scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

fix(ci): stabilize CI - formatting, type errors, test polling, security CVEs, router bug, batch resolution

Browse source 
Fix 1: Run Black formatter on 35 files
Fix 2: Fix MyPy type errors:
  - setup_wizard.py: add type annotation for 'selected' set variable
  - user_api_key_auth.py: remove redundant type annotation on jwt_claims reassignment
Fix 3: Fix spend accuracy test burst 2 polling to wait for expected total
  spend instead of just 'any increase' from burst 2
Fix 4: Bump Next.js 16.1.6 -> 16.1.7 to fix CVE-2026-27978, CVE-2026-27979,
  CVE-2026-27980, CVE-2026-29057
Fix 5: Fix router _pre_call_checks model variable being overwritten inside
  loop, causing wrong model lookups on subsequent deployments. Use local
  _deployment_model variable instead.
Fix 6: Add missing resolve_output_file_ids_to_unified call in batch retrieve
  non-terminal-to-terminal path (matching the terminal path behavior)

Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
This commit is contained in:
Cursor Agent 2026-03-18 01:24:15 +00:00
parent d9a6036162
commit fde9062846
No known key found for this signature in database
41 changed files with 493 additions and 371 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
litellm/__init__.py
View file

@ -1465,9 +1465,15 @@ if TYPE_CHECKING:
from .llms.petals.completion.transformation import PetalsConfig as PetalsConfig
from .llms.ollama.chat.transformation import OllamaChatConfig as OllamaChatConfig
from .llms.ollama.completion.transformation import OllamaConfig as OllamaConfig
from .llms.sagemaker.completion.transformation import SagemakerConfig as SagemakerConfig
from .llms.sagemaker.chat.transformation import SagemakerChatConfig as SagemakerChatConfig
from .llms.sagemaker.nova.transformation import SagemakerNovaConfig as SagemakerNovaConfig
from .llms.sagemaker.completion.transformation import (
SagemakerConfig as SagemakerConfig,
)
from .llms.sagemaker.chat.transformation import (
SagemakerChatConfig as SagemakerChatConfig,
)
from .llms.sagemaker.nova.transformation import (
SagemakerNovaConfig as SagemakerNovaConfig,
)
from .llms.cohere.chat.transformation import CohereChatConfig as CohereChatConfig
from .llms.anthropic.experimental_pass_through.messages.transformation import (
AnthropicMessagesConfig as AnthropicMessagesConfig,

8
litellm/_logging.py
View file

@ -17,7 +17,9 @@ if set_verbose is True:
"`litellm.set_verbose` is deprecated. Please set `os.environ['LITELLM_LOG'] = 'DEBUG'` for debug logs."
)
_ENABLE_SECRET_REDACTION = os.getenv("LITELLM_DISABLE_REDACT_SECRETS", "").lower() != "true"
_ENABLE_SECRET_REDACTION = (
os.getenv("LITELLM_DISABLE_REDACT_SECRETS", "").lower() != "true"
)
_REDACTED = "REDACTED"
@ -199,7 +201,9 @@ class JsonFormatter(Formatter):
json_record[key] = value
if record.exc_info:
json_record["stacktrace"] = record.exc_text or self.formatException(record.exc_info)
json_record["stacktrace"] = record.exc_text or self.formatException(
record.exc_info
)
return safe_dumps(json_record)

8
litellm/cost_calculator.py
View file

@ -1189,7 +1189,9 @@ def completion_cost( # noqa: PLR0915
and _usage["prompt_tokens_details"] != {}
and _usage["prompt_tokens_details"]
):
prompt_tokens_details = _usage.get("prompt_tokens_details") or {}
prompt_tokens_details = (
_usage.get("prompt_tokens_details") or {}
)
cache_read_input_tokens = prompt_tokens_details.get(
"cached_tokens", 0
)
@ -1515,7 +1517,9 @@ def completion_cost( # noqa: PLR0915
if custom_llm_provider == "azure_ai":
model_for_additional_costs = request_model_for_cost
if completion_response is not None:
hidden_params = getattr(completion_response, "_hidden_params", None) or {}
hidden_params = (
getattr(completion_response, "_hidden_params", None) or {}
)
hidden_model = hidden_params.get("model") or hidden_params.get(
"litellm_model_name"
)

7
litellm/integrations/focus/destinations/factory.py
View file

@ -59,17 +59,14 @@ class FocusDestinationFactory:
return {k: v for k, v in resolved.items() if v is not None}
if provider == "vantage":
resolved = {
"api_key": overrides.get("api_key")
or os.getenv("VANTAGE_API_KEY"),
"api_key": overrides.get("api_key") or os.getenv("VANTAGE_API_KEY"),
"integration_token": overrides.get("integration_token")
or os.getenv("VANTAGE_INTEGRATION_TOKEN"),
"base_url": overrides.get("base_url")
or os.getenv("VANTAGE_BASE_URL", "https://api.vantage.sh"),
}
if not resolved.get("api_key"):
raise ValueError(
"VANTAGE_API_KEY must be provided for Vantage exports"
)
raise ValueError("VANTAGE_API_KEY must be provided for Vantage exports")
if not resolved.get("integration_token"):
raise ValueError(
"VANTAGE_INTEGRATION_TOKEN must be provided for Vantage exports"

6
litellm/integrations/langfuse/langfuse_prompt_management.py
View file

@ -340,9 +340,9 @@ class LangfusePromptManagement(LangFuseLogger, PromptManagementBase, CustomLogge
)
status_message = str(kwargs.get("exception", "Unknown error"))
if standard_logging_object is not None:
status_message = standard_logging_object.get(
"error_str", None
) or status_message
status_message = (
standard_logging_object.get("error_str", None) or status_message
)
langfuse_logger_to_use.log_event_on_langfuse(
start_time=start_time,
end_time=end_time,

8
litellm/integrations/vantage/vantage_logger.py
View file

@ -83,7 +83,9 @@ class VantageLogger(FocusLogger):
verbose_logger.debug(
"VantageLogger initialized (integration_token=%s)",
resolved_token[:4] + "***" if resolved_token and len(resolved_token) > 4 else "***",
resolved_token[:4] + "***"
if resolved_token and len(resolved_token) > 4
else "***",
)
async def initialize_focus_export_job(self) -> None:
@ -128,9 +130,7 @@ class VantageLogger(FocusLogger):
callback_type=VantageLogger
)
if not vantage_loggers:
verbose_logger.debug(
"No Vantage logger registered; skipping scheduler"
)
verbose_logger.debug("No Vantage logger registered; skipping scheduler")
return
vantage_logger = cast(VantageLogger, vantage_loggers[0])

5
litellm/litellm_core_utils/default_encoding.py
View file

@ -26,7 +26,9 @@ if custom_cache_dir:
else:
cache_dir = filename
os.environ["TIKTOKEN_CACHE_DIR"] = cache_dir # use local copy of tiktoken b/c of - https://github.com/BerriAI/litellm/issues/1071
os.environ[
"TIKTOKEN_CACHE_DIR"
] = cache_dir # use local copy of tiktoken b/c of - https://github.com/BerriAI/litellm/issues/1071
import tiktoken
import time
@ -48,4 +50,3 @@ for attempt in range(_max_retries):
# Exponential backoff with jitter to reduce collision probability
delay = _retry_delay * (2**attempt) + random.uniform(0, 0.1)
time.sleep(delay)

288
litellm/litellm_core_utils/litellm_logging.py
View file

@ -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
@ -782,9 +782,9 @@ 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 +852,9 @@ 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 +866,9 @@ 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 +928,9 @@ 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 +959,10 @@ 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 +973,34 @@ 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 +1301,13 @@ 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 +1502,9 @@ 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 +1530,9 @@ 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 +1688,9 @@ 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 +1768,9 @@ 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 +1807,10 @@ 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 +1819,9 @@ 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 +1979,17 @@ 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 +2323,10 @@ 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 +2350,10 @@ 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 +2492,9 @@ 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 +2505,10 @@ 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 +2521,10 @@ 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 +2551,9 @@ 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 +2796,18 @@ 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 +3771,9 @@ 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 +3799,13 @@ 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 +3813,19 @@ 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 +3904,9 @@ 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 +4012,9 @@ 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 +4288,9 @@ 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 +4938,10 @@ 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 +5580,9 @@ 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

2
litellm/llms/anthropic/experimental_pass_through/adapters/transformation.py
View file

@ -780,7 +780,7 @@ class LiteLLMAnthropicMessagesAdapter:
# Keep Anthropic-native tools in their original format
new_tools.append(tool) # type: ignore[arg-type]
continue
original_name = tool["name"]
truncated_name = truncate_tool_name(original_name)

16
litellm/llms/base_llm/videos/transformation.py
View file

@ -336,9 +336,7 @@ class BaseVideoConfig(ABC):
Returns:
Tuple[str, Dict]: (url, data) for the POST request
"""
raise NotImplementedError(
"video edit is not supported for this provider"
)
raise NotImplementedError("video edit is not supported for this provider")
def transform_video_edit_response(
self,
@ -346,9 +344,7 @@ class BaseVideoConfig(ABC):
logging_obj: LiteLLMLoggingObj,
custom_llm_provider: Optional[str] = None,
) -> VideoObject:
raise NotImplementedError(
"video edit is not supported for this provider"
)
raise NotImplementedError("video edit is not supported for this provider")
def transform_video_extension_request(
self,
@ -366,9 +362,7 @@ class BaseVideoConfig(ABC):
Returns:
Tuple[str, Dict]: (url, data) for the POST request
"""
raise NotImplementedError(
"video extension is not supported for this provider"
)
raise NotImplementedError("video extension is not supported for this provider")
def transform_video_extension_response(
self,
@ -376,9 +370,7 @@ class BaseVideoConfig(ABC):
logging_obj: LiteLLMLoggingObj,
custom_llm_provider: Optional[str] = None,
) -> VideoObject:
raise NotImplementedError(
"video extension is not supported for this provider"
)
raise NotImplementedError("video extension is not supported for this provider")
def get_error_class(
self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers]

20
litellm/llms/custom_httpx/llm_http_handler.py
View file

@ -6162,7 +6162,10 @@ class BaseLLMHTTPHandler:
litellm_params=dict(litellm_params),
)
url, files_list = video_provider_config.transform_video_create_character_request(
(
url,
files_list,
) = video_provider_config.transform_video_create_character_request(
name=name,
video=video,
api_base=api_base,
@ -6230,7 +6233,10 @@ class BaseLLMHTTPHandler:
litellm_params=dict(litellm_params),
)
url, files_list = video_provider_config.transform_video_create_character_request(
(
url,
files_list,
) = video_provider_config.transform_video_create_character_request(
name=name,
video=video,
api_base=api_base,
@ -6324,11 +6330,7 @@ class BaseLLMHTTPHandler:
)
try:
response = sync_httpx_client.get(
url=url,
headers=headers,
params=params
)
response = sync_httpx_client.get(url=url, headers=headers, params=params)
response.raise_for_status()
return video_provider_config.transform_video_get_character_response(
raw_response=response,
@ -6386,9 +6388,7 @@ class BaseLLMHTTPHandler:
try:
response = await async_httpx_client.get(
url=url,
headers=headers,
params=params
url=url, headers=headers, params=params
)
response.raise_for_status()
return video_provider_config.transform_video_get_character_response(

31
litellm/llms/gemini/videos/transformation.py
View file

@ -525,28 +525,47 @@ class GeminiVideoConfig(BaseVideoConfig):
"""Video delete is not supported."""
raise NotImplementedError("Video delete is not supported by Google Veo.")
def transform_video_create_character_request(self, name, video, api_base, litellm_params, headers):
def transform_video_create_character_request(
self, name, video, api_base, litellm_params, headers
):
raise NotImplementedError("video create character is not supported for Gemini")
def transform_video_create_character_response(self, raw_response, logging_obj):
raise NotImplementedError("video create character is not supported for Gemini")
def transform_video_get_character_request(self, character_id, api_base, litellm_params, headers):
def transform_video_get_character_request(
self, character_id, api_base, litellm_params, headers
):
raise NotImplementedError("video get character is not supported for Gemini")
def transform_video_get_character_response(self, raw_response, logging_obj):
raise NotImplementedError("video get character is not supported for Gemini")
def transform_video_edit_request(self, prompt, video_id, api_base, litellm_params, headers, extra_body=None):
def transform_video_edit_request(
self, prompt, video_id, api_base, litellm_params, headers, extra_body=None
):
raise NotImplementedError("video edit is not supported for Gemini")
def transform_video_edit_response(self, raw_response, logging_obj, custom_llm_provider=None):
def transform_video_edit_response(
self, raw_response, logging_obj, custom_llm_provider=None
):
raise NotImplementedError("video edit is not supported for Gemini")
def transform_video_extension_request(self, prompt, video_id, seconds, api_base, litellm_params, headers, extra_body=None):
def transform_video_extension_request(
self,
prompt,
video_id,
seconds,
api_base,
litellm_params,
headers,
extra_body=None,
):
raise NotImplementedError("video extension is not supported for Gemini")
def transform_video_extension_response(self, raw_response, logging_obj, custom_llm_provider=None):
def transform_video_extension_response(
self, raw_response, logging_obj, custom_llm_provider=None
):
raise NotImplementedError("video extension is not supported for Gemini")
def get_error_class(

18
litellm/llms/moonshot/chat/transformation.py
View file

@ -19,7 +19,8 @@ class MoonshotChatConfig(OpenAIGPTConfig):
@overload
def _transform_messages(
self, messages: List[AllMessageValues], model: str, is_async: Literal[True]
) -> Coroutine[Any, Any, List[AllMessageValues]]: ...
) -> Coroutine[Any, Any, List[AllMessageValues]]:
...
@overload
def _transform_messages(
@ -27,7 +28,8 @@ class MoonshotChatConfig(OpenAIGPTConfig):
messages: List[AllMessageValues],
model: str,
is_async: Literal[False] = False,
) -> List[AllMessageValues]: ...
) -> List[AllMessageValues]:
...
def _transform_messages(
self, messages: List[AllMessageValues], model: str, is_async: bool = False
@ -53,9 +55,13 @@ class MoonshotChatConfig(OpenAIGPTConfig):
messages = handle_messages_with_content_list_to_str_conversion(messages)
if is_async:
return super()._transform_messages(messages=messages, model=model, is_async=True)
return super()._transform_messages(
messages=messages, model=model, is_async=True
)
else:
return super()._transform_messages(messages=messages, model=model, is_async=False)
return super()._transform_messages(
messages=messages, model=model, is_async=False
)
def _get_openai_compatible_provider_info(
self, api_base: Optional[str], api_key: Optional[str]
@ -141,7 +147,9 @@ class MoonshotChatConfig(OpenAIGPTConfig):
optional_params["temperature"] = 0.3
return optional_params
def fill_reasoning_content(self, messages: List[AllMessageValues]) -> List[AllMessageValues]:
def fill_reasoning_content(
self, messages: List[AllMessageValues]
) -> List[AllMessageValues]:
"""
Moonshot reasoning models require `reasoning_content` on every assistant
message that contains tool_calls (multi-turn tool-calling flows).

39
litellm/llms/runwayml/videos/transformation.py
View file

@ -592,28 +592,51 @@ class RunwayMLVideoConfig(BaseVideoConfig):
return video_obj
def transform_video_create_character_request(self, name, video, api_base, litellm_params, headers):
raise NotImplementedError("video create character is not supported for RunwayML")
def transform_video_create_character_request(
self, name, video, api_base, litellm_params, headers
):
raise NotImplementedError(
"video create character is not supported for RunwayML"
)
def transform_video_create_character_response(self, raw_response, logging_obj):
raise NotImplementedError("video create character is not supported for RunwayML")
raise NotImplementedError(
"video create character is not supported for RunwayML"
)
def transform_video_get_character_request(self, character_id, api_base, litellm_params, headers):
def transform_video_get_character_request(
self, character_id, api_base, litellm_params, headers
):
raise NotImplementedError("video get character is not supported for RunwayML")
def transform_video_get_character_response(self, raw_response, logging_obj):
raise NotImplementedError("video get character is not supported for RunwayML")
def transform_video_edit_request(self, prompt, video_id, api_base, litellm_params, headers, extra_body=None):
def transform_video_edit_request(
self, prompt, video_id, api_base, litellm_params, headers, extra_body=None
):
raise NotImplementedError("video edit is not supported for RunwayML")
def transform_video_edit_response(self, raw_response, logging_obj, custom_llm_provider=None):
def transform_video_edit_response(
self, raw_response, logging_obj, custom_llm_provider=None
):
raise NotImplementedError("video edit is not supported for RunwayML")
def transform_video_extension_request(self, prompt, video_id, seconds, api_base, litellm_params, headers, extra_body=None):
def transform_video_extension_request(
self,
prompt,
video_id,
seconds,
api_base,
litellm_params,
headers,
extra_body=None,
):
raise NotImplementedError("video extension is not supported for RunwayML")
def transform_video_extension_response(self, raw_response, logging_obj, custom_llm_provider=None):
def transform_video_extension_response(
self, raw_response, logging_obj, custom_llm_provider=None
):
raise NotImplementedError("video extension is not supported for RunwayML")
def get_error_class(

4
litellm/llms/sagemaker/chat/transformation.py
View file

@ -184,9 +184,7 @@ class SagemakerChatConfig(OpenAIGPTConfig, BaseAWSLLM):
llm_provider = LlmProviders(custom_llm_provider)
except ValueError:
llm_provider = LlmProviders.SAGEMAKER_CHAT
client = get_async_httpx_client(
llm_provider=llm_provider, params={}
)
client = get_async_httpx_client(llm_provider=llm_provider, params={})
try:
response = await client.post(

4
litellm/llms/vertex_ai/batches/transformation.py
View file

@ -142,8 +142,8 @@ class VertexAIBatchTransformation:
Gets the output file id from the Vertex AI Batch response
"""
output_file_id: str = (
response.get("outputInfo", OutputInfo()).get("gcsOutputDirectory", "")
output_file_id: str = response.get("outputInfo", OutputInfo()).get(
"gcsOutputDirectory", ""
)
if output_file_id:
output_file_id = output_file_id.rstrip("/") + "/predictions.jsonl"

39
litellm/llms/vertex_ai/videos/transformation.py
View file

@ -624,28 +624,51 @@ class VertexAIVideoConfig(BaseVideoConfig, VertexBase):
"""Video delete is not supported."""
raise NotImplementedError("Video delete is not supported by Vertex AI Veo.")
def transform_video_create_character_request(self, name, video, api_base, litellm_params, headers):
raise NotImplementedError("video create character is not supported for Vertex AI")
def transform_video_create_character_request(
self, name, video, api_base, litellm_params, headers
):
raise NotImplementedError(
"video create character is not supported for Vertex AI"
)
def transform_video_create_character_response(self, raw_response, logging_obj):
raise NotImplementedError("video create character is not supported for Vertex AI")
raise NotImplementedError(
"video create character is not supported for Vertex AI"
)
def transform_video_get_character_request(self, character_id, api_base, litellm_params, headers):
def transform_video_get_character_request(
self, character_id, api_base, litellm_params, headers
):
raise NotImplementedError("video get character is not supported for Vertex AI")
def transform_video_get_character_response(self, raw_response, logging_obj):
raise NotImplementedError("video get character is not supported for Vertex AI")
def transform_video_edit_request(self, prompt, video_id, api_base, litellm_params, headers, extra_body=None):
def transform_video_edit_request(
self, prompt, video_id, api_base, litellm_params, headers, extra_body=None
):
raise NotImplementedError("video edit is not supported for Vertex AI")
def transform_video_edit_response(self, raw_response, logging_obj, custom_llm_provider=None):
def transform_video_edit_response(
self, raw_response, logging_obj, custom_llm_provider=None
):
raise NotImplementedError("video edit is not supported for Vertex AI")
def transform_video_extension_request(self, prompt, video_id, seconds, api_base, litellm_params, headers, extra_body=None):
def transform_video_extension_request(
self,
prompt,
video_id,
seconds,
api_base,
litellm_params,
headers,
extra_body=None,
):
raise NotImplementedError("video extension is not supported for Vertex AI")
def transform_video_extension_response(self, raw_response, logging_obj, custom_llm_provider=None):
def transform_video_extension_response(
self, raw_response, logging_obj, custom_llm_provider=None
):
raise NotImplementedError("video extension is not supported for Vertex AI")
def get_error_class(

4
litellm/main.py
View file

@ -7533,9 +7533,7 @@ def stream_chunk_builder( # noqa: PLR0915
# the final chunk.
all_annotations: list = []
for ac in annotation_chunks:
all_annotations.extend(
ac["choices"][0]["delta"]["annotations"]
)
all_annotations.extend(ac["choices"][0]["delta"]["annotations"])
response["choices"][0]["message"]["annotations"] = all_annotations
audio_chunks = [

2
litellm/proxy/_experimental/mcp_server/mcp_server_manager.py
View file

@ -1946,7 +1946,7 @@ class MCPServerManager:
incoming_bearer_token: Optional[str] = None
auth_hdr = normalized_raw.get("authorization", "")
if auth_hdr.lower().startswith("bearer "):
incoming_bearer_token = auth_hdr[len("bearer "):]
incoming_bearer_token = auth_hdr[len("bearer ") :]
pre_hook_kwargs = {
"name": name,

12
litellm/proxy/_experimental/mcp_server/rest_endpoints.py
View file

@ -903,12 +903,12 @@ if MCP_AVAILABLE:
try:
client_id, client_secret, scopes = _extract_credentials(request)
_oauth2_flow: Optional[Literal["client_credentials", "authorization_code"]] = (
request.oauth2_flow or (
"client_credentials"
if client_id and client_secret and request.token_url
else None
)
_oauth2_flow: Optional[
Literal["client_credentials", "authorization_code"]
] = request.oauth2_flow or (
"client_credentials"
if client_id and client_secret and request.token_url
else None
)
# client_credentials requires token_url to fetch a token; without it the
# incoming auth header would be dropped with nothing to replace it.

10
litellm/proxy/auth/auth_utils.py
View file

@ -680,7 +680,7 @@ def get_customer_user_header_from_mapping(user_id_mapping) -> Optional[list]:
if customer_headers_mappings:
return customer_headers_mappings
return None
@ -754,15 +754,11 @@ def get_end_user_id_from_request_body(
user_id_str = str(header_value)
if user_id_str.strip():
return user_id_str
elif isinstance(custom_header_name_to_check, str):
for header_name, header_value in request_headers.items():
if header_name.lower() == custom_header_name_to_check.lower():
user_id_str = (
str(header_value)
if header_value is not None
else ""
)
user_id_str = str(header_value) if header_value is not None else ""
if user_id_str.strip():
return user_id_str

2
litellm/proxy/auth/user_api_key_auth.py
View file

@ -730,7 +730,7 @@ async def _user_api_key_auth_builder( # noqa: PLR0915
team_membership: Optional[LiteLLM_TeamMembership] = result.get(
"team_membership", None
)
jwt_claims: Optional[dict] = result.get("jwt_claims", None)
jwt_claims = result.get("jwt_claims", None)
global_proxy_spend = await get_global_proxy_spend(
litellm_proxy_admin_name=litellm_proxy_admin_name,

3
litellm/proxy/batches_endpoints/endpoints.py
View file

@ -537,9 +537,10 @@ async def retrieve_batch( # noqa: PLR0915
)
# Fix: bug_feb14_batch_retrieve_returns_raw_input_file_id
# Resolve raw provider input_file_id to unified ID.
# Resolve raw provider file IDs (input, output, error) to unified IDs.
if unified_batch_id:
await resolve_input_file_id_to_unified(response, prisma_client)
await resolve_output_file_ids_to_unified(response, prisma_client)
### ALERTING ###
asyncio.create_task(

16
litellm/proxy/guardrails/guardrail_hooks/mcp_jwt_signer/mcp_jwt_signer.py
View file

@ -110,7 +110,7 @@ def _load_private_key_from_env(env_var: str) -> RSAPrivateKey:
f"MCPJWTSigner: environment variable '{env_var}' is set but empty."
)
if key_material.startswith("file://"):
path = key_material[len("file://"):]
path = key_material[len("file://") :]
with open(path, "rb") as f:
key_bytes = f.read()
else:
@ -273,9 +273,7 @@ class MCPJWTSigner(CustomGuardrail):
or "litellm"
)
self.audience: str = (
audience
or os.environ.get("MCP_JWT_AUDIENCE")
or self.DEFAULT_AUDIENCE
audience or os.environ.get("MCP_JWT_AUDIENCE") or self.DEFAULT_AUDIENCE
)
resolved_ttl = int(
ttl_seconds
@ -395,8 +393,12 @@ class MCPJWTSigner(CustomGuardrail):
malformed response doesn't permanently disable JWT verification.
"""
now = time.time()
cache_expired = (now - self._oidc_discovery_fetched_at) >= self._OIDC_DISCOVERY_TTL
if (self._oidc_discovery_doc is None or cache_expired) and self.access_token_discovery_uri:
cache_expired = (
now - self._oidc_discovery_fetched_at
) >= self._OIDC_DISCOVERY_TTL
if (
self._oidc_discovery_doc is None or cache_expired
) and self.access_token_discovery_uri:
doc = await _fetch_oidc_discovery(self.access_token_discovery_uri)
if "jwks_uri" in doc:
self._oidc_discovery_doc = doc
@ -560,7 +562,7 @@ class MCPJWTSigner(CustomGuardrail):
value: Optional[str] = None
if source.startswith("token:"):
claim_name = source[len("token:"):]
claim_name = source[len("token:") :]
raw = (jwt_claims or {}).get(claim_name)
value = str(raw) if raw else None

3
litellm/proxy/management_endpoints/internal_user_endpoints.py
View file

@ -2142,8 +2142,7 @@ async def _resolve_org_filter_for_user_search(
member_org_ids: List[str] = []
if caller_user is not None:
member_org_ids = [
m.organization_id
for m in (caller_user.organization_memberships or [])
m.organization_id for m in (caller_user.organization_memberships or [])
]
if member_org_ids:

10
litellm/proxy/management_endpoints/key_management_endpoints.py
View file

@ -1863,16 +1863,10 @@ async def _validate_update_key_data(
user_api_key_cache: Any,
) -> None:
"""Validate permissions and constraints for key update."""
_is_proxy_admin = (
user_api_key_dict.user_role == LitellmUserRoles.PROXY_ADMIN.value
)
_is_proxy_admin = user_api_key_dict.user_role == LitellmUserRoles.PROXY_ADMIN.value
# Prevent non-admin from removing user_id (setting to empty string) (LIT-1884)
if (
data.user_id is not None
and data.user_id == ""
and not _is_proxy_admin
):
if data.user_id is not None and data.user_id == "" and not _is_proxy_admin:
raise HTTPException(
status_code=403,
detail="Non-admin users cannot remove the user_id from a key.",

8
litellm/proxy/management_endpoints/team_endpoints.py
View file

@ -857,7 +857,13 @@ async def new_team( # noqa: PLR0915
# Apply defaults from litellm.default_team_params for any fields
# not explicitly provided in the request.
for field in ("max_budget", "budget_duration", "tpm_limit", "rpm_limit", "team_member_permissions"):
for field in (
"max_budget",
"budget_duration",
"tpm_limit",
"rpm_limit",
"team_member_permissions",
):
if getattr(data, field, None) is None:
default_value = _get_default_team_param(field)
if default_value is not None:

5
litellm/proxy/openai_files_endpoints/common_utils.py
View file

@ -857,7 +857,10 @@ async def update_batch_in_database(
# If the batch_processed column doesn't exist (old schema),
# retry without it so the status update still succeeds.
err_str = str(col_err).lower()
if "batch_processed" in err_str and update_data.get("batch_processed") is not None:
if (
"batch_processed" in err_str
and update_data.get("batch_processed") is not None
):
verbose_proxy_logger.warning(
f"batch_processed column not found, retrying update without it: {col_err}"
)

4
litellm/proxy/response_polling/background_streaming.py
View file

@ -115,7 +115,9 @@ async def background_streaming_task( # noqa: PLR0915
UPDATE_INTERVAL = 0.150 # 150ms batching interval
# Track the terminal event from the stream (may not be "completed")
terminal_status: Optional[ResponsesAPIStatus] = None # Will be set by response.completed/failed/incomplete/cancelled
terminal_status: Optional[
ResponsesAPIStatus
] = None # Will be set by response.completed/failed/incomplete/cancelled
terminal_error = None
_event_to_status = {
"response.completed": "completed",

31
litellm/proxy/spend_tracking/vantage_endpoints.py
View file

@ -40,9 +40,7 @@ def _get_registered_vantage_logger():
return None
async def _set_vantage_settings(
api_key: str, integration_token: str, base_url: str
):
async def _set_vantage_settings(api_key: str, integration_token: str, base_url: str):
"""Store Vantage settings in the database with encrypted API key."""
from litellm.proxy.proxy_server import prisma_client
@ -341,9 +339,7 @@ async def init_vantage_settings(
except HTTPException:
raise
except Exception as e:
verbose_proxy_logger.error(
f"Error initializing Vantage settings: {str(e)}"
)
verbose_proxy_logger.error(f"Error initializing Vantage settings: {str(e)}")
raise HTTPException(
status_code=500,
detail={"error": f"Failed to initialize Vantage settings: {str(e)}"},
@ -395,7 +391,8 @@ async def vantage_dry_run_export(
"""Cast Decimal columns to Float64 so .to_dicts() produces
JSON-serializable float values instead of decimal.Decimal."""
decimal_cols = [
col for col, dtype in zip(frame.columns, frame.dtypes)
col
for col, dtype in zip(frame.columns, frame.dtypes)
if isinstance(dtype, pl.Decimal)
]
if decimal_cols:
@ -404,8 +401,16 @@ async def vantage_dry_run_export(
)
return frame.to_dicts()
usage_sample = _to_json_safe_dicts(data.head(min(50, len(data)))) if not data.is_empty() else []
normalized_sample = _to_json_safe_dicts(normalized.head(min(50, len(normalized)))) if not normalized.is_empty() else []
usage_sample = (
_to_json_safe_dicts(data.head(min(50, len(data))))
if not data.is_empty()
else []
)
normalized_sample = (
_to_json_safe_dicts(normalized.head(min(50, len(normalized))))
if not normalized.is_empty()
else []
)
# Use the same pre-transform column names as
# FocusExportEngine.dry_run_export_usage_data for consistency.
@ -437,14 +442,10 @@ async def vantage_dry_run_export(
except HTTPException:
raise
except Exception as e:
verbose_proxy_logger.error(
f"Error performing Vantage dry run export: {str(e)}"
)
verbose_proxy_logger.error(f"Error performing Vantage dry run export: {str(e)}")
raise HTTPException(
status_code=500,
detail={
"error": f"Failed to perform Vantage dry run export: {str(e)}"
},
detail={"error": f"Failed to perform Vantage dry run export: {str(e)}"},
)

5
litellm/proxy/utils.py
View file

@ -845,7 +845,10 @@ class ProxyLogging:
# key collisions so that the most-specific guardrail (e.g. JWT signer)
# takes precedence over earlier ones.
existing = modified_kwargs.get("extra_headers") or {}
modified_kwargs["extra_headers"] = {**existing, **response_data["extra_headers"]}
modified_kwargs["extra_headers"] = {
**existing,
**response_data["extra_headers"],
}
return modified_kwargs

4
litellm/proxy/video_endpoints/utils.py
View file

@ -7,7 +7,9 @@ from litellm.types.videos.utils import encode_character_id_with_provider
def extract_model_from_target_model_names(target_model_names: Any) -> Optional[str]:
if isinstance(target_model_names, str):
target_model_names = [m.strip() for m in target_model_names.split(",") if m.strip()]
target_model_names = [
m.strip() for m in target_model_names.split(",") if m.strip()
]
elif not isinstance(target_model_names, list):
return None
return target_model_names[0] if target_model_names else None

60
litellm/responses/main.py
View file

@ -692,11 +692,11 @@ def responses(
return run_async_function(aresponses_api_with_mcp, **mcp_call_kwargs)
# get provider config
responses_api_provider_config: Optional[BaseResponsesAPIConfig] = (
ProviderConfigManager.get_provider_responses_api_config(
model=model,
provider=custom_llm_provider,
)
responses_api_provider_config: Optional[
BaseResponsesAPIConfig
] = ProviderConfigManager.get_provider_responses_api_config(
model=model,
provider=custom_llm_provider,
)
local_vars.update(kwargs)
@ -908,11 +908,11 @@ def delete_responses(
raise ValueError("custom_llm_provider is required but passed as None")
# get provider config
responses_api_provider_config: Optional[BaseResponsesAPIConfig] = (
ProviderConfigManager.get_provider_responses_api_config(
model=None,
provider=custom_llm_provider,
)
responses_api_provider_config: Optional[
BaseResponsesAPIConfig
] = ProviderConfigManager.get_provider_responses_api_config(
model=None,
provider=custom_llm_provider,
)
if responses_api_provider_config is None:
@ -1089,11 +1089,11 @@ def get_responses(
raise ValueError("custom_llm_provider is required but passed as None")
# get provider config
responses_api_provider_config: Optional[BaseResponsesAPIConfig] = (
ProviderConfigManager.get_provider_responses_api_config(
model=None,
provider=custom_llm_provider,
)
responses_api_provider_config: Optional[
BaseResponsesAPIConfig
] = ProviderConfigManager.get_provider_responses_api_config(
model=None,
provider=custom_llm_provider,
)
if responses_api_provider_config is None:
@ -1247,11 +1247,11 @@ def list_input_items(
if custom_llm_provider is None:
raise ValueError("custom_llm_provider is required but passed as None")
responses_api_provider_config: Optional[BaseResponsesAPIConfig] = (
ProviderConfigManager.get_provider_responses_api_config(
model=None,
provider=custom_llm_provider,
)
responses_api_provider_config: Optional[
BaseResponsesAPIConfig
] = ProviderConfigManager.get_provider_responses_api_config(
model=None,
provider=custom_llm_provider,
)
if responses_api_provider_config is None:
@ -1406,11 +1406,11 @@ def cancel_responses(
raise ValueError("custom_llm_provider is required but passed as None")
# get provider config
responses_api_provider_config: Optional[BaseResponsesAPIConfig] = (
ProviderConfigManager.get_provider_responses_api_config(
model=None,
provider=custom_llm_provider,
)
responses_api_provider_config: Optional[
BaseResponsesAPIConfig
] = ProviderConfigManager.get_provider_responses_api_config(
model=None,
provider=custom_llm_provider,
)
if responses_api_provider_config is None:
@ -1594,11 +1594,11 @@ def compact_responses(
raise ValueError("custom_llm_provider is required but passed as None")
# get provider config
responses_api_provider_config: Optional[BaseResponsesAPIConfig] = (
ProviderConfigManager.get_provider_responses_api_config(
model=model,
provider=custom_llm_provider,
)
responses_api_provider_config: Optional[
BaseResponsesAPIConfig
] = ProviderConfigManager.get_provider_responses_api_config(
model=model,
provider=custom_llm_provider,
)
if responses_api_provider_config is None:

23
litellm/router.py
View file

@ -8611,6 +8611,7 @@ class Router:
_model_info = deployment.get("model_info", {})
# see if we have the info for this model
_deployment_model = None # per-deployment model name (avoids overwriting the outer `model` group name)
try:
base_model = _model_info.get("base_model", None)
if base_model is None:
@ -8618,7 +8619,7 @@ class Router:
model_info = self.get_router_model_info(
deployment=deployment, received_model_name=model
)
model = base_model or _litellm_params.get("model", None)
_deployment_model = base_model or _litellm_params.get("model", None)
if (
isinstance(model_info, dict)
@ -8632,7 +8633,9 @@ class Router:
_context_window_error = True
_potential_error_str += (
"Model={}, Max Input Tokens={}, Got={}".format(
model, model_info["max_input_tokens"], input_tokens
_deployment_model,
model_info["max_input_tokens"],
input_tokens,
)
)
continue
@ -8688,13 +8691,21 @@ class Router:
## INVALID PARAMS ## -> catch 'gpt-3.5-turbo-16k' not supporting 'response_format' param
if request_kwargs is not None and litellm.drop_params is False:
# get supported params
model, custom_llm_provider, _, _ = litellm.get_llm_provider(
model=model, litellm_params=LiteLLM_Params(**_litellm_params)
# get supported params — use per-deployment model to avoid overwriting the outer model group name
_dep_model_for_params = _deployment_model or model
(
_dep_model_for_params,
custom_llm_provider,
_,
_,
) = litellm.get_llm_provider(
model=_dep_model_for_params,
litellm_params=LiteLLM_Params(**_litellm_params),
)
supported_openai_params = litellm.get_supported_openai_params(
model=model, custom_llm_provider=custom_llm_provider
model=_dep_model_for_params,
custom_llm_provider=custom_llm_provider,
)
if supported_openai_params is None:

9
litellm/setup_wizard.py
View file

@ -319,7 +319,8 @@ class SetupWizard:
@staticmethod
def _select_interactive() -> List[Dict]:
cursor, selected = 0, set()
cursor = 0
selected: set[int] = set()
if _supports_color():
sys.stdout.write(_CURSOR_HIDE)
@ -432,9 +433,9 @@ class SetupWizard:
f" {blue('❯')} Azure deployment name {grey('(e.g. my-gpt4o)')}: "
)
if deployment:
env_vars[f"_LITELLM_AZURE_DEPLOYMENT_{p['id'].upper()}"] = (
deployment
)
env_vars[
f"_LITELLM_AZURE_DEPLOYMENT_{p['id'].upper()}"
] = deployment
# Store the key returned by validation — may be a re-entered replacement
env_vars[p["env_key"]] = SetupWizard._validate_and_report(p, key)

3
litellm/types/proxy/vantage_endpoints.py
View file

@ -39,7 +39,8 @@ class VantageExportRequest(BaseModel):
"""Request model for Vantage export operations (actual export, no default limit)"""
limit: Optional[int] = Field(
None, description="Optional limit on number of records to export (default: no limit)"
None,
description="Optional limit on number of records to export (default: no limit)",
)
start_time_utc: Optional[datetime] = Field(
None, description="Start time for data export in UTC"

4
litellm/types/videos/utils.py
View file

@ -195,7 +195,9 @@ def decode_character_id_with_provider(encoded_character_id: str) -> DecodedChara
character_id=decoded_character_id,
)
except Exception as e:
verbose_logger.debug(f"Error decoding character_id '{encoded_character_id}': {e}")
verbose_logger.debug(
f"Error decoding character_id '{encoded_character_id}': {e}"
)
return DecodedCharacterId(
custom_llm_provider=None,
model_id=None,

34
litellm/videos/main.py
View file

@ -1186,13 +1186,17 @@ def video_create_character(
litellm_params = GenericLiteLLMParams(**kwargs)
provider_config: Optional[BaseVideoConfig] = ProviderConfigManager.get_provider_video_config(
provider_config: Optional[
BaseVideoConfig
] = ProviderConfigManager.get_provider_video_config(
model=None,
provider=litellm.LlmProviders(custom_llm_provider),
)
if provider_config is None:
raise ValueError(f"video create character is not supported for {custom_llm_provider}")
raise ValueError(
f"video create character is not supported for {custom_llm_provider}"
)
local_vars.update(kwargs)
request_params: Dict = {"name": name}
@ -1311,13 +1315,17 @@ def video_get_character(
litellm_params = GenericLiteLLMParams(**kwargs)
provider_config: Optional[BaseVideoConfig] = ProviderConfigManager.get_provider_video_config(
provider_config: Optional[
BaseVideoConfig
] = ProviderConfigManager.get_provider_video_config(
model=None,
provider=litellm.LlmProviders(custom_llm_provider),
)
if provider_config is None:
raise ValueError(f"video get character is not supported for {custom_llm_provider}")
raise ValueError(
f"video get character is not supported for {custom_llm_provider}"
)
local_vars.update(kwargs)
request_params: Dict = {"character_id": character_id}
@ -1439,7 +1447,9 @@ def video_edit(
litellm_params = GenericLiteLLMParams(**kwargs)
provider_config: Optional[BaseVideoConfig] = ProviderConfigManager.get_provider_video_config(
provider_config: Optional[
BaseVideoConfig
] = ProviderConfigManager.get_provider_video_config(
model=None,
provider=litellm.LlmProviders(custom_llm_provider),
)
@ -1572,16 +1582,24 @@ def video_extension(
litellm_params = GenericLiteLLMParams(**kwargs)
provider_config: Optional[BaseVideoConfig] = ProviderConfigManager.get_provider_video_config(
provider_config: Optional[
BaseVideoConfig
] = ProviderConfigManager.get_provider_video_config(
model=None,
provider=litellm.LlmProviders(custom_llm_provider),
)
if provider_config is None:
raise ValueError(f"video extension is not supported for {custom_llm_provider}")
raise ValueError(
f"video extension is not supported for {custom_llm_provider}"
)
local_vars.update(kwargs)
request_params: Dict = {"video_id": video_id, "prompt": prompt, "seconds": seconds}
request_params: Dict = {
"video_id": video_id,
"prompt": prompt,
"seconds": seconds,
}
litellm_logging_obj.update_environment_variables(
model="",

13
tests/spend_tracking_tests/test_spend_accuracy_tests.py
View file

@ -308,16 +308,19 @@ async def test_long_term_spend_accuracy_with_bursts():
response = await chat_completion(session, key)
print(f"Burst 2 - Request {i + 1}/{BURST_2_REQUESTS} completed")
# Poll until key spend reflects burst 2
burst_1_spend = intermediate_key_info["info"]["spend"]
# Poll until key spend reaches expected total (burst 1 + burst 2)
start = time.time()
while time.time() - start < 120:
key_info_check = await get_spend_info(session, "key", key)
current_spend = key_info_check["info"]["spend"]
if current_spend > burst_1_spend:
print(f"Key spend increased to {current_spend} after {time.time() - start:.1f}s")
if abs(current_spend - expected_spend) < TOLERANCE:
print(
f"Total spend reached expected {expected_spend} after {time.time() - start:.1f}s"
)
break
print(f"Key spend still {current_spend}, waiting for burst 2 flush...")
print(
f"Key spend {current_spend}, expected {expected_spend}, waiting..."
)
await asyncio.sleep(10)
# Allow extra time for all entity spend aggregations

82
ui/litellm-dashboard/package-lock.json generated
View file

@ -23,7 +23,7 @@
"jwt-decode": "^4.0.0",
"lucide-react": "^0.513.0",
"moment": "^2.30.1",
"next": "^16.1.6",
"next": "^16.1.7",
"openai": "^4.93.0",
"papaparse": "^5.5.2",
"react": "^18.3.1",
@ -1828,9 +1828,9 @@
}
},
"node_modules/@next/env": {
"version": "16.1.6",
"resolved": "https://registry.npmjs.org/@next/env/-/env-16.1.6.tgz",
"integrity": "sha512-N1ySLuZjnAtN3kFnwhAwPvZah8RJxKasD7x1f8shFqhncnWZn4JMfg37diLNuoHsLAlrDfM3g4mawVdtAG8XLQ==",
"version": "16.1.7",
"resolved": "https://registry.npmjs.org/@next/env/-/env-16.1.7.tgz",
"integrity": "sha512-rJJbIdJB/RQr2F1nylZr/PJzamvNNhfr3brdKP6s/GW850jbtR70QlSfFselvIBbcPUOlQwBakexjFzqLzF6pg==",
"license": "MIT"
},
"node_modules/@next/eslint-plugin-next": {
@ -1844,9 +1844,9 @@
}
},
"node_modules/@next/swc-darwin-arm64": {
"version": "16.1.6",
"resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-16.1.6.tgz",
"integrity": "sha512-wTzYulosJr/6nFnqGW7FrG3jfUUlEf8UjGA0/pyypJl42ExdVgC6xJgcXQ+V8QFn6niSG2Pb8+MIG1mZr2vczw==",
"version": "16.1.7",
"resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-16.1.7.tgz",
"integrity": "sha512-b2wWIE8sABdyafc4IM8r5Y/dS6kD80JRtOGrUiKTsACFQfWWgUQ2NwoUX1yjFMXVsAwcQeNpnucF2ZrujsBBPg==",
"cpu": [
"arm64"
],
@ -1860,9 +1860,9 @@
}
},
"node_modules/@next/swc-darwin-x64": {
"version": "16.1.6",
"resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-16.1.6.tgz",
"integrity": "sha512-BLFPYPDO+MNJsiDWbeVzqvYd4NyuRrEYVB5k2N3JfWncuHAy2IVwMAOlVQDFjj+krkWzhY2apvmekMkfQR0CUQ==",
"version": "16.1.7",
"resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-16.1.7.tgz",
"integrity": "sha512-zcnVaaZulS1WL0Ss38R5Q6D2gz7MtBu8GZLPfK+73D/hp4GFMrC2sudLky1QibfV7h6RJBJs/gOFvYP0X7UVlQ==",
"cpu": [
"x64"
],
@ -1876,9 +1876,9 @@
}
},
"node_modules/@next/swc-linux-arm64-gnu": {
"version": "16.1.6",
"resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-16.1.6.tgz",
"integrity": "sha512-OJYkCd5pj/QloBvoEcJ2XiMnlJkRv9idWA/j0ugSuA34gMT6f5b7vOiCQHVRpvStoZUknhl6/UxOXL4OwtdaBw==",
"version": "16.1.7",
"resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-16.1.7.tgz",
"integrity": "sha512-2ant89Lux/Q3VyC8vNVg7uBaFVP9SwoK2jJOOR0L8TQnX8CAYnh4uctAScy2Hwj2dgjVHqHLORQZJ2wH6VxhSQ==",
"cpu": [
"arm64"
],
@ -1892,9 +1892,9 @@
}
},
"node_modules/@next/swc-linux-arm64-musl": {
"version": "16.1.6",
"resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-16.1.6.tgz",
"integrity": "sha512-S4J2v+8tT3NIO9u2q+S0G5KdvNDjXfAv06OhfOzNDaBn5rw84DGXWndOEB7d5/x852A20sW1M56vhC/tRVbccQ==",
"version": "16.1.7",
"resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-16.1.7.tgz",
"integrity": "sha512-uufcze7LYv0FQg9GnNeZ3/whYfo+1Q3HnQpm16o6Uyi0OVzLlk2ZWoY7j07KADZFY8qwDbsmFnMQP3p3+Ftprw==",
"cpu": [
"arm64"
],
@ -1908,9 +1908,9 @@
}
},
"node_modules/@next/swc-linux-x64-gnu": {
"version": "16.1.6",
"resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-16.1.6.tgz",
"integrity": "sha512-2eEBDkFlMMNQnkTyPBhQOAyn2qMxyG2eE7GPH2WIDGEpEILcBPI/jdSv4t6xupSP+ot/jkfrCShLAa7+ZUPcJQ==",
"version": "16.1.7",
"resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-16.1.7.tgz",
"integrity": "sha512-KWVf2gxYvHtvuT+c4MBOGxuse5TD7DsMFYSxVxRBnOzok/xryNeQSjXgxSv9QpIVlaGzEn/pIuI6Koosx8CGWA==",
"cpu": [
"x64"
],
@ -1924,9 +1924,9 @@
}
},
"node_modules/@next/swc-linux-x64-musl": {
"version": "16.1.6",
"resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-16.1.6.tgz",
"integrity": "sha512-oicJwRlyOoZXVlxmIMaTq7f8pN9QNbdes0q2FXfRsPhfCi8n8JmOZJm5oo1pwDaFbnnD421rVU409M3evFbIqg==",
"version": "16.1.7",
"resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-16.1.7.tgz",
"integrity": "sha512-HguhaGwsGr1YAGs68uRKc4aGWxLET+NevJskOcCAwXbwj0fYX0RgZW2gsOCzr9S11CSQPIkxmoSbuVaBp4Z3dA==",
"cpu": [
"x64"
],
@ -1940,9 +1940,9 @@
}
},
"node_modules/@next/swc-win32-arm64-msvc": {
"version": "16.1.6",
"resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-16.1.6.tgz",
"integrity": "sha512-gQmm8izDTPgs+DCWH22kcDmuUp7NyiJgEl18bcr8irXA5N2m2O+JQIr6f3ct42GOs9c0h8QF3L5SzIxcYAAXXw==",
"version": "16.1.7",
"resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-16.1.7.tgz",
"integrity": "sha512-S0n3KrDJokKTeFyM/vGGGR8+pCmXYrjNTk2ZozOL1C/JFdfUIL9O1ATaJOl5r2POe56iRChbsszrjMAdWSv7kQ==",
"cpu": [
"arm64"
],
@ -1956,9 +1956,9 @@
}
},
"node_modules/@next/swc-win32-x64-msvc": {
"version": "16.1.6",
"resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-16.1.6.tgz",
"integrity": "sha512-NRfO39AIrzBnixKbjuo2YiYhB6o9d8v/ymU9m/Xk8cyVk+k7XylniXkHwjs4s70wedVffc6bQNbufk5v0xEm0A==",
"version": "16.1.7",
"resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-16.1.7.tgz",
"integrity": "sha512-mwgtg8CNZGYm06LeEd+bNnOUfwOyNem/rOiP14Lsz+AnUY92Zq/LXwtebtUiaeVkhbroRCQ0c8GlR4UT1U+0yg==",
"cpu": [
"x64"
],
@ -9343,14 +9343,14 @@
"license": "MIT"
},
"node_modules/next": {
"version": "16.1.6",
"resolved": "https://registry.npmjs.org/next/-/next-16.1.6.tgz",
"integrity": "sha512-hkyRkcu5x/41KoqnROkfTm2pZVbKxvbZRuNvKXLRXxs3VfyO0WhY50TQS40EuKO9SW3rBj/sF3WbVwDACeMZyw==",
"version": "16.1.7",
"resolved": "https://registry.npmjs.org/next/-/next-16.1.7.tgz",
"integrity": "sha512-WM0L7WrSvKwoLegLYr6V+mz+RIofqQgVAfHhMp9a88ms0cFX8iX9ew+snpWlSBwpkURJOUdvCEt3uLl3NNzvWg==",
"license": "MIT",
"dependencies": {
"@next/env": "16.1.6",
"@next/env": "16.1.7",
"@swc/helpers": "0.5.15",
"baseline-browser-mapping": "^2.8.3",
"baseline-browser-mapping": "^2.9.19",
"caniuse-lite": "^1.0.30001579",
"postcss": "8.4.31",
"styled-jsx": "5.1.6"
@ -9362,14 +9362,14 @@
"node": ">=20.9.0"
},
"optionalDependencies": {
"@next/swc-darwin-arm64": "16.1.6",
"@next/swc-darwin-x64": "16.1.6",
"@next/swc-linux-arm64-gnu": "16.1.6",
"@next/swc-linux-arm64-musl": "16.1.6",
"@next/swc-linux-x64-gnu": "16.1.6",
"@next/swc-linux-x64-musl": "16.1.6",
"@next/swc-win32-arm64-msvc": "16.1.6",
"@next/swc-win32-x64-msvc": "16.1.6",
"@next/swc-darwin-arm64": "16.1.7",
"@next/swc-darwin-x64": "16.1.7",
"@next/swc-linux-arm64-gnu": "16.1.7",
"@next/swc-linux-arm64-musl": "16.1.7",
"@next/swc-linux-x64-gnu": "16.1.7",
"@next/swc-linux-x64-musl": "16.1.7",
"@next/swc-win32-arm64-msvc": "16.1.7",
"@next/swc-win32-x64-msvc": "16.1.7",
"sharp": "^0.34.4"
},
"peerDependencies": {

2
ui/litellm-dashboard/package.json
View file

@ -35,7 +35,7 @@
"jwt-decode": "^4.0.0",
"lucide-react": "^0.513.0",
"moment": "^2.30.1",
"next": "^16.1.6",
"next": "^16.1.7",
"openai": "^4.93.0",
"papaparse": "^5.5.2",
"react": "^18.3.1",