feat: 添加流式输出优化器以改善聊天体验

新增StreamOptimizer类用于优化API响应的流式输出
实现智能延迟调整算法，根据文本长度动态计算延迟时间
添加长文本分块输出功能，提高大段文本的显示效果
将优化器集成到Gemini和OpenAI聊天服务中
优化后的输出更接近自然打字效果，提升用户体验

app/services/gemini_chat_service.py

@@ -4,6 +4,7 @@ import json
 from typing import Dict, Any, AsyncGenerator, List
 from app.core.logger import get_gemini_logger
 from app.services.chat.api_client import GeminiApiClient
+from app.services.chat.stream_optimizer import gemini_optimizer
 from app.schemas.gemini_models import GeminiRequest
 from app.core.config import settings
 from app.services.chat.response_handler import GeminiResponseHandler
@@ -78,6 +79,26 @@ class GeminiChatService:
         self.api_client = GeminiApiClient(base_url)
         self.key_manager = key_manager
         self.response_handler = GeminiResponseHandler()
+        
+    def _extract_text_from_response(self, response: Dict[str, Any]) -> str:
+        """从响应中提取文本内容"""
+        if not response.get("candidates"):
+            return ""
+            
+        candidate = response["candidates"][0]
+        content = candidate.get("content", {})
+        parts = content.get("parts", [])
+        
+        if parts and "text" in parts[0]:
+            return parts[0].get("text", "")
+        return ""
+        
+    def _create_char_response(self, original_response: Dict[str, Any], text: str) -> Dict[str, Any]:
+        """创建包含指定文本的响应"""
+        response_copy = json.loads(json.dumps(original_response))  # 深拷贝
+        if response_copy.get("candidates") and response_copy["candidates"][0].get("content", {}).get("parts"):
+            response_copy["candidates"][0]["content"]["parts"][0]["text"] = text
+        return response_copy
 
     async def generate_content(self, model: str, request: GeminiRequest, api_key: str) -> Dict[str, Any]:
         """生成内容"""
@@ -96,8 +117,21 @@ class GeminiChatService:
                     # print(line)
                     if line.startswith("data:"):
                         line = line[6:]
-                        line = json.dumps(self.response_handler.handle_response(json.loads(line), model, stream=True))
-                        yield "data: " + line + "\n\n"
+                        response_data = self.response_handler.handle_response(json.loads(line), model, stream=True)
+                        text = self._extract_text_from_response(response_data)
+                        
+                        # 如果有文本内容，使用流式输出优化器处理
+                        if text:
+                            # 使用流式输出优化器处理文本输出
+                            async for optimized_chunk in gemini_optimizer.optimize_stream_output(
+                                text,
+                                lambda t: self._create_char_response(response_data, t),
+                                lambda c: "data: " + json.dumps(c) + "\n\n"
+                            ):
+                                yield optimized_chunk
+                        else:
+                            # 如果没有文本内容（如工具调用等），整块输出
+                            yield "data: " + json.dumps(response_data) + "\n\n"
                 logger.info("Streaming completed successfully")
                 break
             except Exception as e: