'commit'

WeiXin/T1_OpenChat.py

@@ -4,6 +4,7 @@ import time
 import logging
 import sys
 import os
+import WxUtil
 
 # 添加项目根目录到 sys.path
 project_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
@@ -29,11 +30,8 @@ def open_chat(target_name="糖豆爸爸"):
     logger.info(f"开始执行 T1: 打开微信并进入 '{target_name}' 的对话框...")
     
     # 连接设备
-    try:
-        d = u2.connect()
-        logger.info(f"设备连接成功: {d.info.get('serial')}")
-    except Exception as e:
-        logger.error(f"设备连接失败: {e}")
+    d = WxUtil.connect_device()
+    if not d:
         return
 
     # 1. 启动微信

WeiXin/T2_GetHistory.py

@@ -1,14 +1,15 @@
 # coding=utf-8
-import uiautomator2 as u2
 import time
 import logging
 import sys
 import os
+import asyncio
 
 project_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 if project_root not in sys.path:
     sys.path.append(project_root)
 
+from WeiXin import WxUtil
 from WeiXin.WxUtil import analyze_chat_image
 
 # 配置日志
@@ -26,14 +27,11 @@ logging.basicConfig(
 )
 logger = logging.getLogger("T2_GetHistory")
 
-def get_history(target_name="对方"):
+async def get_history(target_name="对方"):
     logger.info("开始执行 T2: 获取当前屏幕对话历史...")
     
-    try:
-        d = u2.connect()
-        logger.info(f"设备连接成功: {d.info.get('serial')}")
-    except Exception as e:
-        logger.error(f"设备连接失败: {e}")
+    d = WxUtil.connect_device()
+    if not d:
         return
 
     # 截图
@@ -53,8 +51,12 @@ def get_history(target_name="对方"):
         analyzed_path = os.path.join(screenshot_dir, analyzed_filename)
         
         # 调用 WxUtil 中的分析函数
-        dialogue_log = analyze_chat_image(save_path, analyzed_path, target_name=target_name)
+        dialogue_log, input_box = await analyze_chat_image(save_path, analyzed_path, device=d, target_name=target_name)
         
+        if dialogue_log == "VOICE_CONVERTING":
+            logger.info("检测到语音正在转文字，T2 任务暂停。")
+            return
+
         logger.info("✅ T2 执行完成。历史对话如下：")
         if dialogue_log:
             for log in dialogue_log:
@@ -66,4 +68,4 @@ def get_history(target_name="对方"):
         logger.error(f"❌ T2 执行失败: {e}")
 
 if __name__ == "__main__":
-    get_history()
+    asyncio.run(get_history())

WeiXin/T3_MarkInputBox.py

@@ -1,5 +1,4 @@
 # coding=utf-8
-import uiautomator2 as u2
 import time
 import logging
 import sys
@@ -11,6 +10,7 @@ project_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 if project_root not in sys.path:
     sys.path.append(project_root)
 
+from WeiXin import WxUtil
 from WeiXin.WxUtil import find_input_box_center
 
 # 配置日志
@@ -31,11 +31,8 @@ logger = logging.getLogger("T3_MarkInputBox")
 def mark_input_box():
     logger.info("开始执行 T3: 标识输入框位置...")
     
-    try:
-        d = u2.connect()
-        logger.info(f"设备连接成功: {d.info.get('serial')}")
-    except Exception as e:
-        logger.error(f"设备连接失败: {e}")
+    d = WxUtil.connect_device()
+    if not d:
         return
 
     screenshot_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "Screenshots")

WeiXin/T4_InputLlmText.py

@@ -1,5 +1,4 @@
 # coding=utf-8
-import uiautomator2 as u2
 import time
 import logging
 import sys
@@ -11,6 +10,7 @@ project_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 if project_root not in sys.path:
     sys.path.append(project_root)
 
+from WeiXin import WxUtil
 from WeiXin.WxUtil import find_input_box_center, perform_input_action, analyze_chat_image, clean_screenshots_dir, is_in_chat_interface
 from Util.LlmUtil import get_llm_response
 
@@ -37,8 +37,9 @@ async def generate_and_input():
     
     try:
         # 1. 连接设备
-        d = u2.connect()
-        logger.info(f"设备连接成功: {d.info.get('serial')}")
+        d = WxUtil.connect_device()
+        if not d:
+            return
 
         # 检查界面状态
         if not is_in_chat_interface(d):
@@ -54,14 +55,14 @@ async def generate_and_input():
         d.screenshot(tmp_shot)
         
         analyzed_shot = os.path.join(screenshot_dir, "t4_temp_history_analyzed.jpg")
-        dialogue_log = analyze_chat_image(tmp_shot, analyzed_shot)
+        dialogue_log, input_box = await analyze_chat_image(tmp_shot, analyzed_shot, device=d)
         
         # 语音转文字处理
         if dialogue_log == "VOICE_CONVERTING":
             logger.info("检测到语音正在转文字，等待 3 秒后重新截图分析...")
             await asyncio.sleep(3)
             d.screenshot(tmp_shot)
-            dialogue_log = analyze_chat_image(tmp_shot, analyzed_shot)
+            dialogue_log, input_box = await analyze_chat_image(tmp_shot, analyzed_shot, device=d)
         
         history_text = ""
         if dialogue_log:

WeiXin/T5_VLM_Voice_Debug.py

@@ -6,13 +6,13 @@ import sys
 import time
 
 import cv2
-import uiautomator2 as u2
 
 # 添加项目根目录到 sys.path
 project_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 if project_root not in sys.path:
     sys.path.append(project_root)
 
+from WeiXin import WxUtil
 from WeiXin.WxUtil import get_vlm_analysis
 from Util.EasyOcrKit import EasyOcrKit
 
@@ -24,11 +24,8 @@ async def main():
     logger.info("🚀 T6 VLM 语音坐标调试工具启动...")
     
     # 连接设备
-    try:
-        d = u2.connect()
-        logger.info(f"设备已连接: {d.info.get('serial')}")
-    except Exception as e:
-        logger.error(f"设备连接失败: {e}")
+    d = WxUtil.connect_device()
+    if not d:
         return
 
     # 截图目录

WeiXin/T6_CV_Voice_Debug.py

@@ -4,21 +4,24 @@ import sys
 import time
 
 import cv2
-import uiautomator2 as u2
 
 # 添加项目根目录到 sys.path
 project_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 if project_root not in sys.path:
     sys.path.append(project_root)
 
+from WeiXin import WxUtil
 from WeiXin.WxUtil import find_all_template_matches
 
 
 def run_cv_debug():
     # 1. 拍照 (获取当前设备屏幕)
     print("📸 正在连接设备并截取屏幕...")
+    d = WxUtil.connect_device()
+    if not d:
+        return
+    
     try:
-        d = u2.connect()
         screenshot_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "Screenshots")
         if not os.path.exists(screenshot_dir):
             os.makedirs(screenshot_dir)

WeiXin/T7_AutoChatMonitor.py

@@ -6,8 +6,6 @@ import sys
 import time
 from datetime import datetime
 
-import uiautomator2 as u2
-
 # 添加项目根目录到 sys.path
 project_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 if project_root not in sys.path:
@@ -15,6 +13,7 @@ if project_root not in sys.path:
 
 from Util import Win32Patch
 
+from WeiXin import WxUtil
 from WeiXin.WxUtil import perform_input_action, clean_screenshots_dir, find_template_match, find_all_template_matches
 from Util.LlmUtil import get_llm_response
 from Util.EasyOcrKit import EasyOcrKit
@@ -54,7 +53,9 @@ CHECK_INTERVAL = 5  # 检查频率 (秒)
 
 class ChatBot:
     def __init__(self):
-        self.d = u2.connect()
+        self.d = WxUtil.connect_device()
+        if not self.d:
+            raise Exception("无法连接到设备，任务终止")
         self.last_message_text = ""
         self.last_processed_msg = None # 记录上一条已处理/回复过的对方消息内容
         self.screenshot_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "Screenshots")

WeiXin/WxUtil.py

@@ -25,6 +25,23 @@ ocr_kit = EasyOcrKit()
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
 logger = logging.getLogger("WxUtil")
 
+def connect_device():
+    """
+    连接设备并返回设备对象，同时打印详细的设备信息
+    """
+    try:
+        d = u2.connect()
+        # 获取可靠的序列号
+        device_serial = d.serial if hasattr(d, 'serial') else "未知"
+        logger.info(f"设备连接成功: {device_serial}")
+        
+        # 获取并打印详细设备信息
+        device_info = d.device_info
+        logger.info(f"详细设备信息: 品牌={device_info.get('brand')}, 型号={device_info.get('model')}, SDK={device_info.get('sdk')}")
+        return d
+    except Exception as e:
+        logger.error(f"设备连接失败: {e}")
+        return None
 
 async def get_vlm_json(image_path, prompt):
     """
@@ -249,7 +266,7 @@ async def analyze_chat_image(image_path, output_path, device=None, target_name="
             unconverted_voices = [unconverted_voices[-1]]
             
             # 使用传入的 device 或创建新连接
-            d = device if device else u2.connect()
+            d = device if device else connect_device()
             
             for voice in unconverted_voices:
                 vx, vy = voice['coordinates']