Merge branch 'main' into sync-logging

litellm/caching/caching_handler.py

@@ -247,7 +247,6 @@ class LLMCachingHandler:
                     pass
                 else:
                     call_type = original_function.__name__
-
                     cached_result = self._convert_cached_result_to_model_response(
                         cached_result=cached_result,
                         call_type=call_type,
@@ -719,6 +718,7 @@ class LLMCachingHandler:
         """
         Sync internal method to add the result to the cache
         """
+
         new_kwargs = kwargs.copy()
         new_kwargs.update(
             convert_args_to_kwargs(
@@ -732,6 +732,7 @@ class LLMCachingHandler:
         if self._should_store_result_in_cache(
             original_function=self.original_function, kwargs=new_kwargs
         ):
+
             litellm.cache.add_cache(result, **new_kwargs)
 
         return
@@ -783,6 +784,7 @@ class LLMCachingHandler:
         - Else append the chunk to self.async_streaming_chunks
 
         """
+
         complete_streaming_response: Optional[
             Union[ModelResponse, TextCompletionResponse]
         ] = _assemble_complete_response_from_streaming_chunks(
@@ -793,7 +795,6 @@ class LLMCachingHandler:
             streaming_chunks=self.async_streaming_chunks,
             is_async=True,
         )
-
         # if a complete_streaming_response is assembled, add it to the cache
         if complete_streaming_response is not None:
             await self.async_set_cache(