fix: 修复流式输出问题，以及各种神秘问题

src/plugins/chat/bot.py

@@ -162,7 +162,7 @@ class ChatBot:
             logger.debug(f"8处理表情包时间: {timer2 - timer1}秒")
 
             timer1 = time.time()
-            await self._update_using_response(message, chat, response_set)
+            await self._update_using_response(message, response_set)
             timer2 = time.time()
             logger.info(f"6更新htfl时间: {timer2 - timer1}秒")
 
@@ -213,7 +213,7 @@ class ChatBot:
                 stream_id, limit=global_config.MAX_CONTEXT_SIZE, combine=True
             )
 
-        heartflow.get_subheartflow(stream_id).do_after_reply(response_set, chat_talking_prompt)
+        await heartflow.get_subheartflow(stream_id).do_after_reply(response_set, chat_talking_prompt)
 
     async def _send_response_messages(self, message, chat, response_set, thinking_id):
         container = message_manager.get_container(chat.stream_id)

src/plugins/chat/llm_generator.py

@@ -26,8 +26,7 @@ class ResponseGenerator:
         self.model_reasoning = LLM_request(
             model=global_config.llm_reasoning,
             temperature=0.7,
-            max_tokens=1000,
-            stream=True,
+            max_tokens=3000,
             request_type="response",
         )
         self.model_normal = LLM_request(

src/plugins/message/api.py

@@ -1,9 +1,13 @@
 from fastapi import FastAPI, HTTPException
 from typing import Dict, Any, Callable, List
+from src.common.logger import get_module_logger
 import aiohttp
 import asyncio
 import uvicorn
 import os
+import traceback
+
+logger = get_module_logger("api")
 
 
 class BaseMessageAPI:
@@ -50,8 +54,9 @@ class BaseMessageAPI:
                 for handler in self.message_handlers:
                     try:
                         await handler(self.cache[0])
-                    except Exception:
-                        pass
+                    except Exception as e:
+                        logger.error(str(e))
+                        logger.error(traceback.format_exc())
                 self.cache.pop(0)
             if len(self.cache) > 0:
                 await asyncio.sleep(0.1 / len(self.cache))