Apply Black formatting and fix Ruff issues

- Format code with Black to meet style requirements
- Fix auto-fixable Ruff linting issues
- Maintain header implementation functionality

Author: uzaxirr

litellm/main.py

@@ -1079,7 +1079,6 @@ def completion(  # type: ignore # noqa: PLR0915
             prompt_id=prompt_id, non_default_params=non_default_params
         )
     ):
-
         (
             model,
             messages,
@@ -2034,7 +2033,6 @@ def completion(  # type: ignore # noqa: PLR0915
 
             try:
                 if use_base_llm_http_handler:
-
                     response = base_llm_http_handler.completion(
                         model=model,
                         messages=messages,
@@ -2550,15 +2548,10 @@ def completion(  # type: ignore # noqa: PLR0915
             )
         elif custom_llm_provider == "compactifai":
             api_key = (
-                api_key
-                or get_secret_str("COMPACTIFAI_API_KEY")
-                or litellm.api_key
+                api_key or get_secret_str("COMPACTIFAI_API_KEY") or litellm.api_key
             )
 
-            api_base = (
-                api_base
-                or "https://api.compactif.ai/v1"
-            )
+            api_base = api_base or "https://api.compactif.ai/v1"
 
             ## COMPLETION CALL
             response = base_llm_http_handler.completion(
@@ -3144,9 +3137,9 @@ def completion(  # type: ignore # noqa: PLR0915
                     "aws_region_name" not in optional_params
                     or optional_params["aws_region_name"] is None
                 ):
-                    optional_params["aws_region_name"] = (
-                        aws_bedrock_client.meta.region_name
-                    )
+                    optional_params[
+                        "aws_region_name"
+                    ] = aws_bedrock_client.meta.region_name
 
             bedrock_route = BedrockModelInfo.get_bedrock_route(model)
             if bedrock_route == "converse":
@@ -3488,7 +3481,6 @@ def completion(  # type: ignore # noqa: PLR0915
                 )
                 raise e
         elif custom_llm_provider == "gradient_ai":
-
             api_base = litellm.api_base or api_base
             response = base_llm_http_handler.completion(
                 model=model,
@@ -3848,7 +3840,7 @@ def embedding(
     *,
     aembedding: Literal[True],
     **kwargs,
-) -> Coroutine[Any, Any, EmbeddingResponse]: 
+) -> Coroutine[Any, Any, EmbeddingResponse]:
     ...
 
 
@@ -3874,7 +3866,7 @@ def embedding(
     *,
     aembedding: Literal[False] = False,
     **kwargs,
-) -> EmbeddingResponse: 
+) -> EmbeddingResponse:
     ...
 
 # fmt: on
@@ -5127,9 +5119,9 @@ def adapter_completion(
     new_kwargs = translation_obj.translate_completion_input_params(kwargs=kwargs)
 
     response: Union[ModelResponse, CustomStreamWrapper] = completion(**new_kwargs)  # type: ignore
-    translated_response: Optional[Union[BaseModel, AdapterCompletionStreamWrapper]] = (
-        None
-    )
+    translated_response: Optional[
+        Union[BaseModel, AdapterCompletionStreamWrapper]
+    ] = None
     if isinstance(response, ModelResponse):
         translated_response = translation_obj.translate_completion_output_params(
             response=response
@@ -6117,9 +6109,9 @@ def stream_chunk_builder(  # noqa: PLR0915
         ]
 
         if len(content_chunks) > 0:
-            response["choices"][0]["message"]["content"] = (
-                processor.get_combined_content(content_chunks)
-            )
+            response["choices"][0]["message"][
+                "content"
+            ] = processor.get_combined_content(content_chunks)
 
         thinking_blocks = [
             chunk
@@ -6130,9 +6122,9 @@ def stream_chunk_builder(  # noqa: PLR0915
         ]
 
         if len(thinking_blocks) > 0:
-            response["choices"][0]["message"]["thinking_blocks"] = (
-                processor.get_combined_thinking_content(thinking_blocks)
-            )
+            response["choices"][0]["message"][
+                "thinking_blocks"
+            ] = processor.get_combined_thinking_content(thinking_blocks)
 
         reasoning_chunks = [
             chunk
@@ -6143,9 +6135,9 @@ def stream_chunk_builder(  # noqa: PLR0915
         ]
 
         if len(reasoning_chunks) > 0:
-            response["choices"][0]["message"]["reasoning_content"] = (
-                processor.get_combined_reasoning_content(reasoning_chunks)
-            )
+            response["choices"][0]["message"][
+                "reasoning_content"
+            ] = processor.get_combined_reasoning_content(reasoning_chunks)
 
         audio_chunks = [
             chunk