scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-10 22:41:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 83

fix: apply black formatting to modified files

Browse source 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Kavin Anand 2026-04-10 11:43:43 -07:00
parent 4d07f9960f
commit 1d5d30e5f1
4 changed files with 95 additions and 81 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

120
litellm/__init__.py
View file

@ -167,12 +167,12 @@ prometheus_initialize_budget_metrics: Optional[bool] = False
require_auth_for_metrics_endpoint: Optional[bool] = False
argilla_batch_size: Optional[int] = None
datadog_use_v1: Optional[bool] = False # if you want to use v1 datadog logged payload.
gcs_pub_sub_use_v1: Optional[
bool
] = False # if you want to use v1 gcs pubsub logged payload
generic_api_use_v1: Optional[
bool
] = False # if you want to use v1 generic api logged payload
gcs_pub_sub_use_v1: Optional[bool] = (
False # if you want to use v1 gcs pubsub logged payload
)
generic_api_use_v1: Optional[bool] = (
False # if you want to use v1 generic api logged payload
)
argilla_transformation_object: Optional[Dict[str, Any]] = None
_async_input_callback: List[
Union[str, Callable, "CustomLogger"]
@ -192,25 +192,25 @@ _async_failure_callback: List[
pre_call_rules: List[Callable] = []
post_call_rules: List[Callable] = []
turn_off_message_logging: Optional[bool] = False
standard_logging_payload_excluded_fields: Optional[
List[str]
] = None # Fields to exclude from StandardLoggingPayload before callbacks receive it
standard_logging_payload_excluded_fields: Optional[List[str]] = (
None # Fields to exclude from StandardLoggingPayload before callbacks receive it
)
log_raw_request_response: bool = False
redact_messages_in_exceptions: Optional[bool] = False
redact_user_api_key_info: Optional[bool] = False
filter_invalid_headers: Optional[bool] = False
add_user_information_to_llm_headers: Optional[
bool
] = None # adds user_id, team_id, token hash (params from StandardLoggingMetadata) to request headers
add_user_information_to_llm_headers: Optional[bool] = (
None # adds user_id, team_id, token hash (params from StandardLoggingMetadata) to request headers
)
store_audit_logs = False # Enterprise feature, allow users to see audit logs
### end of callbacks #############
email: Optional[
str
] = None # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
token: Optional[
str
] = None # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
email: Optional[str] = (
None # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
)
token: Optional[str] = (
None # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
)
telemetry = True
max_tokens: int = DEFAULT_MAX_TOKENS # OpenAI Defaults
drop_params = bool(os.getenv("LITELLM_DROP_PARAMS", False))
@ -272,9 +272,9 @@ use_client: bool = False
ssl_verify: Union[str, bool] = True
ssl_security_level: Optional[str] = None
ssl_certificate: Optional[str] = None
ssl_ecdh_curve: Optional[
str
] = None # Set to 'X25519' to disable PQC and improve performance
ssl_ecdh_curve: Optional[str] = (
None # Set to 'X25519' to disable PQC and improve performance
)
disable_streaming_logging: bool = False
disable_token_counter: bool = False
disable_add_transform_inline_image_block: bool = False
@ -328,20 +328,24 @@ enable_loadbalancing_on_batch_endpoints: Optional[bool] = None
enable_caching_on_provider_specific_optional_params: bool = (
False # feature-flag for caching on optional params - e.g. 'top_k'
)
caching: bool = False # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
caching_with_models: bool = False # # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
cache: Optional[
"Cache"
] = None # cache object <- use this - https://docs.litellm.ai/docs/caching
caching: bool = (
False # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
)
caching_with_models: bool = (
False # # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
)
cache: Optional["Cache"] = (
None # cache object <- use this - https://docs.litellm.ai/docs/caching
)
default_in_memory_ttl: Optional[float] = None
default_redis_ttl: Optional[float] = None
default_redis_batch_cache_expiry: Optional[float] = None
model_alias_map: Dict[str, str] = {}
model_group_settings: Optional["ModelGroupSettings"] = None
max_budget: float = 0.0 # set the max budget across all providers
budget_duration: Optional[
str
] = None # proxy only - resets budget after fixed duration. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d").
budget_duration: Optional[str] = (
None # proxy only - resets budget after fixed duration. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d").
)
default_soft_budget: float = (
DEFAULT_SOFT_BUDGET # by default all litellm proxy keys have a soft budget of 50.0
)
@ -350,7 +354,9 @@ forward_traceparent_to_llm_provider: bool = False
_current_cost = 0.0 # private variable, used if max budget is set
error_logs: Dict = {}
add_function_to_prompt: bool = False # if function calling not supported by api, append function call details to system prompt
add_function_to_prompt: bool = (
False # if function calling not supported by api, append function call details to system prompt
)
client_session: Optional[httpx.Client] = None
aclient_session: Optional[httpx.AsyncClient] = None
model_fallbacks: Optional[List] = None # Deprecated for 'litellm.fallbacks'
@ -397,7 +403,9 @@ prometheus_emit_stream_label: bool = False
disable_add_prefix_to_prompt: bool = (
False # used by anthropic, to disable adding prefix to prompt
)
disable_copilot_system_to_assistant: bool = False # If false (default), converts all 'system' role messages to 'assistant' for GitHub Copilot compatibility. Set to true to disable this behavior.
disable_copilot_system_to_assistant: bool = (
False # If false (default), converts all 'system' role messages to 'assistant' for GitHub Copilot compatibility. Set to true to disable this behavior.
)
public_mcp_servers: Optional[List[str]] = None
public_model_groups: Optional[List[str]] = None
public_agent_groups: Optional[List[str]] = None
@ -406,9 +414,9 @@ public_agent_groups: Optional[List[str]] = None
# Old format: { "displayName": "url" } (for backward compatibility)
public_model_groups_links: Dict[str, Union[str, Dict[str, Any]]] = {}
#### REQUEST PRIORITIZATION #######
priority_reservation: Optional[
Dict[str, Union[float, "PriorityReservationDict"]]
] = None
priority_reservation: Optional[Dict[str, Union[float, "PriorityReservationDict"]]] = (
None
)
# priority_reservation_settings is lazy-loaded via __getattr__
# Only declare for type checking - at runtime __getattr__ handles it
if TYPE_CHECKING:
@ -416,13 +424,17 @@ if TYPE_CHECKING:
######## Networking Settings ########
use_aiohttp_transport: bool = True # Older variable, aiohttp is now the default. use disable_aiohttp_transport instead.
use_aiohttp_transport: bool = (
True # Older variable, aiohttp is now the default. use disable_aiohttp_transport instead.
)
aiohttp_trust_env: bool = False # set to true to use HTTP_ Proxy settings
disable_aiohttp_transport: bool = False # Set this to true to use httpx instead
disable_aiohttp_trust_env: bool = (
False # When False, aiohttp will respect HTTP(S)_PROXY env vars
)
force_ipv4: bool = False # when True, litellm will force ipv4 for all LLM requests. Some users have seen httpx ConnectionError when using ipv6.
force_ipv4: bool = (
False # when True, litellm will force ipv4 for all LLM requests. Some users have seen httpx ConnectionError when using ipv6.
)
network_mock: bool = False # When True, use mock transport — no real network calls
####### STOP SEQUENCE LIMIT #######
@ -437,13 +449,13 @@ context_window_fallbacks: Optional[List] = None
content_policy_fallbacks: Optional[List] = None
allowed_fails: int = 3
allow_dynamic_callback_disabling: bool = True
num_retries_per_request: Optional[
int
] = None # for the request overall (incl. fallbacks + model retries)
num_retries_per_request: Optional[int] = (
None # for the request overall (incl. fallbacks + model retries)
)
####### SECRET MANAGERS #####################
secret_manager_client: Optional[
Any
] = None # list of instantiated key management clients - e.g. azure kv, infisical, etc.
secret_manager_client: Optional[Any] = (
None # list of instantiated key management clients - e.g. azure kv, infisical, etc.
)
_google_kms_resource_name: Optional[str] = None
_key_management_system: Optional["KeyManagementSystem"] = None
# Note: KeyManagementSettings must be eagerly imported because _key_management_settings
@ -456,12 +468,12 @@ output_parse_pii: bool = False
from litellm.litellm_core_utils.get_model_cost_map import get_model_cost_map
model_cost = get_model_cost_map(url=model_cost_map_url)
cost_discount_config: Dict[
str, float
] = {} # Provider-specific cost discounts {"vertex_ai": 0.05} = 5% discount
cost_margin_config: Dict[
str, Union[float, Dict[str, float]]
] = {} # Provider-specific or global cost margins. Examples:
cost_discount_config: Dict[str, float] = (
{}
) # Provider-specific cost discounts {"vertex_ai": 0.05} = 5% discount
cost_margin_config: Dict[str, Union[float, Dict[str, float]]] = (
{}
) # Provider-specific or global cost margins. Examples:
# Percentage: {"openai": 0.10} = 10% margin
# Fixed: {"openai": {"fixed_amount": 0.001}} = $0.001 per request
# Global: {"global": 0.05} = 5% global margin on all providers
@ -1310,12 +1322,12 @@ from . import rag
from .types.llms.custom_llm import CustomLLMItem
custom_provider_map: List[CustomLLMItem] = []
_custom_providers: List[
str
] = [] # internal helper util, used to track names of custom providers
disable_hf_tokenizer_download: Optional[
bool
] = None # disable huggingface tokenizer download. Defaults to openai clk100
_custom_providers: List[str] = (
[]
) # internal helper util, used to track names of custom providers
disable_hf_tokenizer_download: Optional[bool] = (
None # disable huggingface tokenizer download. Defaults to openai clk100
)
global_disable_no_log_param: bool = False
### CLI UTILITIES ###

2
litellm/constants.py
View file

@ -1422,7 +1422,7 @@ APSCHEDULER_REPLACE_EXISTING = os.getenv(
"1",
] # always replace existing jobs
# The number of tag entries are higher than number of user, team entries. This leads to a higher QPS.
# The number of tag entries are higher than number of user, team entries. This leads to a higher QPS.
# This will run tag spcific tasks at a later time to smooth QPS
DAILY_TAG_SPEND_BATCH_MULTIPLIER = 2.3

6
litellm/litellm_core_utils/get_llm_provider_logic.py
View file

@ -533,7 +533,11 @@ def _get_openai_compatible_provider_info( # noqa: PLR0915
return model, custom_llm_provider, dynamic_api_key, api_base
if custom_llm_provider == "sail_research":
api_base = api_base or get_secret_str("SAIL_API_BASE") or "https://api.sailresearch.com"
api_base = (
api_base
or get_secret_str("SAIL_API_BASE")
or "https://api.sailresearch.com"
)
dynamic_api_key = api_key or get_secret_str("SAIL_API_KEY")
elif custom_llm_provider == "perplexity":
# perplexity is openai compatible, we just need to set this to custom_openai and have the api_base be https://api.perplexity.ai

48
litellm/utils.py
View file

@ -783,9 +783,9 @@ def function_setup( # noqa: PLR0915
coroutine_checker = get_coroutine_checker_fn()
## DYNAMIC CALLBACKS ##
dynamic_callbacks: Optional[
List[Union[str, Callable, "CustomLogger"]]
] = kwargs.pop("callbacks", None)
dynamic_callbacks: Optional[List[Union[str, Callable, "CustomLogger"]]] = (
kwargs.pop("callbacks", None)
)
all_callbacks = get_dynamic_callbacks(dynamic_callbacks=dynamic_callbacks)
if len(all_callbacks) > 0:
@ -1691,9 +1691,9 @@ def client(original_function): # noqa: PLR0915
exception=e,
retry_policy=kwargs.get("retry_policy"),
)
kwargs[
"retry_policy"
] = reset_retry_policy() # prevent infinite loops
kwargs["retry_policy"] = (
reset_retry_policy()
) # prevent infinite loops
litellm.num_retries = (
None # set retries to None to prevent infinite loops
)
@ -1740,9 +1740,9 @@ def client(original_function): # noqa: PLR0915
exception=e,
retry_policy=kwargs.get("retry_policy"),
)
kwargs[
"retry_policy"
] = reset_retry_policy() # prevent infinite loops
kwargs["retry_policy"] = (
reset_retry_policy()
) # prevent infinite loops
litellm.num_retries = (
None # set retries to None to prevent infinite loops
)
@ -3771,10 +3771,10 @@ def pre_process_non_default_params(
if "response_format" in non_default_params:
if provider_config is not None:
non_default_params[
"response_format"
] = provider_config.get_json_schema_from_pydantic_object(
response_format=non_default_params["response_format"]
non_default_params["response_format"] = (
provider_config.get_json_schema_from_pydantic_object(
response_format=non_default_params["response_format"]
)
)
else:
non_default_params["response_format"] = type_to_response_format_param(
@ -3903,16 +3903,16 @@ def pre_process_optional_params(
True # so that main.py adds the function call to the prompt
)
if "tools" in non_default_params:
optional_params[
"functions_unsupported_model"
] = non_default_params.pop("tools")
optional_params["functions_unsupported_model"] = (
non_default_params.pop("tools")
)
non_default_params.pop(
"tool_choice", None
) # causes ollama requests to hang
elif "functions" in non_default_params:
optional_params[
"functions_unsupported_model"
] = non_default_params.pop("functions")
optional_params["functions_unsupported_model"] = (
non_default_params.pop("functions")
)
elif (
litellm.add_function_to_prompt
): # if user opts to add it to prompt instead
@ -4893,9 +4893,7 @@ def _get_order_filtered_deployments(
) -> List:
if target_order is not None:
filtered = [
d
for d in healthy_deployments
if _get_deployment_order(d) == target_order
d for d in healthy_deployments if _get_deployment_order(d) == target_order
]
if filtered:
return filtered
@ -7549,9 +7547,9 @@ class ModelResponseIterator:
if convert_to_delta is True:
_stream_response = ModelResponseStream()
_stream_response.choices[0].delta.content = model_response.choices[0].message.content # type: ignore
self.model_response: Union[
ModelResponse, ModelResponseStream
] = _stream_response
self.model_response: Union[ModelResponse, ModelResponseStream] = (
_stream_response
)
else:
self.model_response = model_response
self.is_done = False