feat: add stream smoothing feature for improved user experience

- Implement StreamSmoother class to split large content chunks into smaller pieces with delay
- Support OpenAI, Claude, and Gemini API response formats for smooth playback
- Add stream smoothing configuration to system settings (enable, chunk size, delay)
- Create streamlined API for stream smoothing with StreamSmoothingConfig dataclass
- Add admin UI controls for configuring stream smoothing parameters
- Use batch configuration loading to minimize database queries
- Enable typing effect simulation for better user experience in streaming responses

src/api/handlers/base/chat_handler_base.py

@@ -32,7 +32,7 @@ from src.api.handlers.base.parsers import get_parser_for_format
 from src.api.handlers.base.request_builder import PassthroughRequestBuilder
 from src.api.handlers.base.response_parser import ResponseParser
 from src.api.handlers.base.stream_context import StreamContext
-from src.api.handlers.base.stream_processor import StreamProcessor
+from src.api.handlers.base.stream_processor import StreamProcessor, StreamSmoothingConfig
 from src.api.handlers.base.stream_telemetry import StreamTelemetryRecorder
 from src.api.handlers.base.utils import build_sse_headers
 from src.config.settings import config
@@ -52,6 +52,7 @@ from src.models.database import (
     User,
 )
 from src.services.provider.transport import build_provider_url
+from src.services.system.config import SystemConfigService
 
 
 
@@ -297,11 +298,23 @@ class ChatHandlerBase(BaseMessageHandler, ABC):
         def update_streaming_status() -> None:
             self._update_usage_to_streaming_with_ctx(ctx)
 
+        # 从数据库批量读取流式平滑输出配置（单次查询）
+        smoothing_cfg = SystemConfigService.get_configs(
+            self.db,
+            ["stream_smoothing_enabled", "stream_smoothing_chunk_size", "stream_smoothing_delay_ms"],
+        )
+        smoothing_config = StreamSmoothingConfig(
+            enabled=bool(smoothing_cfg.get("stream_smoothing_enabled", False)),
+            chunk_size=int(smoothing_cfg.get("stream_smoothing_chunk_size") or 5),
+            delay_ms=int(smoothing_cfg.get("stream_smoothing_delay_ms") or 15),
+        )
+
         # 创建流处理器
         stream_processor = StreamProcessor(
             request_id=self.request_id,
             default_parser=self.parser,
             on_streaming_start=update_streaming_status,
+            smoothing_config=smoothing_config,
         )
 
         # 定义请求函数
@@ -379,8 +392,11 @@ class ChatHandlerBase(BaseMessageHandler, ABC):
                 http_request.is_disconnected,
             )
 
+            # 创建平滑输出流（如果启用）
+            smoothed_stream = stream_processor.create_smoothed_stream(monitored_stream)
+
             return StreamingResponse(
-                monitored_stream,
+                smoothed_stream,
                 media_type="text/event-stream",
                 headers=build_sse_headers(),
                 background=background_tasks,