tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-07 22:21:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

fixed lint errors

Browse Source
This commit is contained in:
mubashir1osmani
2025-09-17 00:31:29 -04:00
parent e56b11cb54
commit 439577fd35
4 changed files with 225 additions and 198 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/litellm_core_utils/litellm_logging.py
+160 -155
View File
@@ -299,9 +299,9 @@ class Logging(LiteLLMLoggingBaseClass):
self.litellm_trace_id: str = litellm_trace_id or str(uuid.uuid4())
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
@@ -670,24 +670,23 @@ 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
#########################################################
# Vector Store / Knowledge Base hooks
#########################################################
if litellm.vector_store_registry is not None:
vector_store_custom_logger = _init_custom_logger_compatible_class(
logging_integration="vector_store_pre_call_hook",
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__
return vector_store_custom_logger
return None
@@ -739,9 +738,9 @@ 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
@@ -770,10 +769,10 @@ 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", ""),
@@ -784,32 +783,32 @@ 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", {})
),
raw_request_headers=self._get_masked_headers(
additional_args.get("headers", {}) or {},
ignore_sensitive_headers=True,
),
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", {})
),
raw_request_headers=self._get_masked_headers(
additional_args.get("headers", {}) or {},
ignore_sensitive_headers=True,
),
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:
@@ -1092,13 +1091,13 @@ 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
@@ -1218,9 +1217,9 @@ 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:
@@ -1245,9 +1244,9 @@ 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
@@ -1391,9 +1390,9 @@ 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
self.model_call_details["cache_hit"] = cache_hit
@@ -1446,39 +1445,39 @@ class Logging(LiteLLMLoggingBaseClass):
"response_cost"
]
else:
self.model_call_details["response_cost"] = (
self._response_cost_calculator(result=logging_result)
)
self.model_call_details[
"response_cost"
] = self._response_cost_calculator(result=logging_result)
## STANDARDIZED LOGGING PAYLOAD
self.model_call_details["standard_logging_object"] = (
get_standard_logging_object_payload(
kwargs=self.model_call_details,
init_response_obj=logging_result,
start_time=start_time,
end_time=end_time,
logging_obj=self,
status="success",
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=logging_result,
start_time=start_time,
end_time=end_time,
logging_obj=self,
status="success",
standard_built_in_tools_params=self.standard_built_in_tools_params,
)
elif isinstance(result, dict) or isinstance(result, list):
## STANDARDIZED LOGGING PAYLOAD
self.model_call_details["standard_logging_object"] = (
get_standard_logging_object_payload(
kwargs=self.model_call_details,
init_response_obj=result,
start_time=start_time,
end_time=end_time,
logging_obj=self,
status="success",
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=result,
start_time=start_time,
end_time=end_time,
logging_obj=self,
status="success",
standard_built_in_tools_params=self.standard_built_in_tools_params,
)
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: # streaming chunks + image gen.
self.model_call_details["response_cost"] = None
@@ -1577,7 +1576,6 @@ class Logging(LiteLLMLoggingBaseClass):
)
if complete_streaming_response is not None:
self.success_handler(result=complete_streaming_response)
return
@@ -1630,23 +1628,23 @@ 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"] = (
get_standard_logging_object_payload(
kwargs=self.model_call_details,
init_response_obj=complete_streaming_response,
start_time=start_time,
end_time=end_time,
logging_obj=self,
status="success",
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=complete_streaming_response,
start_time=start_time,
end_time=end_time,
logging_obj=self,
status="success",
standard_built_in_tools_params=self.standard_built_in_tools_params,
)
callbacks = self.get_combined_callback_list(
dynamic_success_callbacks=self.dynamic_success_callbacks,
@@ -1970,10 +1968,10 @@ 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(
@@ -2012,10 +2010,10 @@ 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"]
@@ -2117,10 +2115,12 @@ class Logging(LiteLLMLoggingBaseClass):
result.usage = batch_usage
elif not is_base64_unified_file_id: # only run for non-unified file ids
response_cost, batch_usage, batch_models = (
await _handle_completed_batch(
batch=result, custom_llm_provider=self.custom_llm_provider
)
(
response_cost,
batch_usage,
batch_models,
) = await _handle_completed_batch(
batch=result, custom_llm_provider=self.custom_llm_provider
)
result._hidden_params["response_cost"] = response_cost
@@ -2151,9 +2151,9 @@ 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:
@@ -2164,10 +2164,10 @@ 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(
@@ -2180,16 +2180,16 @@ class Logging(LiteLLMLoggingBaseClass):
self.model_call_details["response_cost"] = None
## STANDARDIZED LOGGING PAYLOAD
self.model_call_details["standard_logging_object"] = (
get_standard_logging_object_payload(
kwargs=self.model_call_details,
init_response_obj=complete_streaming_response,
start_time=start_time,
end_time=end_time,
logging_obj=self,
status="success",
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=complete_streaming_response,
start_time=start_time,
end_time=end_time,
logging_obj=self,
status="success",
standard_built_in_tools_params=self.standard_built_in_tools_params,
)
callbacks = self.get_combined_callback_list(
dynamic_success_callbacks=self.dynamic_async_success_callbacks,
@@ -2402,18 +2402,18 @@ 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
@@ -3302,9 +3302,9 @@ def _init_custom_logger_compatible_class( # noqa: PLR0915
endpoint=arize_config.endpoint,
)
os.environ["OTEL_EXPORTER_OTLP_TRACES_HEADERS"] = (
f"space_id={arize_config.space_key},api_key={arize_config.api_key}"
)
os.environ[
"OTEL_EXPORTER_OTLP_TRACES_HEADERS"
] = f"space_id={arize_config.space_key},api_key={arize_config.api_key}"
for callback in _in_memory_loggers:
if (
isinstance(callback, ArizeLogger)
@@ -3328,9 +3328,9 @@ def _init_custom_logger_compatible_class( # noqa: PLR0915
# 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 (
@@ -3367,6 +3367,7 @@ def _init_custom_logger_compatible_class( # noqa: PLR0915
return galileo_logger # type: ignore
elif logging_integration == "cloudzero":
from litellm.integrations.cloudzero.cloudzero import CloudZeroLogger
for callback in _in_memory_loggers:
if isinstance(callback, CloudZeroLogger):
return callback # type: ignore
@@ -3437,9 +3438,9 @@ 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)
@@ -3594,6 +3595,7 @@ def get_custom_logger_compatible_class( # noqa: PLR0915
return callback
elif logging_integration == "cloudzero":
from litellm.integrations.cloudzero.cloudzero import CloudZeroLogger
for callback in _in_memory_loggers:
if isinstance(callback, CloudZeroLogger):
return callback
@@ -4088,10 +4090,10 @@ 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
@@ -4504,7 +4506,7 @@ def get_standard_logging_object_payload(
def emit_standard_logging_payload(payload: StandardLoggingPayload):
if os.getenv("LITELLM_PRINT_STANDARD_LOGGING_PAYLOAD"):
print(json.dumps(payload, indent=4)) # noqa
print(json.dumps(payload, indent=4)) # noqa
def get_standard_logging_metadata(
@@ -4527,6 +4529,9 @@ def get_standard_logging_metadata(
clean_metadata = StandardLoggingMetadata(
user_api_key_hash=None,
user_api_key_alias=None,
user_api_key_spend=None,
user_api_key_max_budget=None,
user_api_key_budget_reset_at=None,
user_api_key_team_id=None,
user_api_key_org_id=None,
user_api_key_user_id=None,
@@ -4576,9 +4581,9 @@ 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
litellm/proxy/litellm_pre_call_utils.py
+45 -29
View File
@@ -171,12 +171,12 @@ def _get_dynamic_logging_metadata(
user_api_key_dict: UserAPIKeyAuth, proxy_config: ProxyConfig
) -> Optional[TeamCallbackMetadata]:
callback_settings_obj: Optional[TeamCallbackMetadata] = None
key_dynamic_logging_settings: Optional[dict] = (
KeyAndTeamLoggingSettings.get_key_dynamic_logging_settings(user_api_key_dict)
)
team_dynamic_logging_settings: Optional[dict] = (
KeyAndTeamLoggingSettings.get_team_dynamic_logging_settings(user_api_key_dict)
)
key_dynamic_logging_settings: Optional[
dict
] = KeyAndTeamLoggingSettings.get_key_dynamic_logging_settings(user_api_key_dict)
team_dynamic_logging_settings: Optional[
dict
] = KeyAndTeamLoggingSettings.get_team_dynamic_logging_settings(user_api_key_dict)
#########################################################################################
# Key-based callbacks
#########################################################################################
@@ -272,7 +272,7 @@ class LiteLLMProxyRequestSetup:
if timeout_header is not None:
return float(timeout_header)
return None
@staticmethod
def _get_stream_timeout_from_request(headers: dict) -> Optional[float]:
"""
@@ -292,13 +292,14 @@ class LiteLLMProxyRequestSetup:
if num_retries_header is not None:
return int(num_retries_header)
return None
@staticmethod
def _get_spend_logs_metadata_from_request_headers(headers: dict) -> Optional[dict]:
"""
Get the `spend_logs_metadata` from the request headers.
"""
from litellm.litellm_core_utils.safe_json_loads import safe_json_loads
spend_logs_metadata_header = headers.get("x-litellm-spend-logs-metadata", None)
if spend_logs_metadata_header is not None:
return safe_json_loads(spend_logs_metadata_header)
@@ -337,16 +338,24 @@ class LiteLLMProxyRequestSetup:
return None
@staticmethod
def add_internal_user_from_user_mapping(general_settings: Optional[Dict], user_api_key_dict: UserAPIKeyAuth, headers: dict) -> UserAPIKeyAuth:
def add_internal_user_from_user_mapping(
general_settings: Optional[Dict],
user_api_key_dict: UserAPIKeyAuth,
headers: dict,
) -> UserAPIKeyAuth:
if general_settings is None:
return user_api_key_dict
user_header_mapping = general_settings.get("user_header_mappings")
if not user_header_mapping:
return user_api_key_dict
header_name = LiteLLMProxyRequestSetup.get_internal_user_header_from_mapping(user_header_mapping)
header_name = LiteLLMProxyRequestSetup.get_internal_user_header_from_mapping(
user_header_mapping
)
if not header_name:
return user_api_key_dict
header_value = LiteLLMProxyRequestSetup._get_case_insensitive_header(headers, header_name)
header_value = LiteLLMProxyRequestSetup._get_case_insensitive_header(
headers, header_name
)
if header_value:
user_api_key_dict.user_id = header_value
return user_api_key_dict
@@ -497,8 +506,10 @@ class LiteLLMProxyRequestSetup:
timeout = LiteLLMProxyRequestSetup._get_timeout_from_request(headers)
if timeout is not None:
data["timeout"] = timeout
stream_timeout = LiteLLMProxyRequestSetup._get_stream_timeout_from_request(headers)
stream_timeout = LiteLLMProxyRequestSetup._get_stream_timeout_from_request(
headers
)
if stream_timeout is not None:
data["stream_timeout"] = stream_timeout
@@ -507,7 +518,7 @@ class LiteLLMProxyRequestSetup:
data["num_retries"] = num_retries
return data
@staticmethod
def add_litellm_metadata_from_request_headers(
headers: dict,
@@ -520,11 +531,16 @@ class LiteLLMProxyRequestSetup:
Relevant issue: https://github.com/BerriAI/litellm/issues/14008
"""
from litellm.proxy._types import LitellmMetadataFromRequestHeaders
metadata_from_headers = LitellmMetadataFromRequestHeaders()
spend_logs_metadata = LiteLLMProxyRequestSetup._get_spend_logs_metadata_from_request_headers(headers)
spend_logs_metadata = (
LiteLLMProxyRequestSetup._get_spend_logs_metadata_from_request_headers(
headers
)
)
if spend_logs_metadata is not None:
metadata_from_headers["spend_logs_metadata"] = spend_logs_metadata
#########################################################################################
# Finally update the requests metadata with the `metadata_from_headers`
#########################################################################################
@@ -539,6 +555,8 @@ class LiteLLMProxyRequestSetup:
user_api_key_logged_metadata = StandardLoggingUserAPIKeyMetadata(
user_api_key_hash=user_api_key_dict.api_key, # just the hashed token
user_api_key_alias=user_api_key_dict.key_alias,
user_api_key_spend=user_api_key_dict.spend,
user_api_key_max_budget=user_api_key_dict.max_budget,
user_api_key_team_id=user_api_key_dict.team_id,
user_api_key_user_id=user_api_key_dict.user_id,
user_api_key_org_id=user_api_key_dict.org_id,
@@ -589,11 +607,11 @@ class LiteLLMProxyRequestSetup:
## KEY-LEVEL SPEND LOGS / TAGS
if "tags" in key_metadata and key_metadata["tags"] is not None:
data[_metadata_variable_name]["tags"] = (
LiteLLMProxyRequestSetup._merge_tags(
request_tags=data[_metadata_variable_name].get("tags"),
tags_to_add=key_metadata["tags"],
)
data[_metadata_variable_name][
"tags"
] = LiteLLMProxyRequestSetup._merge_tags(
request_tags=data[_metadata_variable_name].get("tags"),
tags_to_add=key_metadata["tags"],
)
if "spend_logs_metadata" in key_metadata and isinstance(
key_metadata["spend_logs_metadata"], dict
@@ -715,7 +733,6 @@ async def add_litellm_data_to_request( # noqa: PLR0915
from litellm.proxy.proxy_server import llm_router, premium_user
from litellm.types.proxy.litellm_pre_call_utils import SecretFields
_headers = clean_headers(
request.headers,
litellm_key_header_name=(
@@ -741,8 +758,6 @@ async def add_litellm_data_to_request( # noqa: PLR0915
if data.get(_metadata_variable_name, None) is None:
data[_metadata_variable_name] = {}
data.update(
LiteLLMProxyRequestSetup.add_litellm_data_for_backend_llm_call(
headers=_headers,
@@ -764,7 +779,9 @@ async def add_litellm_data_to_request( # noqa: PLR0915
data=data, headers=_headers, user_api_key_dict=user_api_key_dict
)
user_api_key_dict = LiteLLMProxyRequestSetup.add_internal_user_from_user_mapping(general_settings, user_api_key_dict, _headers)
user_api_key_dict = LiteLLMProxyRequestSetup.add_internal_user_from_user_mapping(
general_settings, user_api_key_dict, _headers
)
# Parse user info from headers
user = LiteLLMProxyRequestSetup.get_user_from_headers(_headers, general_settings)
@@ -774,7 +791,6 @@ async def add_litellm_data_to_request( # noqa: PLR0915
if "user" not in data:
data["user"] = user
data["secret_fields"] = SecretFields(raw_headers=dict(request.headers))
## Dynamic api version (Azure OpenAI endpoints) ##
@@ -824,9 +840,9 @@ async def add_litellm_data_to_request( # noqa: PLR0915
data[_metadata_variable_name]["litellm_api_version"] = version
if general_settings is not None:
data[_metadata_variable_name]["global_max_parallel_requests"] = (
general_settings.get("global_max_parallel_requests", None)
)
data[_metadata_variable_name][
"global_max_parallel_requests"
] = general_settings.get("global_max_parallel_requests", None)
### KEY-LEVEL Controls
key_metadata = user_api_key_dict.metadata
litellm/proxy/pass_through_endpoints/pass_through_endpoints.py
+14 -10
View File
@@ -474,6 +474,9 @@ class HttpPassThroughEndpointHelpers(BasePassthroughUtils):
user_api_key_team_alias=user_api_key_dict.team_alias,
user_api_key_end_user_id=user_api_key_dict.end_user_id,
user_api_key_request_route=user_api_key_dict.request_route,
user_api_key_spend=user_api_key_dict.spend,
user_api_key_max_budget=user_api_key_dict.max_budget,
user_api_key_budget_reset_at=user_api_key_dict.budget_reset_at,
)
)
@@ -1003,7 +1006,7 @@ class InitPassThroughEndpointHelpers:
):
"""Add exact path route for pass-through endpoint"""
route_key = f"{endpoint_id}:exact:{path}"
# Check if this exact route is already registered
if route_key in _registered_pass_through_routes:
verbose_proxy_logger.debug(
@@ -1011,7 +1014,7 @@ class InitPassThroughEndpointHelpers:
path,
)
return
verbose_proxy_logger.debug(
"adding exact pass through endpoint: %s, dependencies: %s",
path,
@@ -1032,12 +1035,12 @@ class InitPassThroughEndpointHelpers:
methods=["GET", "POST", "PUT", "DELETE", "PATCH"],
dependencies=dependencies,
)
# Register the route to prevent duplicates
_registered_pass_through_routes[route_key] = {
"endpoint_id": endpoint_id,
"path": path,
"type": "exact"
"type": "exact",
}
@staticmethod
@@ -1055,7 +1058,7 @@ class InitPassThroughEndpointHelpers:
"""Add wildcard route for sub-paths"""
wildcard_path = f"{path}/{{subpath:path}}"
route_key = f"{endpoint_id}:subpath:{path}"
# Check if this subpath route is already registered
if route_key in _registered_pass_through_routes:
verbose_proxy_logger.debug(
@@ -1063,7 +1066,7 @@ class InitPassThroughEndpointHelpers:
wildcard_path,
)
return
verbose_proxy_logger.debug(
"adding wildcard pass through endpoint: %s, dependencies: %s",
wildcard_path,
@@ -1085,19 +1088,20 @@ class InitPassThroughEndpointHelpers:
methods=["GET", "POST", "PUT", "DELETE", "PATCH"],
dependencies=dependencies,
)
# Register the route to prevent duplicates
_registered_pass_through_routes[route_key] = {
"endpoint_id": endpoint_id,
"path": path,
"type": "subpath"
"type": "subpath",
}
@staticmethod
def remove_endpoint_routes(endpoint_id: str):
"""Remove all routes for a specific endpoint ID from the registry"""
keys_to_remove = [
key for key, value in _registered_pass_through_routes.items()
key
for key, value in _registered_pass_through_routes.items()
if value["endpoint_id"] == endpoint_id
]
for key in keys_to_remove:
@@ -1480,7 +1484,7 @@ async def delete_pass_through_endpoints(
pass_through_endpoint_data.pop(endpoint_index)
response_obj = found_endpoint
# Remove routes from registry
# Remove routes from registry
InitPassThroughEndpointHelpers.remove_endpoint_routes(endpoint_id)
## Update db
litellm/types/utils.py
+6 -4
View File
@@ -162,7 +162,9 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
SearchContextCostPerQuery
] # Cost for using web search tool
citation_cost_per_token: Optional[float] # Cost per citation token for Perplexity
tiered_pricing: Optional[List[Dict[str, Any]]] # Tiered pricing structure for models like Dashscope
tiered_pricing: Optional[
List[Dict[str, Any]]
] # Tiered pricing structure for models like Dashscope
litellm_provider: Required[str]
mode: Required[
Literal[
@@ -1808,8 +1810,8 @@ class StandardLoggingUserAPIKeyMetadata(TypedDict):
user_api_key_hash: Optional[str] # hash of the litellm virtual key used
user_api_key_alias: Optional[str]
user_api_key_spend: Optional[float]
user_api_key_max_budget: Optional[float] = None
user_api_key_budget_reset_at: Optional[str] = None
user_api_key_max_budget: Optional[float]
user_api_key_budget_reset_at: Optional[str]
user_api_key_org_id: Optional[str]
user_api_key_team_id: Optional[str]
user_api_key_user_id: Optional[str]
@@ -1999,7 +2001,7 @@ class StandardLoggingGuardrailInformation(TypedDict, total=False):
]
guardrail_request: Optional[dict]
guardrail_response: Optional[Union[dict, str, List[dict]]]
guardrail_status: Literal["success", "failure","blocked"]
guardrail_status: Literal["success", "failure", "blocked"]
start_time: Optional[float]
end_time: Optional[float]
duration: Optional[float]