fix: resolve ruff lint errors (#17490)

Fixed 20 of 22 lint errors:

- batches/batch_utils.py: Added missing model_name parameter to functions
- integrations/custom_guardrail.py: Removed unused Tuple import
- llms/custom_httpx/http_handler.py: Removed unused AIOHTTP_NEEDS_CLEANUP_CLOSED import
- llms/anthropic/chat/guardrail_translation/handler.py: Prefixed unused variable with underscore
- llms/openai/responses/guardrail_translation/handler.py: Removed duplicate BaseModel import, prefixed unused variable
- llms/pass_through/guardrail_translation/handler.py: Prefixed unused variables with underscore
- proxy/guardrails/guardrail_hooks/generic_guardrail_api/generic_guardrail_api.py: Removed unused List and Tuple imports
- proxy/hooks/parallel_request_limiter_v3.py: Removed unused import

Remaining 2 errors are PLR0915 (too many statements) which require refactoring.

litellm/batches/batch_utils.py

@@ -15,6 +15,7 @@ from litellm.utils import token_counter
 async def calculate_batch_cost_and_usage(
     file_content_dictionary: List[dict],
     custom_llm_provider: Literal["openai", "azure", "vertex_ai", "hosted_vllm"],
+    model_name: Optional[str] = None,
 ) -> Tuple[float, Usage, List[str]]:
     """
     Calculate the cost and usage of a batch
@@ -37,6 +38,7 @@ async def calculate_batch_cost_and_usage(
 async def _handle_completed_batch(
     batch: Batch,
     custom_llm_provider: Literal["openai", "azure", "vertex_ai", "hosted_vllm"],
+    model_name: Optional[str] = None,
 ) -> Tuple[float, Usage, List[str]]:
     """Helper function to process a completed batch and handle logging"""
     # Get batch results
@@ -83,6 +85,7 @@ def _get_batch_models_from_file_content(
 def _batch_cost_calculator(
     file_content_dictionary: List[dict],
     custom_llm_provider: Literal["openai", "azure", "vertex_ai", "hosted_vllm"] = "openai",
+    model_name: Optional[str] = None,
 ) -> float:
     """
     Calculate the cost of a batch based on the output file id
@@ -251,6 +254,7 @@ def _get_batch_job_cost_from_file_content(
 def _get_batch_job_total_usage_from_file_content(
     file_content_dictionary: List[dict],
     custom_llm_provider: Literal["openai", "azure", "vertex_ai", "hosted_vllm"] = "openai",
+    model_name: Optional[str] = None,
 ) -> Usage:
     """
     Get the tokens of a batch job from the file content

litellm/integrations/custom_guardrail.py

@@ -6,7 +6,6 @@ from typing import (
     List,
     Literal,
     Optional,
-    Tuple,
     Type,
     Union,
     get_args,

litellm/llms/anthropic/chat/guardrail_translation/handler.py

@@ -302,7 +302,7 @@ class AnthropicMessagesHandler(BaseTranslation):
         Get the string so far, check the apply guardrail to the string so far, and return the list of responses so far.
         """
         string_so_far = self.get_streaming_string_so_far(responses_so_far)
-        guardrailed_inputs = await guardrail_to_apply.apply_guardrail(  # allow rejecting the response, if invalid
+        _guardrailed_inputs = await guardrail_to_apply.apply_guardrail(  # allow rejecting the response, if invalid
             inputs={"texts": [string_so_far]},
             request_data={},
             input_type="response",

litellm/llms/custom_httpx/http_handler.py

@@ -18,7 +18,6 @@ from litellm.constants import (
     AIOHTTP_CONNECTOR_LIMIT,
     AIOHTTP_CONNECTOR_LIMIT_PER_HOST,
     AIOHTTP_KEEPALIVE_TIMEOUT,
-    AIOHTTP_NEEDS_CLEANUP_CLOSED,
     AIOHTTP_TTL_DNS_CACHE,
     DEFAULT_SSL_CIPHERS,
 )

litellm/llms/openai/responses/guardrail_translation/handler.py

@@ -32,8 +32,6 @@ from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union, cast
 
 from openai import BaseModel
 
-from openai import BaseModel
-
 from litellm._logging import verbose_proxy_logger
 from litellm.llms.base_llm.guardrail_translation.base_translation import BaseTranslation
 from litellm.responses.litellm_completion_transformation.transformation import (
@@ -339,7 +337,7 @@ class OpenAIResponsesHandler(BaseTranslation):
         Process output streaming response by applying guardrails to text content.
         """
         string_so_far = self.get_streaming_string_so_far(responses_so_far)
-        guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
+        _guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
             inputs={"texts": [string_so_far]},
             request_data={},
             input_type="response",

litellm/llms/pass_through/guardrail_translation/handler.py

@@ -118,7 +118,7 @@ class PassThroughEndpointHandler(BaseTranslation):
             return data
 
         # Apply guardrail (pass-through doesn't modify the text, just checks it)
-        guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
+        _guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
             inputs={"texts": [text_to_check]},
             request_data=data,
             input_type="request",
@@ -178,7 +178,7 @@ class PassThroughEndpointHandler(BaseTranslation):
             request_data["litellm_metadata"] = user_metadata
 
         # Apply guardrail (pass-through doesn't modify the text, just checks it)
-        guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
+        _guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
             inputs={"texts": [text_to_check]},
             request_data=request_data,
             input_type="response",

litellm/proxy/guardrails/guardrail_hooks/generic_guardrail_api/generic_guardrail_api.py

@@ -6,7 +6,7 @@
 #  Thank you users! We ❤️ you! - Krrish & Ishaan
 
 import os
-from typing import TYPE_CHECKING, Any, Dict, List, Literal, Optional, Tuple
+from typing import TYPE_CHECKING, Any, Dict, Literal, Optional
 
 from litellm._logging import verbose_proxy_logger
 from litellm.integrations.custom_guardrail import CustomGuardrail

litellm/proxy/hooks/parallel_request_limiter_v3.py

@@ -1327,7 +1327,6 @@ class _PROXY_MaxParallelRequestsHandler_v3(CustomLogger):
             _get_parent_otel_span_from_kwargs,
         )
         from litellm.proxy.common_utils.callback_utils import (
-            get_metadata_variable_name_from_kwargs,
             get_model_group_from_litellm_kwargs,
         )
         from litellm.types.caching import RedisPipelineIncrementOperation