From d03548b0642b91fcfb0dd1117935ddd9eef06c53 Mon Sep 17 00:00:00 2001 From: Sameer Kankute Date: Wed, 14 Jan 2026 17:42:52 +0530 Subject: [PATCH] Fix all 130126 tests --- litellm/llms/bedrock/chat/invoke_handler.py | 1 + litellm/llms/bedrock/passthrough/transformation.py | 1 + .../openai/chat/guardrail_translation/handler.py | 2 +- .../watsonx/audio_transcription/transformation.py | 12 ++++++------ litellm/proxy/proxy_server.py | 4 ++-- litellm/router.py | 6 +++--- 6 files changed, 14 insertions(+), 12 deletions(-) diff --git a/litellm/llms/bedrock/chat/invoke_handler.py b/litellm/llms/bedrock/chat/invoke_handler.py index 49292545208..81ba717ab3f 100644 --- a/litellm/llms/bedrock/chat/invoke_handler.py +++ b/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, ) diff --git a/litellm/llms/bedrock/passthrough/transformation.py b/litellm/llms/bedrock/passthrough/transformation.py index 71c418757bf..5efd3ba1d9f 100644 --- a/litellm/llms/bedrock/passthrough/transformation.py +++ b/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 diff --git a/litellm/llms/openai/chat/guardrail_translation/handler.py b/litellm/llms/openai/chat/guardrail_translation/handler.py index e2cf9f46104..d0ed3f165cc 100644 --- a/litellm/llms/openai/chat/guardrail_translation/handler.py +++ b/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( diff --git a/litellm/llms/watsonx/audio_transcription/transformation.py b/litellm/llms/watsonx/audio_transcription/transformation.py index fd6ac61821e..397b5c932f1 100644 --- a/litellm/llms/watsonx/audio_transcription/transformation.py +++ b/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: diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py index dd7f70750ca..a3254c32340 100644 --- a/litellm/proxy/proxy_server.py +++ b/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 diff --git a/litellm/router.py b/litellm/router.py index 3e5e8c9b8db..b77e3c9c299 100644 --- a/litellm/router.py +++ b/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"