feat: Introduce LLM response caching and streaming, add application configuration, and enhance session data with progress and history tracking.

utils/llm_helper.py

@@ -5,8 +5,17 @@ LLM调用辅助模块
 
 import asyncio
 import yaml
+from typing import Optional, Callable, AsyncIterator
 from config.llm_config import LLMConfig
+from config.app_config import app_config
 from utils.fallback_openai_client import AsyncFallbackOpenAIClient
+from utils.cache_manager import LLMCacheManager
+
+# 初始化LLM缓存管理器
+llm_cache = LLMCacheManager(
+    cache_dir=app_config.llm_cache_dir,
+    enabled=app_config.llm_cache_enabled
+)
 
 class LLMHelper:
     """LLM调用辅助类，支持同步和异步调用"""
@@ -82,6 +91,104 @@ class LLMHelper:
             print(f"原始响应: {response}")
             return {}
     
+    
     async def close(self):
         """关闭客户端"""
-        await self.client.close()
+        await self.client.close()
+    
+    async def async_call_with_cache(
+        self, 
+        prompt: str, 
+        system_prompt: str = None, 
+        max_tokens: int = None, 
+        temperature: float = None,
+        use_cache: bool = True
+    ) -> str:
+        """带缓存的异步LLM调用"""
+        messages = []
+        if system_prompt:
+            messages.append({"role": "system", "content": system_prompt})
+        messages.append({"role": "user", "content": prompt})
+        
+        # 生成缓存键
+        cache_key = llm_cache.get_cache_key_from_messages(messages, self.config.model)
+        
+        # 尝试从缓存获取
+        if use_cache and app_config.llm_cache_enabled:
+            cached_response = llm_cache.get(cache_key)
+            if cached_response:
+                print("💾 使用LLM缓存响应")
+                return cached_response
+        
+        # 调用LLM
+        response = await self.async_call(prompt, system_prompt, max_tokens, temperature)
+        
+        # 缓存响应
+        if use_cache and app_config.llm_cache_enabled and response:
+            llm_cache.set(cache_key, response)
+        
+        return response
+    
+    def call_with_cache(
+        self, 
+        prompt: str, 
+        system_prompt: str = None, 
+        max_tokens: int = None, 
+        temperature: float = None,
+        use_cache: bool = True
+    ) -> str:
+        """带缓存的同步LLM调用"""
+        try:
+            loop = asyncio.get_event_loop()
+        except RuntimeError:
+            loop = asyncio.new_event_loop()
+            asyncio.set_event_loop(loop)
+            
+        import nest_asyncio
+        nest_asyncio.apply()
+        
+        return loop.run_until_complete(
+            self.async_call_with_cache(prompt, system_prompt, max_tokens, temperature, use_cache)
+        )
+    
+    async def async_call_stream(
+        self, 
+        prompt: str, 
+        system_prompt: str = None,
+        max_tokens: int = None,
+        temperature: float = None,
+        callback: Optional[Callable[[str], None]] = None
+    ) -> AsyncIterator[str]:
+        """流式异步LLM调用"""
+        messages = []
+        if system_prompt:
+            messages.append({"role": "system", "content": system_prompt})
+        messages.append({"role": "user", "content": prompt})
+        
+        kwargs = {
+            'stream': True,
+            'max_tokens': max_tokens or self.config.max_tokens,
+            'temperature': temperature or self.config.temperature
+        }
+        
+        try:
+            response = await self.client.chat_completions_create(
+                messages=messages,
+                **kwargs
+            )
+            
+            full_response = ""
+            async for chunk in response:
+                if chunk.choices[0].delta.content:
+                    content = chunk.choices[0].delta.content
+                    full_response += content
+                    
+                    # 调用回调函数
+                    if callback:
+                        callback(content)
+                    
+                    yield content
+            
+        except Exception as e:
+            print(f"流式LLM调用失败: {e}")
+            yield ""