Fix all 130126 tests

litellm/llms/bedrock/chat/invoke_handler.py

@@ -1533,6 +1533,7 @@ class AWSEventStreamDecoder:
                     )
                 ],
                 id=self.response_id,
+                model=self.model,
                 usage=usage,
                 provider_specific_fields=model_response_provider_specific_fields,
             )

litellm/llms/bedrock/passthrough/transformation.py

@@ -236,6 +236,7 @@ class BedrockPassthroughConfig(
         if len(all_translated_chunks) > 0:
             model_response = stream_chunk_builder(
                 chunks=all_translated_chunks,
+                logging_obj=litellm_logging_obj,
             )
             return model_response
         return None

litellm/llms/openai/chat/guardrail_translation/handler.py

@@ -362,7 +362,7 @@ class OpenAIChatCompletionsHandler(BaseTranslation):
         if has_stream_ended:
             # convert to model response
             model_response = cast(
-                ModelResponse, stream_chunk_builder(chunks=responses_so_far)
+                ModelResponse, stream_chunk_builder(chunks=responses_so_far, logging_obj=litellm_logging_obj)
             )
             # run process_output_response
             await self.process_output_response(

litellm/llms/watsonx/audio_transcription/transformation.py

@@ -98,16 +98,16 @@ class IBMWatsonXAudioTranscriptionConfig(
         """
         # Use common utility to process the audio file
         processed_audio = process_audio_file(audio_file)
-
-        # Get API params to extract project_id or space_id
-        api_params = _get_api_params(params=optional_params.copy(), model=model)
+        project_id = optional_params.get("project_id") or optional_params.get(
+            "watsonx_project"
+        )
+        space_id = optional_params.get("space_id")
+        api_params = _get_api_params(params=optional_params, model=model)
 
         # Initialize form data with required fields
         form_data: WatsonXAudioTranscriptionRequestBody = {"model": model}
 
-        project_id = api_params.get("project_id")
-        space_id = api_params.get("space_id")
-
+        # Only add project_id or space_id if they were explicitly provided by the user
         if project_id:
             form_data["project_id"] = project_id
         elif space_id:

litellm/proxy/proxy_server.py

@@ -7094,8 +7094,8 @@ async def token_counter(request: TokenCountRequest, call_endpoint: bool = False)
                     f"Provider token counting failed ({result.status_code}): {result.error_message}. "
                     "Falling back to local tokenizer."
                 )
-            else:
-                # Success - return the result
+            elif result is not None:
+                # Success - return the result (only if not None)
                 return result
 
     # Check if token counter is disabled before fallback

litellm/router.py

@@ -1514,7 +1514,7 @@ class Router:
 
         return FallbackStreamWrapper(stream_with_fallbacks())
 
-    async def _acompletion(
+    async def _acompletion(  # noqa: PLR0915
         self, model: str, messages: List[Dict[str, str]], **kwargs
     ) -> Union[ModelResponse, CustomStreamWrapper,]:
         """
@@ -1699,13 +1699,13 @@ class Router:
         per-deployment retry settings instead of the global setting.
         """
         # Only set if exception doesn't already have num_retries
-        if hasattr(exception, "num_retries") and exception.num_retries is not None:
+        if hasattr(exception, "num_retries") and exception.num_retries is not None:  # type: ignore
             return
 
         litellm_params = deployment.get("litellm_params", {})
         dep_num_retries = litellm_params.get("num_retries")
         if dep_num_retries is not None and isinstance(dep_num_retries, int):
-            exception.num_retries = dep_num_retries
+            exception.num_retries = dep_num_retries  # type: ignore
 
     def _update_kwargs_with_default_litellm_params(
         self, kwargs: dict, metadata_variable_name: Optional[str] = "metadata"