diff --git a/litellm/litellm_core_utils/get_litellm_params.py b/litellm/litellm_core_utils/get_litellm_params.py index ad9538ac171..0925e753e5e 100644 --- a/litellm/litellm_core_utils/get_litellm_params.py +++ b/litellm/litellm_core_utils/get_litellm_params.py @@ -104,6 +104,19 @@ def get_litellm_params( litellm_trace_id = _meta.get("trace_id") or _meta.get("session_id") # Build base dict with explicit parameters (always included) + # Merge litellm_metadata into metadata so callbacks (e.g. Langfuse) + # that read from litellm_params["metadata"] see API key fields even when + # the request uses "litellm_metadata" (e.g. /v1/messages from Claude Code). + _merged_metadata = metadata + if litellm_metadata and isinstance(litellm_metadata, dict): + if _merged_metadata is None: + _merged_metadata = dict(litellm_metadata) + else: + _merged_metadata = dict(_merged_metadata) # don't mutate caller's dict + for k, v in litellm_metadata.items(): + if k not in _merged_metadata: + _merged_metadata[k] = v + litellm_params = { "acompletion": acompletion, "api_key": api_key, @@ -116,7 +129,7 @@ def get_litellm_params( "model_alias_map": model_alias_map, "completion_call_id": completion_call_id, "aembedding": aembedding, - "metadata": metadata, + "metadata": _merged_metadata, "model_info": model_info, "proxy_server_request": proxy_server_request, "preset_cache_key": preset_cache_key, diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py index a92f4cb9ec8..e10f8e28ae9 100644 --- a/litellm/litellm_core_utils/litellm_logging.py +++ b/litellm/litellm_core_utils/litellm_logging.py @@ -352,9 +352,9 @@ class Logging(LiteLLMLoggingBaseClass): ) self.function_id = function_id self.streaming_chunks: List[Any] = [] # for generating complete stream response - self.sync_streaming_chunks: List[Any] = ( - [] - ) # for generating complete stream response + self.sync_streaming_chunks: List[ + Any + ] = [] # for generating complete stream response self.log_raw_request_response = log_raw_request_response # Initialize dynamic callbacks @@ -592,6 +592,13 @@ class Logging(LiteLLMLoggingBaseClass): base_litellm_params["litellm_metadata"] = kwargs["litellm_metadata"] if "metadata" not in base_litellm_params: base_litellm_params["metadata"] = kwargs["litellm_metadata"].copy() + else: + # Merge litellm_metadata into metadata without overwriting existing + # keys so API key fields are visible to callbacks even when + # Anthropic's native metadata is present (/v1/messages). + for key, value in kwargs["litellm_metadata"].items(): + if key not in base_litellm_params["metadata"]: + base_litellm_params["metadata"][key] = value if litellm_params: base_litellm_params.update(litellm_params) @@ -782,9 +789,9 @@ class Logging(LiteLLMLoggingBaseClass): prompt_spec=prompt_spec, dynamic_callback_params=dynamic_callback_params, ): - self.model_call_details["prompt_integration"] = ( - logger.__class__.__name__ - ) + self.model_call_details[ + "prompt_integration" + ] = logger.__class__.__name__ return logger except Exception: # If check fails, continue to next logger @@ -852,9 +859,9 @@ class Logging(LiteLLMLoggingBaseClass): if anthropic_cache_control_logger := AnthropicCacheControlHook.get_custom_logger_for_anthropic_cache_control_hook( non_default_params ): - self.model_call_details["prompt_integration"] = ( - anthropic_cache_control_logger.__class__.__name__ - ) + self.model_call_details[ + "prompt_integration" + ] = anthropic_cache_control_logger.__class__.__name__ return anthropic_cache_control_logger ######################################################### @@ -866,9 +873,9 @@ class Logging(LiteLLMLoggingBaseClass): internal_usage_cache=None, llm_router=None, ) - self.model_call_details["prompt_integration"] = ( - vector_store_custom_logger.__class__.__name__ - ) + self.model_call_details[ + "prompt_integration" + ] = vector_store_custom_logger.__class__.__name__ # Add to global callbacks so post-call hooks are invoked if ( vector_store_custom_logger @@ -928,9 +935,9 @@ class Logging(LiteLLMLoggingBaseClass): model ): # if model name was changes pre-call, overwrite the initial model call name with the new one self.model_call_details["model"] = model - self.model_call_details["litellm_params"]["api_base"] = ( - self._get_masked_api_base(additional_args.get("api_base", "")) - ) + self.model_call_details["litellm_params"][ + "api_base" + ] = self._get_masked_api_base(additional_args.get("api_base", "")) def pre_call(self, input, api_key, model=None, additional_args={}): # noqa: PLR0915 # Log the exact input to the LLM API @@ -959,10 +966,10 @@ class Logging(LiteLLMLoggingBaseClass): try: # [Non-blocking Extra Debug Information in metadata] if turn_off_message_logging is True: - _metadata["raw_request"] = ( - "redacted by litellm. \ + _metadata[ + "raw_request" + ] = "redacted by litellm. \ 'litellm.turn_off_message_logging=True'" - ) else: curl_command = self._get_request_curl_command( api_base=additional_args.get("api_base", ""), @@ -973,34 +980,34 @@ class Logging(LiteLLMLoggingBaseClass): _metadata["raw_request"] = str(curl_command) # split up, so it's easier to parse in the UI - self.model_call_details["raw_request_typed_dict"] = ( - RawRequestTypedDict( - raw_request_api_base=str( - additional_args.get("api_base") or "" - ), - raw_request_body=self._get_raw_request_body( - additional_args.get("complete_input_dict", {}) - ), - # NOTE: setting ignore_sensitive_headers to True will cause - # the Authorization header to be leaked when calls to the health - # endpoint are made and fail. - raw_request_headers=self._get_masked_headers( - additional_args.get("headers", {}) or {}, - ), - error=None, - ) + self.model_call_details[ + "raw_request_typed_dict" + ] = RawRequestTypedDict( + raw_request_api_base=str( + additional_args.get("api_base") or "" + ), + raw_request_body=self._get_raw_request_body( + additional_args.get("complete_input_dict", {}) + ), + # NOTE: setting ignore_sensitive_headers to True will cause + # the Authorization header to be leaked when calls to the health + # endpoint are made and fail. + raw_request_headers=self._get_masked_headers( + additional_args.get("headers", {}) or {}, + ), + error=None, ) except Exception as e: - self.model_call_details["raw_request_typed_dict"] = ( - RawRequestTypedDict( - error=str(e), - ) + self.model_call_details[ + "raw_request_typed_dict" + ] = RawRequestTypedDict( + error=str(e), ) - _metadata["raw_request"] = ( - "Unable to Log \ + _metadata[ + "raw_request" + ] = "Unable to Log \ raw request: {}".format( - str(e) - ) + str(e) ) if getattr(self, "logger_fn", None) and callable(self.logger_fn): try: @@ -1301,13 +1308,13 @@ class Logging(LiteLLMLoggingBaseClass): for callback in callbacks: try: if isinstance(callback, CustomLogger): - response: Optional[MCPPostCallResponseObject] = ( - await callback.async_post_mcp_tool_call_hook( - kwargs=kwargs, - response_obj=post_mcp_tool_call_response_obj, - start_time=start_time, - end_time=end_time, - ) + response: Optional[ + MCPPostCallResponseObject + ] = await callback.async_post_mcp_tool_call_hook( + kwargs=kwargs, + response_obj=post_mcp_tool_call_response_obj, + start_time=start_time, + end_time=end_time, ) ###################################################################### # if any of the callbacks modify the response, use the modified response @@ -1502,9 +1509,9 @@ class Logging(LiteLLMLoggingBaseClass): verbose_logger.debug( f"response_cost_failure_debug_information: {debug_info}" ) - self.model_call_details["response_cost_failure_debug_information"] = ( - debug_info - ) + self.model_call_details[ + "response_cost_failure_debug_information" + ] = debug_info return None try: @@ -1530,9 +1537,9 @@ class Logging(LiteLLMLoggingBaseClass): verbose_logger.debug( f"response_cost_failure_debug_information: {debug_info}" ) - self.model_call_details["response_cost_failure_debug_information"] = ( - debug_info - ) + self.model_call_details[ + "response_cost_failure_debug_information" + ] = debug_info return None @@ -1688,9 +1695,9 @@ class Logging(LiteLLMLoggingBaseClass): result=logging_result ) - self.model_call_details["standard_logging_object"] = ( - self._build_standard_logging_payload(logging_result, start_time, end_time) - ) + self.model_call_details[ + "standard_logging_object" + ] = self._build_standard_logging_payload(logging_result, start_time, end_time) if ( standard_logging_payload := self.model_call_details.get( @@ -1768,9 +1775,9 @@ class Logging(LiteLLMLoggingBaseClass): end_time = datetime.datetime.now() if self.completion_start_time is None: self.completion_start_time = end_time - self.model_call_details["completion_start_time"] = ( - self.completion_start_time - ) + self.model_call_details[ + "completion_start_time" + ] = self.completion_start_time self.model_call_details["log_event_type"] = "successful_api_call" self.model_call_details["end_time"] = end_time @@ -1807,10 +1814,10 @@ class Logging(LiteLLMLoggingBaseClass): end_time=end_time, ) elif isinstance(result, dict) or isinstance(result, list): - self.model_call_details["standard_logging_object"] = ( - self._build_standard_logging_payload( - result, start_time, end_time - ) + self.model_call_details[ + "standard_logging_object" + ] = self._build_standard_logging_payload( + result, start_time, end_time ) if ( standard_logging_payload := self.model_call_details.get( @@ -1819,9 +1826,9 @@ class Logging(LiteLLMLoggingBaseClass): ) is not None: emit_standard_logging_payload(standard_logging_payload) elif standard_logging_object is not None: - self.model_call_details["standard_logging_object"] = ( - standard_logging_object - ) + self.model_call_details[ + "standard_logging_object" + ] = standard_logging_object else: self.model_call_details["response_cost"] = None @@ -1979,17 +1986,17 @@ class Logging(LiteLLMLoggingBaseClass): verbose_logger.debug( "Logging Details LiteLLM-Success Call streaming complete" ) - self.model_call_details["complete_streaming_response"] = ( - complete_streaming_response - ) - self.model_call_details["response_cost"] = ( - self._response_cost_calculator(result=complete_streaming_response) - ) + self.model_call_details[ + "complete_streaming_response" + ] = complete_streaming_response + self.model_call_details[ + "response_cost" + ] = self._response_cost_calculator(result=complete_streaming_response) ## STANDARDIZED LOGGING PAYLOAD - self.model_call_details["standard_logging_object"] = ( - self._build_standard_logging_payload( - complete_streaming_response, start_time, end_time - ) + self.model_call_details[ + "standard_logging_object" + ] = self._build_standard_logging_payload( + complete_streaming_response, start_time, end_time ) if ( standard_logging_payload := self.model_call_details.get( @@ -2323,10 +2330,10 @@ class Logging(LiteLLMLoggingBaseClass): ) else: if self.stream and complete_streaming_response: - self.model_call_details["complete_response"] = ( - self.model_call_details.get( - "complete_streaming_response", {} - ) + self.model_call_details[ + "complete_response" + ] = self.model_call_details.get( + "complete_streaming_response", {} ) result = self.model_call_details["complete_response"] openMeterLogger.log_success_event( @@ -2350,10 +2357,10 @@ class Logging(LiteLLMLoggingBaseClass): ) else: if self.stream and complete_streaming_response: - self.model_call_details["complete_response"] = ( - self.model_call_details.get( - "complete_streaming_response", {} - ) + self.model_call_details[ + "complete_response" + ] = self.model_call_details.get( + "complete_streaming_response", {} ) result = self.model_call_details["complete_response"] @@ -2492,9 +2499,9 @@ class Logging(LiteLLMLoggingBaseClass): if complete_streaming_response is not None: print_verbose("Async success callbacks: Got a complete streaming response") - self.model_call_details["async_complete_streaming_response"] = ( - complete_streaming_response - ) + self.model_call_details[ + "async_complete_streaming_response" + ] = complete_streaming_response try: if self.model_call_details.get("cache_hit", False) is True: @@ -2505,10 +2512,10 @@ class Logging(LiteLLMLoggingBaseClass): model_call_details=self.model_call_details ) # base_model defaults to None if not set on model_info - self.model_call_details["response_cost"] = ( - self._response_cost_calculator( - result=complete_streaming_response - ) + self.model_call_details[ + "response_cost" + ] = self._response_cost_calculator( + result=complete_streaming_response ) verbose_logger.debug( @@ -2521,10 +2528,10 @@ class Logging(LiteLLMLoggingBaseClass): self.model_call_details["response_cost"] = None ## STANDARDIZED LOGGING PAYLOAD - self.model_call_details["standard_logging_object"] = ( - self._build_standard_logging_payload( - complete_streaming_response, start_time, end_time - ) + self.model_call_details[ + "standard_logging_object" + ] = self._build_standard_logging_payload( + complete_streaming_response, start_time, end_time ) # print standard logging payload @@ -2551,9 +2558,9 @@ class Logging(LiteLLMLoggingBaseClass): # _success_handler_helper_fn if self.model_call_details.get("standard_logging_object") is None: ## STANDARDIZED LOGGING PAYLOAD - self.model_call_details["standard_logging_object"] = ( - self._build_standard_logging_payload(result, start_time, end_time) - ) + self.model_call_details[ + "standard_logging_object" + ] = self._build_standard_logging_payload(result, start_time, end_time) # print standard logging payload if ( @@ -2796,18 +2803,18 @@ class Logging(LiteLLMLoggingBaseClass): ## STANDARDIZED LOGGING PAYLOAD - self.model_call_details["standard_logging_object"] = ( - get_standard_logging_object_payload( - kwargs=self.model_call_details, - init_response_obj={}, - start_time=start_time, - end_time=end_time, - logging_obj=self, - status="failure", - error_str=str(exception), - original_exception=exception, - standard_built_in_tools_params=self.standard_built_in_tools_params, - ) + self.model_call_details[ + "standard_logging_object" + ] = get_standard_logging_object_payload( + kwargs=self.model_call_details, + init_response_obj={}, + start_time=start_time, + end_time=end_time, + logging_obj=self, + status="failure", + error_str=str(exception), + original_exception=exception, + standard_built_in_tools_params=self.standard_built_in_tools_params, ) return start_time, end_time @@ -3771,9 +3778,9 @@ def _init_custom_logger_compatible_class( # noqa: PLR0915 service_name=arize_config.project_name, ) - os.environ["OTEL_EXPORTER_OTLP_TRACES_HEADERS"] = ( - f"space_id={arize_config.space_key or arize_config.space_id},api_key={arize_config.api_key}" - ) + os.environ[ + "OTEL_EXPORTER_OTLP_TRACES_HEADERS" + ] = f"space_id={arize_config.space_key or arize_config.space_id},api_key={arize_config.api_key}" for callback in _in_memory_loggers: if ( isinstance(callback, ArizeLogger) @@ -3799,13 +3806,13 @@ def _init_custom_logger_compatible_class( # noqa: PLR0915 existing_attrs = os.environ.get("OTEL_RESOURCE_ATTRIBUTES", "") # Add openinference.project.name attribute if existing_attrs: - os.environ["OTEL_RESOURCE_ATTRIBUTES"] = ( - f"{existing_attrs},openinference.project.name={arize_phoenix_config.project_name}" - ) + os.environ[ + "OTEL_RESOURCE_ATTRIBUTES" + ] = f"{existing_attrs},openinference.project.name={arize_phoenix_config.project_name}" else: - os.environ["OTEL_RESOURCE_ATTRIBUTES"] = ( - f"openinference.project.name={arize_phoenix_config.project_name}" - ) + os.environ[ + "OTEL_RESOURCE_ATTRIBUTES" + ] = f"openinference.project.name={arize_phoenix_config.project_name}" # Set Phoenix project name from environment variable phoenix_project_name = os.environ.get("PHOENIX_PROJECT_NAME", None) @@ -3813,19 +3820,19 @@ def _init_custom_logger_compatible_class( # noqa: PLR0915 existing_attrs = os.environ.get("OTEL_RESOURCE_ATTRIBUTES", "") # Add openinference.project.name attribute if existing_attrs: - os.environ["OTEL_RESOURCE_ATTRIBUTES"] = ( - f"{existing_attrs},openinference.project.name={phoenix_project_name}" - ) + os.environ[ + "OTEL_RESOURCE_ATTRIBUTES" + ] = f"{existing_attrs},openinference.project.name={phoenix_project_name}" else: - os.environ["OTEL_RESOURCE_ATTRIBUTES"] = ( - f"openinference.project.name={phoenix_project_name}" - ) + os.environ[ + "OTEL_RESOURCE_ATTRIBUTES" + ] = f"openinference.project.name={phoenix_project_name}" # auth can be disabled on local deployments of arize phoenix if arize_phoenix_config.otlp_auth_headers is not None: - os.environ["OTEL_EXPORTER_OTLP_TRACES_HEADERS"] = ( - arize_phoenix_config.otlp_auth_headers - ) + os.environ[ + "OTEL_EXPORTER_OTLP_TRACES_HEADERS" + ] = arize_phoenix_config.otlp_auth_headers for callback in _in_memory_loggers: if ( @@ -3904,7 +3911,9 @@ def _init_custom_logger_compatible_class( # noqa: PLR0915 from litellm.integrations.focus.focus_logger import FocusLogger for callback in _in_memory_loggers: - if type(callback) is FocusLogger: # exact match; exclude subclasses like VantageLogger + if ( + type(callback) is FocusLogger + ): # exact match; exclude subclasses like VantageLogger return callback # type: ignore focus_logger = FocusLogger() _in_memory_loggers.append(focus_logger) @@ -4010,9 +4019,9 @@ def _init_custom_logger_compatible_class( # noqa: PLR0915 exporter="otlp_http", endpoint="https://langtrace.ai/api/trace", ) - os.environ["OTEL_EXPORTER_OTLP_TRACES_HEADERS"] = ( - f"api_key={os.getenv('LANGTRACE_API_KEY')}" - ) + os.environ[ + "OTEL_EXPORTER_OTLP_TRACES_HEADERS" + ] = f"api_key={os.getenv('LANGTRACE_API_KEY')}" for callback in _in_memory_loggers: if ( isinstance(callback, OpenTelemetry) @@ -4286,7 +4295,9 @@ def get_custom_logger_compatible_class( # noqa: PLR0915 from litellm.integrations.focus.focus_logger import FocusLogger for callback in _in_memory_loggers: - if type(callback) is FocusLogger: # exact match; exclude subclasses like VantageLogger + if ( + type(callback) is FocusLogger + ): # exact match; exclude subclasses like VantageLogger return callback elif logging_integration == "vantage": from litellm.integrations.vantage.vantage_logger import VantageLogger @@ -4934,10 +4945,10 @@ class StandardLoggingPayloadSetup: for key in StandardLoggingHiddenParams.__annotations__.keys(): if key in hidden_params: if key == "additional_headers": - clean_hidden_params["additional_headers"] = ( - StandardLoggingPayloadSetup.get_additional_headers( - hidden_params[key] - ) + clean_hidden_params[ + "additional_headers" + ] = StandardLoggingPayloadSetup.get_additional_headers( + hidden_params[key] ) else: clean_hidden_params[key] = hidden_params[key] # type: ignore @@ -5576,9 +5587,9 @@ def scrub_sensitive_keys_in_metadata(litellm_params: Optional[dict]): ): for k, v in metadata["user_api_key_metadata"].items(): if k == "logging": # prevent logging user logging keys - cleaned_user_api_key_metadata[k] = ( - "scrubbed_by_litellm_for_sensitive_keys" - ) + cleaned_user_api_key_metadata[ + k + ] = "scrubbed_by_litellm_for_sensitive_keys" else: cleaned_user_api_key_metadata[k] = v diff --git a/litellm/utils.py b/litellm/utils.py index 81d749ab821..51b8efe6f23 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -1156,6 +1156,14 @@ def function_setup( # noqa: PLR0915 # read API key info from litellm_params["metadata"] see the fields. if not litellm_params.get("metadata"): litellm_params["metadata"] = kwargs["litellm_metadata"].copy() + else: + # Merge litellm_metadata into metadata without overwriting existing + # keys. This ensures API key fields (user_api_key_hash, etc.) are + # visible to callbacks even when Anthropic's native metadata field + # is present in /v1/messages requests from Claude Code. + for key, value in kwargs["litellm_metadata"].items(): + if key not in litellm_params["metadata"]: + litellm_params["metadata"][key] = value logging_obj.update_environment_variables( model=model,