected device.
+
+        Args:
+            device_id: Device ID. If None, uses first available device.
+
+        Returns:
+            IP address string or None if not found.
+        """
+        try:
+            cmd = [self.hdc_path]
+            if device_id:
+                cmd.extend(["-t", device_id])
+            cmd.extend(["shell", "ifconfig"])
+
+            result = _run_hdc_command(cmd, capture_output=True, text=True, encoding="utf-8", timeout=5)
+
+            # Parse IP from ifconfig output
+            for line in result.stdout.split("\n"):
+                if "inet addr:" in line or "inet " in line:
+                    parts = line.strip().split()
+                    for i, part in enumerate(parts):
+                        if "addr:" in part:
+                            ip = part.split(":")[1]
+                            # Filter out localhost
+                            if not ip.startswith("127."):
+                                return ip
+                        elif part == "inet" and i + 1 < len(parts):
+                            ip = parts[i + 1].split("/")[0]
+                            if not ip.startswith("127."):
+                                return ip
+
+            return None
+
+        except Exception as e:
+            print(f"Error getting device IP: {e}")
+            return None
+
+    def restart_server(self) -> tuple[bool, str]:
+        """
+        Restart the HDC server.
+
+        Returns:
+            Tuple of (success, message).
+        """
+        try:
+            # Kill server
+            _run_hdc_command(
+                [self.hdc_path, "kill"], capture_output=True, timeout=5
+            )
+
+            time.sleep(TIMING_CONFIG.connection.server_restart_delay)
+
+            # Start server (HDC auto-starts when running commands)
+            _run_hdc_command(
+                [self.hdc_path, "start", "-r"], capture_output=True, timeout=5
+            )
+
+            return True, "HDC server restarted"
+
+        except Exception as e:
+            return False, f"Error restarting server: {e}"
+
+
+def quick_connect(address: str) -> tuple[bool, str]:
+    """
+    Quick helper to connect to a remote device.
+
+    Args:
+        address: Device address (e.g., "192.168.1.100" or "192.168.1.100:5555").
+
+    Returns:
+        Tuple of (success, message).
+    """
+    conn = HDCConnection()
+    return conn.connect(address)
+
+
+def list_devices() -> list[DeviceInfo]:
+    """
+    Quick helper to list connected devices.
+
+    Returns:
+        List of DeviceInfo objects.
+    """
+    conn = HDCConnection()
+    return conn.list_devices()

phone_agent/hdc/device.py

@@ -0,0 +1,269 @@
+"""Device control utilities for HarmonyOS automation."""
+
+import os
+import subprocess
+import time
+from typing import List, Optional, Tuple
+
+from phone_agent.config.apps_harmonyos import APP_PACKAGES
+from phone_agent.config.timing import TIMING_CONFIG
+from phone_agent.hdc.connection import _run_hdc_command
+
+
+def get_current_app(device_id: str | None = None) -> str:
+    """
+    Get the currently focused app name.
+
+    Args:
+        device_id: Optional HDC device ID for multi-device setups.
+
+    Returns:
+        The app name if recognized, otherwise "System Home".
+    """
+    hdc_prefix = _get_hdc_prefix(device_id)
+
+    result = _run_hdc_command(
+        hdc_prefix + ["shell", "hidumper", "-s", "WindowManagerService", "-a", "-a"],
+        capture_output=True,
+        text=True,
+        encoding="utf-8"
+    )
+    output = result.stdout
+    if not output:
+        raise ValueError("No output from hidumper")
+
+    # Parse window focus info
+    for line in output.split("\n"):
+        if "focused" in line.lower() or "current" in line.lower():
+            for app_name, package in APP_PACKAGES.items():
+                if package in line:
+                    return app_name
+
+    return "System Home"
+
+
+def tap(
+    x: int, y: int, device_id: str | None = None, delay: float | None = None
+) -> None:
+    """
+    Tap at the specified coordinates.
+
+    Args:
+        x: X coordinate.
+        y: Y coordinate.
+        device_id: Optional HDC device ID.
+        delay: Delay in seconds after tap. If None, uses configured default.
+    """
+    if delay is None:
+        delay = TIMING_CONFIG.device.default_tap_delay
+
+    hdc_prefix = _get_hdc_prefix(device_id)
+
+    # HarmonyOS uses uitest uiInput click
+    _run_hdc_command(
+        hdc_prefix + ["shell", "uitest", "uiInput", "click", str(x), str(y)],
+        capture_output=True
+    )
+    time.sleep(delay)
+
+
+def double_tap(
+    x: int, y: int, device_id: str | None = None, delay: float | None = None
+) -> None:
+    """
+    Double tap at the specified coordinates.
+
+    Args:
+        x: X coordinate.
+        y: Y coordinate.
+        device_id: Optional HDC device ID.
+        delay: Delay in seconds after double tap. If None, uses configured default.
+    """
+    if delay is None:
+        delay = TIMING_CONFIG.device.default_double_tap_delay
+
+    hdc_prefix = _get_hdc_prefix(device_id)
+
+    # HarmonyOS uses uitest uiInput doubleClick
+    _run_hdc_command(
+        hdc_prefix + ["shell", "uitest", "uiInput", "doubleClick", str(x), str(y)],
+        capture_output=True
+    )
+    time.sleep(delay)
+
+
+def long_press(
+    x: int,
+    y: int,
+    duration_ms: int = 3000,
+    device_id: str | None = None,
+    delay: float | None = None,
+) -> None:
+    """
+    Long press at the specified coordinates.
+
+    Args:
+        x: X coordinate.
+        y: Y coordinate.
+        duration_ms: Duration of press in milliseconds (note: HarmonyOS longClick may not support duration).
+        device_id: Optional HDC device ID.
+        delay: Delay in seconds after long press. If None, uses configured default.
+    """
+    if delay is None:
+        delay = TIMING_CONFIG.device.default_long_press_delay
+
+    hdc_prefix = _get_hdc_prefix(device_id)
+
+    # HarmonyOS uses uitest uiInput longClick
+    # Note: longClick may have a fixed duration, duration_ms parameter might not be supported
+    _run_hdc_command(
+        hdc_prefix + ["shell", "uitest", "uiInput", "longClick", str(x), str(y)],
+        capture_output=True,
+    )
+    time.sleep(delay)
+
+
+def swipe(
+    start_x: int,
+    start_y: int,
+    end_x: int,
+    end_y: int,
+    duration_ms: int | None = None,
+    device_id: str | None = None,
+    delay: float | None = None,
+) -> None:
+    """
+    Swipe from start to end coordinates.
+
+    Args:
+        start_x: Starting X coordinate.
+        start_y: Starting Y coordinate.
+        end_x: Ending X coordinate.
+        end_y: Ending Y coordinate.
+        duration_ms: Duration of swipe in milliseconds (auto-calculated if None).
+        device_id: Optional HDC device ID.
+        delay: Delay in seconds after swipe. If None, uses configured default.
+    """
+    if delay is None:
+        delay = TIMING_CONFIG.device.default_swipe_delay
+
+    hdc_prefix = _get_hdc_prefix(device_id)
+
+    if duration_ms is None:
+        # Calculate duration based on distance
+        dist_sq = (start_x - end_x) ** 2 + (start_y - end_y) ** 2
+        duration_ms = int(dist_sq / 1000)
+        duration_ms = max(500, min(duration_ms, 1000))  # Clamp between 500-1000ms
+
+    # HarmonyOS uses uitest uiInput swipe
+    # Format: swipe startX startY endX endY duration
+    _run_hdc_command(
+        hdc_prefix
+        + [
+            "shell",
+            "uitest",
+            "uiInput",
+            "swipe",
+            str(start_x),
+            str(start_y),
+            str(end_x),
+            str(end_y),
+            str(duration_ms),
+        ],
+        capture_output=True,
+    )
+    time.sleep(delay)
+
+
+def back(device_id: str | None = None, delay: float | None = None) -> None:
+    """
+    Press the back button.
+
+    Args:
+        device_id: Optional HDC device ID.
+        delay: Delay in seconds after pressing back. If None, uses configured default.
+    """
+    if delay is None:
+        delay = TIMING_CONFIG.device.default_back_delay
+
+    hdc_prefix = _get_hdc_prefix(device_id)
+
+    # HarmonyOS uses uitest uiInput keyEvent Back
+    _run_hdc_command(
+        hdc_prefix + ["shell", "uitest", "uiInput", "keyEvent", "Back"],
+        capture_output=True
+    )
+    time.sleep(delay)
+
+
+def home(device_id: str | None = None, delay: float | None = None) -> None:
+    """
+    Press the home button.
+
+    Args:
+        device_id: Optional HDC device ID.
+        delay: Delay in seconds after pressing home. If None, uses configured default.
+    """
+    if delay is None:
+        delay = TIMING_CONFIG.device.default_home_delay
+
+    hdc_prefix = _get_hdc_prefix(device_id)
+
+    # HarmonyOS uses uitest uiInput keyEvent Home
+    _run_hdc_command(
+        hdc_prefix + ["shell", "uitest", "uiInput", "keyEvent", "Home"],
+        capture_output=True
+    )
+    time.sleep(delay)
+
+
+def launch_app(
+    app_name: str, device_id: str | None = None, delay: float | None = None
+) -> bool:
+    """
+    Launch an app by name.
+
+    Args:
+        app_name: The app name (must be in APP_PACKAGES).
+        device_id: Optional HDC device ID.
+        delay: Delay in seconds after launching. If None, uses configured default.
+
+    Returns:
+        True if app was launched, False if app not found.
+    """
+    if delay is None:
+        delay = TIMING_CONFIG.device.default_launch_delay
+
+    if app_name not in APP_PACKAGES:
+        print(f"[HDC] App '{app_name}' not found in HarmonyOS app list")
+        print(f"[HDC] Available apps: {', '.join(sorted(APP_PACKAGES.keys())[:10])}...")
+        return False
+
+    hdc_prefix = _get_hdc_prefix(device_id)
+    bundle = APP_PACKAGES[app_name]
+
+    # HarmonyOS uses 'aa start' command to launch apps
+    # Format: aa start -b {bundle} -a {ability}
+    # Most HarmonyOS apps use "EntryAbility" as the main ability name
+    _run_hdc_command(
+        hdc_prefix
+        + [
+            "shell",
+            "aa",
+            "start",
+            "-b",
+            bundle,
+            "-a",
+            "EntryAbility",
+        ],
+        capture_output=True,
+    )
+    time.sleep(delay)
+    return True
+
+
+def _get_hdc_prefix(device_id: str | None) -> list:
+    """Get HDC command prefix with optional device specifier."""
+    if device_id:
+        return ["hdc", "-t", device_id]
+    return ["hdc"]

phone_agent/hdc/input.py

@@ -0,0 +1,136 @@
+"""Input utilities for HarmonyOS device text input."""
+
+import base64
+import subprocess
+from typing import Optional
+
+from phone_agent.hdc.connection import _run_hdc_command
+
+
+def type_text(text: str, device_id: str | None = None, x: int = None, y: int = None) -> None:
+    """
+    Type text into the currently focused input field.
+
+    Args:
+        text: The text to type.
+        device_id: Optional HDC device ID for multi-device setups.
+        x: Optional X coordinate for input field (deprecated, kept for compatibility).
+        y: Optional Y coordinate for input field (deprecated, kept for compatibility).
+
+    Note:
+        HarmonyOS uses: hdc shell uitest uiInput text "文本内容"
+        This command works without coordinates when input field is focused.
+        Recommendation: Click on the input field first to focus it, then use this function.
+    """
+    hdc_prefix = _get_hdc_prefix(device_id)
+
+    # Escape special characters for shell (keep quotes for proper text handling)
+    # The text will be wrapped in quotes in the command
+    escaped_text = text.replace('"', '\\"').replace("$", "\\$")
+
+    try:
+        # HarmonyOS uitest uiInput text command
+        # Format: hdc shell uitest uiInput text "文本内容"
+        _run_hdc_command(
+            hdc_prefix + ["shell", "uitest", "uiInput", "text", escaped_text],
+            capture_output=True,
+            text=True,
+        )
+    except Exception as e:
+        print(f"[HDC] Text input failed: {e}")
+        # Fallback: try with coordinates if provided (for older HarmonyOS versions)
+        if x is not None and y is not None:
+            try:
+                _run_hdc_command(
+                    hdc_prefix + ["shell", "uitest", "uiInput", "inputText", str(x), str(y), escaped_text],
+                    capture_output=True,
+                    text=True,
+                )
+            except Exception:
+                pass
+
+
+def clear_text(device_id: str | None = None) -> None:
+    """
+    Clear text in the currently focused input field.
+
+    Args:
+        device_id: Optional HDC device ID for multi-device setups.
+
+    Note:
+        This method uses repeated delete key events to clear text.
+        For HarmonyOS, you might also use select all + delete for better efficiency.
+    """
+    hdc_prefix = _get_hdc_prefix(device_id)
+    # Ctrl+A to select all (key code 2072 for Ctrl, 2017 for A)
+    # Then delete
+    _run_hdc_command(
+        hdc_prefix + ["shell", "uitest", "uiInput", "keyEvent", "2072", "2017"],
+        capture_output=True,
+        text=True,
+    )
+    _run_hdc_command(
+        hdc_prefix + ["shell", "uitest", "uiInput", "keyEvent", "2055"],  # Delete key
+        capture_output=True,
+        text=True,
+    )
+
+
+def detect_and_set_adb_keyboard(device_id: str | None = None) -> str:
+    """
+    Detect current keyboard and switch to ADB Keyboard if available.
+
+    Args:
+        device_id: Optional HDC device ID for multi-device setups.
+
+    Returns:
+        The original keyboard IME identifier for later restoration.
+
+    Note:
+        This is a placeholder. HarmonyOS may not support ADB Keyboard.
+        If there's a similar tool for HarmonyOS, integrate it here.
+    """
+    hdc_prefix = _get_hdc_prefix(device_id)
+
+    # Get current IME (if HarmonyOS supports this)
+    try:
+        result = _run_hdc_command(
+            hdc_prefix + ["shell", "settings", "get", "secure", "default_input_method"],
+            capture_output=True,
+            text=True,
+        )
+        current_ime = (result.stdout + result.stderr).strip()
+
+        # If ADB Keyboard equivalent exists for HarmonyOS, switch to it
+        # For now, we'll just return the current IME
+        return current_ime
+    except Exception:
+        return ""
+
+
+def restore_keyboard(ime: str, device_id: str | None = None) -> None:
+    """
+    Restore the original keyboard IME.
+
+    Args:
+        ime: The IME identifier to restore.
+        device_id: Optional HDC device ID for multi-device setups.
+    """
+    if not ime:
+        return
+
+    hdc_prefix = _get_hdc_prefix(device_id)
+
+    try:
+        _run_hdc_command(
+            hdc_prefix + ["shell", "ime", "set", ime], capture_output=True, text=True
+        )
+    except Exception:
+        pass
+
+
+def _get_hdc_prefix(device_id: str | None) -> list:
+    """Get HDC command prefix with optional device specifier."""
+    if device_id:
+        return ["hdc", "-t", device_id]
+    return ["hdc"]

phone_agent/hdc/screenshot.py

@@ -0,0 +1,125 @@
+"""Screenshot utilities for capturing HarmonyOS device screen."""
+
+import base64
+import os
+import subprocess
+import tempfile
+import uuid
+from dataclasses import dataclass
+from io import BytesIO
+from typing import Tuple
+
+from PIL import Image
+from phone_agent.hdc.connection import _run_hdc_command
+
+
+@dataclass
+class Screenshot:
+    """Represents a captured screenshot."""
+
+    base64_data: str
+    width: int
+    height: int
+    is_sensitive: bool = False
+
+
+def get_screenshot(device_id: str | None = None, timeout: int = 10) -> Screenshot:
+    """
+    Capture a screenshot from the connected HarmonyOS device.
+
+    Args:
+        device_id: Optional HDC device ID for multi-device setups.
+        timeout: Timeout in seconds for screenshot operations.
+
+    Returns:
+        Screenshot object containing base64 data and dimensions.
+
+    Note:
+        If the screenshot fails (e.g., on sensitive screens like payment pages),
+        a black fallback image is returned with is_sensitive=True.
+    """
+    temp_path = os.path.join(tempfile.gettempdir(), f"screenshot_{uuid.uuid4()}.png")
+    hdc_prefix = _get_hdc_prefix(device_id)
+
+    try:
+        # Execute screenshot command
+        # HarmonyOS HDC only supports JPEG format
+        remote_path = "/data/local/tmp/tmp_screenshot.jpeg"
+
+        # Try method 1: hdc shell screenshot (newer HarmonyOS versions)
+        result = _run_hdc_command(
+            hdc_prefix + ["shell", "screenshot", remote_path],
+            capture_output=True,
+            text=True,
+            timeout=timeout,
+        )
+
+        # Check for screenshot failure (sensitive screen)
+        output = result.stdout + result.stderr
+        if "fail" in output.lower() or "error" in output.lower() or "not found" in output.lower():
+            # Try method 2: snapshot_display (older versions or different devices)
+            result = _run_hdc_command(
+                hdc_prefix + ["shell", "snapshot_display", "-f", remote_path],
+                capture_output=True,
+                text=True,
+                timeout=timeout,
+            )
+            output = result.stdout + result.stderr
+            if "fail" in output.lower() or "error" in output.lower():
+                return _create_fallback_screenshot(is_sensitive=True)
+
+        # Pull screenshot to local temp path
+        # Note: remote file is JPEG, but PIL can open it regardless of local extension
+        _run_hdc_command(
+            hdc_prefix + ["file", "recv", remote_path, temp_path],
+            capture_output=True,
+            text=True,
+            timeout=5,
+        )
+
+        if not os.path.exists(temp_path):
+            return _create_fallback_screenshot(is_sensitive=False)
+
+        # Read JPEG image and convert to PNG for model inference
+        # PIL automatically detects the image format from file content
+        img = Image.open(temp_path)
+        width, height = img.size
+
+        buffered = BytesIO()
+        img.save(buffered, format="PNG")
+        base64_data = base64.b64encode(buffered.getvalue()).decode("utf-8")
+
+        # Cleanup
+        os.remove(temp_path)
+
+        return Screenshot(
+            base64_data=base64_data, width=width, height=height, is_sensitive=False
+        )
+
+    except Exception as e:
+        print(f"Screenshot error: {e}")
+        return _create_fallback_screenshot(is_sensitive=False)
+
+
+def _get_hdc_prefix(device_id: str | None) -> list:
+    """Get HDC command prefix with optional device specifier."""
+    if device_id:
+        return ["hdc", "-t", device_id]
+    return ["hdc"]
+
+
+def _create_fallback_screenshot(is_sensitive: bool) -> Screenshot:
+    """Create a black fallback image when screenshot fails."""
+    default_width, default_height = 1080, 2400
+
+    black_img = Image.new("RGB", (default_width, default_height), color="black")
+    buffered = BytesIO()
+    black_img.save(buffered, format="PNG")
+    base64_data = base64.b64encode(buffered.getvalue()).decode("utf-8")
+
+    return Screenshot(
+        base64_data=base64_data,
+        width=default_width,
+        height=default_height,
+        is_sensitive=is_sensitive,
+    )