v0.3.3 异步处理记忆，修复了GUI

src/plugins/memory_system/llm_module.py

@@ -3,6 +3,8 @@ import requests
 from typing import Tuple, Union
 import time
 from nonebot import get_driver
+import aiohttp
+import asyncio
 
 driver = get_driver()
 config = driver.config
@@ -15,7 +17,7 @@ class LLMModel:
         self.api_key = config.siliconflow_key
         self.base_url = config.siliconflow_base_url
 
-    def generate_response(self, prompt: str) -> Tuple[str, str]:
+    async def generate_response(self, prompt: str) -> Tuple[str, str]:
         """根据输入的提示生成模型的响应"""
         headers = {
             "Authorization": f"Bearer {self.api_key}",
@@ -34,32 +36,32 @@ class LLMModel:
         api_url = f"{self.base_url.rstrip('/')}/chat/completions"
         
         max_retries = 3
-        base_wait_time = 15  # 基础等待时间（秒）
+        base_wait_time = 15
         
         for retry in range(max_retries):
             try:
-                response = requests.post(api_url, headers=headers, json=data)
+                async with aiohttp.ClientSession() as session:
+                    async with session.post(api_url, headers=headers, json=data) as response:
+                        if response.status == 429:
+                            wait_time = base_wait_time * (2 ** retry)  # 指数退避
+                            print(f"遇到请求限制(429)，等待{wait_time}秒后重试...")
+                            await asyncio.sleep(wait_time)
+                            continue
+                            
+                        response.raise_for_status()  # 检查其他响应状态
+                        
+                        result = await response.json()
+                        if "choices" in result and len(result["choices"]) > 0:
+                            content = result["choices"][0]["message"]["content"]
+                            reasoning_content = result["choices"][0]["message"].get("reasoning_content", "")
+                            return content, reasoning_content
+                        return "没有返回结果", ""
                 
-                if response.status_code == 429:
-                    wait_time = base_wait_time * (2 ** retry)  # 指数退避
-                    print(f"遇到请求限制(429)，等待{wait_time}秒后重试...")
-                    time.sleep(wait_time)
-                    continue
-                    
-                response.raise_for_status()  # 检查其他响应状态
-                
-                result = response.json()
-                if "choices" in result and len(result["choices"]) > 0:
-                    content = result["choices"][0]["message"]["content"]
-                    reasoning_content = result["choices"][0]["message"].get("reasoning_content", "")
-                    return content, reasoning_content
-                return "没有返回结果", ""
-                
-            except requests.exceptions.RequestException as e:
+            except Exception as e:
                 if retry < max_retries - 1:  # 如果还有重试机会
                     wait_time = base_wait_time * (2 ** retry)
                     print(f"请求失败，等待{wait_time}秒后重试... 错误: {str(e)}")
-                    time.sleep(wait_time)
+                    await asyncio.sleep(wait_time)
                 else:
                     return f"请求失败: {str(e)}", ""