Merge branch 'py_test_tts' of https://github.com/xinnan-tech/xiaozhi-esp32-server into py_test_tts

main/xiaozhi-server/core/connection.py

@@ -499,6 +499,11 @@ class ConnectionHandler:
             self.config["selected_module"]["LLM"] = private_config["selected_module"][
                 "LLM"
             ]
+        if private_config.get("VLLM", None) is not None:
+            self.config["VLLM"] = private_config["VLLM"]
+            self.config["selected_module"]["VLLM"] = private_config["selected_module"][
+                "VLLM"
+            ]
         if private_config.get("Memory", None) is not None:
             init_memory = True
             self.config["Memory"] = private_config["Memory"]

main/xiaozhi-server/core/handle/intentHandler.py

@@ -13,6 +13,16 @@ TAG = __name__
 
 
 async def handle_user_intent(conn, text):
+    # 预处理输入文本，处理可能的JSON格式
+    try:
+        if text.strip().startswith('{') and text.strip().endswith('}'):
+            parsed_data = json.loads(text)
+            if isinstance(parsed_data, dict) and "content" in parsed_data:
+                text = parsed_data["content"]  # 提取content用于意图分析
+                conn.current_speaker = parsed_data.get("speaker")  # 保留说话人信息
+    except (json.JSONDecodeError, TypeError):
+        pass
+
     # 检查是否有明确的退出命令
     filtered_text = remove_punctuation_and_length(text)[1]
     if await check_direct_exit(conn, filtered_text):

main/xiaozhi-server/core/handle/sendAudioHandle.py

@@ -109,6 +109,9 @@ async def send_stt_message(conn, text):
             if isinstance(parsed_data, dict) and "content" in parsed_data:
                 # 如果是包含说话人信息的JSON格式，只显示content部分
                 display_text = parsed_data["content"]
+                # 保存说话人信息到conn对象
+                if "speaker" in parsed_data:
+                    conn.current_speaker = parsed_data["speaker"]
     except (json.JSONDecodeError, TypeError):
         # 如果不是JSON格式，直接使用原始文本
         display_text = text