scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-26 01:12:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 98

refactor: clear fresh tech debt from the last 24 hours (2026-09-13)

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
mateo 2026-09-13 08:03:59 +00:00
parent 65eddb5fdd
commit a84163f597
7 changed files with 13 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
litellm/cost_calculator.py
View file

@ -1924,8 +1924,8 @@ def _deployment_model_info(
return registered_deployment_info
if litellm_logging_obj is None:
return None
litellm_params: Final = getattr(litellm_logging_obj, "litellm_params", None)
if litellm_params is None:
litellm_params: Final = litellm_logging_obj.litellm_params
if not litellm_params:
return None
return next(
(
@ -1943,7 +1943,9 @@ def _ocr_model_info(
router_model_id: str | None,
) -> OCRPricing | None:
deployment_info: Final = _deployment_model_info(litellm_logging_obj, custom_pricing, router_model_id)
litellm_params: Final = getattr(litellm_logging_obj, "litellm_params", None) if custom_pricing else None
litellm_params: Final = (
litellm_logging_obj.litellm_params if custom_pricing and litellm_logging_obj is not None else None
)
if litellm_params is None:
return deployment_info
return _layered_ocr_pricing(litellm_params, deployment_info)

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

@ -3489,7 +3489,7 @@ class MCPServerManager:
passthrough_server_ids: Final = [
server.server_id
for server in self.get_registry().values()
if getattr(server, "auth_type", None) == MCPAuth.true_passthrough
if server.auth_type == MCPAuth.true_passthrough
]
combined_servers.update(passthrough_server_ids)

6
litellm/proxy/management_endpoints/model_management_endpoints.py
View file

@ -2094,8 +2094,10 @@ async def add_new_model(
enforced=bool(general_settings.get(ENFORCE_RPM_TPM_ON_MODEL_ADD_SETTING, False)),
)
model_params.model_info = ModelInfo( # rebind-ok: downstream team-model handling mutates this same object
**without_server_derived_pricing(model_params.model_info.model_dump(exclude_none=True))
model_params.model_info = (
ModelInfo.model_validate( # rebind-ok: downstream team-model handling mutates this same object
dict(without_server_derived_pricing(model_params.model_info.model_dump(exclude_none=True)))
)
)
model_response: prisma_models.LiteLLM_ProxyModelTable | LiteLLM_ProxyModelTable | None = None

2
litellm/responses/litellm_completion_transformation/transformation.py
View file

@ -2238,7 +2238,7 @@ class LiteLLMCompletionResponsesConfig:
) -> Mapping[str, ResponseFunctionWebSearch]:
calls: Final[dict[str, ResponseFunctionWebSearch]] = {} # mutable-ok: indexes provider-built calls
for choice in chat_completion_response.choices:
provider_fields = getattr(choice.message, "provider_specific_fields", None)
provider_fields = choice.message.provider_specific_fields
if not isinstance(provider_fields, Mapping):
continue
web_search_calls = provider_fields.get("web_search_calls")

6
litellm/rust_bridge/lifecycle.py
View file

@ -147,11 +147,7 @@ def callbacks_needed(logger: Logging, phase: str) -> bool:
_is_debugging_on, # pyright: ignore[reportPrivateUsage] # use the same debug gate as Logging
)
if (
_is_debugging_on()
or getattr(logger, "litellm_request_debug", False)
or os.getenv("LITELLM_PRINT_STANDARD_LOGGING_PAYLOAD")
):
if _is_debugging_on() or logger.litellm_request_debug or os.getenv("LITELLM_PRINT_STANDARD_LOGGING_PAYLOAD"):
return True
input_needed: Final = bool(
litellm.input_callback

2
litellm/types/utils.py
View file

@ -3667,7 +3667,7 @@ def is_server_derived_pricing_key(key: str) -> bool:
return key in SERVER_DERIVED_PRICING_FIELDS or ABOVE_THRESHOLD_COST_KEY_PATTERN.search(key) is not None
def without_server_derived_pricing(model_info: Mapping[str, Any]) -> Mapping[str, Any]:
def without_server_derived_pricing(model_info: Mapping[str, object]) -> Mapping[str, object]:
"""Drop the pricing ``/model/info`` derives for display, keeping everything else.
``/model/info`` fills a deployment's missing pricing in from the cost map so the

2
ui/litellm-dashboard/src/lib/http/schema.d.ts generated vendored
View file

@ -16781,7 +16781,6 @@ export interface paths {
* - permissions: Optional[dict] - [Not Implemented Yet] User-specific permissions, eg. turning off pii masking.
* - metadata: Optional[dict] - Metadata for user, store information for user. Example metadata = {"team": "core-infra", "app": "app2", "email": "ishaan@berri.ai" }
* - max_parallel_requests: Optional[int] - Rate limit a user based on the number of parallel requests. Raises 429 error, if user's parallel requests > x.
* - soft_budget: Optional[float] - Get alerts when user crosses given budget, doesn't block requests.
* - model_max_budget: Optional[dict] - Model-specific max budget for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)
* - budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
* - model_rpm_limit: Optional[float] - Model-specific rpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)
@ -16887,7 +16886,6 @@ export interface paths {
* - permissions: Optional[dict] - [Not Implemented Yet] User-specific permissions, eg. turning off pii masking.
* - metadata: Optional[dict] - Metadata for user, store information for user. Example metadata = {"team": "core-infra", "app": "app2", "email": "ishaan@berri.ai" }
* - max_parallel_requests: Optional[int] - Rate limit a user based on the number of parallel requests. Raises 429 error, if user's parallel requests > x.
* - soft_budget: Optional[float] - Get alerts when user crosses given budget, doesn't block requests.
* - model_max_budget: Optional[dict] - Model-specific max budget for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)
* - budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
* - model_rpm_limit: Optional[float] - Model-specific rpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)